diff --git a/.DS_Store b/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..1d01355f9dccd782c49204af593e5c54d941a42d Binary files /dev/null and b/.DS_Store differ diff --git a/.gitattributes b/.gitattributes index c7d9f3332a950355d5a77d85000f05e6f45435ea..d18eaa438af5809a2ea87050b775e17c4912061d 100644 --- a/.gitattributes +++ b/.gitattributes @@ -32,3 +32,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7 filter=lfs diff=lfs merge=lfs -text +inference/output/results.mp4 filter=lfs diff=lfs merge=lfs -text +results.mp4 filter=lfs diff=lfs merge=lfs -text +test.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..4480b134e1d9dad6217f84c91d896a247dcc9375 --- /dev/null +++ b/.gitignore @@ -0,0 +1,5 @@ +.env/ +**__pycache__** +*.onnx +*.pt +yolov7/weights/ diff --git a/Readme.md b/Readme.md new file mode 100644 index 0000000000000000000000000000000000000000..a132dfa98b733ac8bf0fbe369e0e2f7fa5321979 --- /dev/null +++ b/Readme.md @@ -0,0 +1,85 @@ +# Yolov7 with ByteTrack + +1. Clone repo. + +``` +git clone https://github.com/axcelerateai/yolov7-bytetrack-streamlit.git +cd yolov7-bytetrack-streamlit +``` + +2. Install requirements. + +### Pip + +``` +python3 -m venv .env +source .env/bin/activate +``` +``` +pip install Cython numpy +``` +``` +pip install -r requirements.txt +``` + +- [Note]: `cython_bbox` have no windows distribution on pypi. If you're a windows user then run following command to install `cython_bbox` from source. + +``` +# for windows +pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox + +# for linux +pip install cython-bbox + +``` + +### conda + +``` +conda env create -f environment.yml +``` + +``` +conda activate yolov7_bytetrack +``` + +- [Note]: `cython_bbox` have no windows distribution on pypi. If you're a windows user then run following command to install `cython_bbox` from source. + +``` +# for windows +pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox + +# for linux +pip install cython-bbox + +``` + + +3. Download weights. + +``` +python download_weights.py +``` + +4. Run stremlit server + +``` +streamlit run yolov7-tiny-demo.py --server.port [LPORT] +``` +- `LPORT` = Local port of system + +### Test yolov7-tiny + +- To run Yolov7-Tiny +``` +streamlit run yolov7-tiny-demo.py --server.port 2085 +``` + +### Test yolov7 +``` +streamlit run yolov7-demo.py --server.port 2085 +``` +### Test yolor +``` +streamlit run yolor-demo.py --server.port 2085 +``` diff --git a/__pycache__/yolo_v7.cpython-310.pyc b/__pycache__/yolo_v7.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0379544b1837b3af49d6313b6115ff68c61a9520 Binary files /dev/null and b/__pycache__/yolo_v7.cpython-310.pyc differ diff --git a/__pycache__/yolo_v7.cpython-39.pyc b/__pycache__/yolo_v7.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..90331a50f12de8aab0495ecdf0bc52e62a327015 Binary files /dev/null and b/__pycache__/yolo_v7.cpython-39.pyc differ diff --git a/__pycache__/yolor.cpython-39.pyc b/__pycache__/yolor.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6136082b4a36430210d3a2e3c9c29a6f2db809a2 Binary files /dev/null and b/__pycache__/yolor.cpython-39.pyc differ diff --git a/byte_track/__init__.py b/byte_track/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..c775de92803401e2fa17c888c3f6645d709bc888 --- /dev/null +++ b/byte_track/__init__.py @@ -0,0 +1,3 @@ +import sys +import os +sys.path.append(os.path.dirname(__file__)) \ No newline at end of file diff --git a/byte_track/__pycache__/__init__.cpython-310.pyc b/byte_track/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c48570aaa08c21b87872b9d9280718285966dada Binary files /dev/null and b/byte_track/__pycache__/__init__.cpython-310.pyc differ diff --git a/byte_track/__pycache__/__init__.cpython-39.pyc b/byte_track/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1e5db6eccf0a15c7828c0a2c5f8a2b5997ca551c Binary files /dev/null and b/byte_track/__pycache__/__init__.cpython-39.pyc differ diff --git a/byte_track/__pycache__/bytetracker.cpython-310.pyc b/byte_track/__pycache__/bytetracker.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2edf5960bffa45a2f86ec5b46fcd8d0de2e60c2d Binary files /dev/null and b/byte_track/__pycache__/bytetracker.cpython-310.pyc differ diff --git a/byte_track/__pycache__/bytetracker.cpython-39.pyc b/byte_track/__pycache__/bytetracker.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..906674c97824811f45e5728660cfd6da337154d0 Binary files /dev/null and b/byte_track/__pycache__/bytetracker.cpython-39.pyc differ diff --git a/byte_track/bytetracker.py b/byte_track/bytetracker.py new file mode 100644 index 0000000000000000000000000000000000000000..d338f77e4bc7ed73f37544f7c2e4cadac595455c --- /dev/null +++ b/byte_track/bytetracker.py @@ -0,0 +1,106 @@ +from .tracker.byte_tracker import BYTETracker +import cv2 +import numpy as np + +class ByteTrack(object): + def __init__(self, detector, min_box_area=10): + self.min_box_area = min_box_area + + self.rgb_means = (0.485, 0.456, 0.406) + self.std = (0.229, 0.224, 0.225) + + self.detector = detector + self.input_shape = tuple(detector.model.get_inputs()[0].shape[2:]) + self.tracker = BYTETracker(frame_rate=30) + + def inference(self, image, conf_thresh=0.25, classes=None): + + dets, image_info = self.detector.detect(image, conf_thres=conf_thresh, input_shape=self.input_shape, classes=classes) + + class_ids=[] + ids=[] + bboxes=[] + scores=[] + + if isinstance(dets, np.ndarray) and len(dets) > 0: + class_ids = dets[:, -1].tolist() + bboxes, ids, scores = self._tracker_update( + dets, + image_info, + ) + # image = self.draw_tracking_info( + # image, + # bboxes, + # ids, + # scores, + # ) + + # return image, len(bboxes), class_ids + return bboxes, ids, scores, class_ids + + def get_id_color(self, index): + temp_index = abs(int(index)) * 3 + color = ((37 * temp_index) % 255, (17 * temp_index) % 255, + (29 * temp_index) % 255) + return color + + def draw_tracking_info( + self, + image, + tlwhs, + ids, + scores, + frame_id=0, + elapsed_time=0., + ): + text_scale = 1.5 + text_thickness = 2 + line_thickness = 2 + + # text = 'frame: %d ' % (frame_id) + # text += 'elapsed time: %.0fms ' % (elapsed_time * 1000) + # text += 'num: %d' % (len(tlwhs)) + # cv2.putText( + # image, + # text, + # (0, int(15 * text_scale)), + # cv2.FONT_HERSHEY_PLAIN, + # 2, + # (0, 255, 0), + # thickness=text_thickness, + # ) + + for index, tlwh in enumerate(tlwhs): + x1, y1 = int(tlwh[0]), int(tlwh[1]) + x2, y2 = x1 + int(tlwh[2]), y1 + int(tlwh[3]) + color = self.get_id_color(ids[index]) + cv2.rectangle(image, (x1, y1), (x2, y2), color, line_thickness) + + text = str(ids[index]) + cv2.putText(image, text, (x1, y1 - 5), cv2.FONT_HERSHEY_PLAIN, + text_scale, (0, 0, 0), text_thickness + 3) + cv2.putText(image, text, (x1, y1 - 5), cv2.FONT_HERSHEY_PLAIN, + text_scale, (255, 255, 255), text_thickness) + return image + + def _tracker_update(self, dets, image_info): + online_targets = [] + if dets is not None: + online_targets = self.tracker.update( + dets[:, :-1], + [image_info['height'], image_info['width']], + [image_info['height'], image_info['width']], + ) + online_tlwhs = [] + online_ids = [] + online_scores = [] + for online_target in online_targets: + tlwh = online_target.tlwh + track_id = online_target.track_id + vertical = tlwh[2] / tlwh[3] > 1.6 + if tlwh[2] * tlwh[3] > self.min_box_area and not vertical: + online_tlwhs.append(tlwh) + online_ids.append(track_id) + online_scores.append(online_target.score) + + return online_tlwhs, online_ids, online_scores \ No newline at end of file diff --git a/byte_track/tracker/__init__.py b/byte_track/tracker/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..a448f52b8518228f01e6074802c6eea886b3f6df --- /dev/null +++ b/byte_track/tracker/__init__.py @@ -0,0 +1,4 @@ +import sys +import os +sys.path.append(os.path.dirname(__file__)) + diff --git a/byte_track/tracker/__pycache__/__init__.cpython-310.pyc b/byte_track/tracker/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fd5a0f0e73bd0a6c2f35d85d74f525ba15239c45 Binary files /dev/null and b/byte_track/tracker/__pycache__/__init__.cpython-310.pyc differ diff --git a/byte_track/tracker/__pycache__/__init__.cpython-39.pyc b/byte_track/tracker/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f4f75636600af3e788dceaac77f54a6062281dce Binary files /dev/null and b/byte_track/tracker/__pycache__/__init__.cpython-39.pyc differ diff --git a/byte_track/tracker/__pycache__/basetrack.cpython-310.pyc b/byte_track/tracker/__pycache__/basetrack.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5a0d3952727e6b0358430529a86498bc7e7b1b73 Binary files /dev/null and b/byte_track/tracker/__pycache__/basetrack.cpython-310.pyc differ diff --git a/byte_track/tracker/__pycache__/basetrack.cpython-39.pyc b/byte_track/tracker/__pycache__/basetrack.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e5916bac0db1712ef68f84a339596c8cf8ed3d85 Binary files /dev/null and b/byte_track/tracker/__pycache__/basetrack.cpython-39.pyc differ diff --git a/byte_track/tracker/__pycache__/byte_tracker.cpython-310.pyc b/byte_track/tracker/__pycache__/byte_tracker.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fb69a3f9328e2bc85d4da3d7043d65f7c7e1a938 Binary files /dev/null and b/byte_track/tracker/__pycache__/byte_tracker.cpython-310.pyc differ diff --git a/byte_track/tracker/__pycache__/byte_tracker.cpython-39.pyc b/byte_track/tracker/__pycache__/byte_tracker.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4c735a9667dd206ec4dfa9515aabdc868c37689e Binary files /dev/null and b/byte_track/tracker/__pycache__/byte_tracker.cpython-39.pyc differ diff --git a/byte_track/tracker/__pycache__/kalman_filter.cpython-310.pyc b/byte_track/tracker/__pycache__/kalman_filter.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..35e316e5f3ba34e5d8d5bc00635f427d8ddacc23 Binary files /dev/null and b/byte_track/tracker/__pycache__/kalman_filter.cpython-310.pyc differ diff --git a/byte_track/tracker/__pycache__/kalman_filter.cpython-39.pyc b/byte_track/tracker/__pycache__/kalman_filter.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1d95a8a9fec0f29d4d78e1da36d6db68fdf7aa9c Binary files /dev/null and b/byte_track/tracker/__pycache__/kalman_filter.cpython-39.pyc differ diff --git a/byte_track/tracker/__pycache__/matching.cpython-310.pyc b/byte_track/tracker/__pycache__/matching.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..eb879bd618f23515e9e35aa2a63f84f09711d0a9 Binary files /dev/null and b/byte_track/tracker/__pycache__/matching.cpython-310.pyc differ diff --git a/byte_track/tracker/__pycache__/matching.cpython-39.pyc b/byte_track/tracker/__pycache__/matching.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9bfde6fc61993f378a4b6ca4b7f0fe568492384e Binary files /dev/null and b/byte_track/tracker/__pycache__/matching.cpython-39.pyc differ diff --git a/byte_track/tracker/basetrack.py b/byte_track/tracker/basetrack.py new file mode 100644 index 0000000000000000000000000000000000000000..a7130b5cc08ac55705c155594d0f2a1d09f96774 --- /dev/null +++ b/byte_track/tracker/basetrack.py @@ -0,0 +1,52 @@ +import numpy as np +from collections import OrderedDict + + +class TrackState(object): + New = 0 + Tracked = 1 + Lost = 2 + Removed = 3 + + +class BaseTrack(object): + _count = 0 + + track_id = 0 + is_activated = False + state = TrackState.New + + history = OrderedDict() + features = [] + curr_feature = None + score = 0 + start_frame = 0 + frame_id = 0 + time_since_update = 0 + + # multi-camera + location = (np.inf, np.inf) + + @property + def end_frame(self): + return self.frame_id + + @staticmethod + def next_id(): + BaseTrack._count += 1 + return BaseTrack._count + + def activate(self, *args): + raise NotImplementedError + + def predict(self): + raise NotImplementedError + + def update(self, *args, **kwargs): + raise NotImplementedError + + def mark_lost(self): + self.state = TrackState.Lost + + def mark_removed(self): + self.state = TrackState.Removed \ No newline at end of file diff --git a/byte_track/tracker/byte_tracker.py b/byte_track/tracker/byte_tracker.py new file mode 100644 index 0000000000000000000000000000000000000000..4c32ca33a566ffb2d383029c5fef2fcecc807126 --- /dev/null +++ b/byte_track/tracker/byte_tracker.py @@ -0,0 +1,326 @@ +import numpy as np +from .kalman_filter import KalmanFilter +import matching +from .basetrack import BaseTrack, TrackState + +class STrack(BaseTrack): + shared_kalman = KalmanFilter() + def __init__(self, tlwh, score): + + # wait activate + self._tlwh = np.asarray(tlwh, dtype=np.float) + self.kalman_filter = None + self.mean, self.covariance = None, None + self.is_activated = False + + self.score = score + self.tracklet_len = 0 + + def predict(self): + mean_state = self.mean.copy() + if self.state != TrackState.Tracked: + mean_state[7] = 0 + self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance) + + @staticmethod + def multi_predict(stracks): + if len(stracks) > 0: + multi_mean = np.asarray([st.mean.copy() for st in stracks]) + multi_covariance = np.asarray([st.covariance for st in stracks]) + for i, st in enumerate(stracks): + if st.state != TrackState.Tracked: + multi_mean[i][7] = 0 + multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(multi_mean, multi_covariance) + for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)): + stracks[i].mean = mean + stracks[i].covariance = cov + + def activate(self, kalman_filter, frame_id): + """Start a new tracklet""" + self.kalman_filter = kalman_filter + self.track_id = self.next_id() + self.mean, self.covariance = self.kalman_filter.initiate(self.tlwh_to_xyah(self._tlwh)) + + self.tracklet_len = 0 + self.state = TrackState.Tracked + if frame_id == 1: + self.is_activated = True + # self.is_activated = True + self.frame_id = frame_id + self.start_frame = frame_id + + def re_activate(self, new_track, frame_id, new_id=False): + self.mean, self.covariance = self.kalman_filter.update( + self.mean, self.covariance, self.tlwh_to_xyah(new_track.tlwh) + ) + self.tracklet_len = 0 + self.state = TrackState.Tracked + self.is_activated = True + self.frame_id = frame_id + if new_id: + self.track_id = self.next_id() + self.score = new_track.score + + def update(self, new_track, frame_id): + """ + Update a matched track + :type new_track: STrack + :type frame_id: int + :type update_feature: bool + :return: + """ + self.frame_id = frame_id + self.tracklet_len += 1 + + new_tlwh = new_track.tlwh + self.mean, self.covariance = self.kalman_filter.update( + self.mean, self.covariance, self.tlwh_to_xyah(new_tlwh)) + self.state = TrackState.Tracked + self.is_activated = True + + self.score = new_track.score + + @property + # @jit(nopython=True) + def tlwh(self): + """Get current position in bounding box format `(top left x, top left y, + width, height)`. + """ + if self.mean is None: + return self._tlwh.copy() + ret = self.mean[:4].copy() + ret[2] *= ret[3] + ret[:2] -= ret[2:] / 2 + return ret + + @property + # @jit(nopython=True) + def tlbr(self): + """Convert bounding box to format `(min x, min y, max x, max y)`, i.e., + `(top left, bottom right)`. + """ + ret = self.tlwh.copy() + ret[2:] += ret[:2] + return ret + + @staticmethod + # @jit(nopython=True) + def tlwh_to_xyah(tlwh): + """Convert bounding box to format `(center x, center y, aspect ratio, + height)`, where the aspect ratio is `width / height`. + """ + ret = np.asarray(tlwh).copy() + ret[:2] += ret[2:] / 2 + ret[2] /= ret[3] + return ret + + def to_xyah(self): + return self.tlwh_to_xyah(self.tlwh) + + @staticmethod + # @jit(nopython=True) + def tlbr_to_tlwh(tlbr): + ret = np.asarray(tlbr).copy() + ret[2:] -= ret[:2] + return ret + + @staticmethod + # @jit(nopython=True) + def tlwh_to_tlbr(tlwh): + ret = np.asarray(tlwh).copy() + ret[2:] += ret[:2] + return ret + + def __repr__(self): + return 'OT_{}_({}-{})'.format(self.track_id, self.start_frame, self.end_frame) + + +class BYTETracker(object): + def __init__(self, track_thresh=0.5,match_thresh=0.8, track_buffer=30, mot20=False, frame_rate=30): + self.tracked_stracks = [] # type: list[STrack] + self.lost_stracks = [] # type: list[STrack] + self.removed_stracks = [] # type: list[STrack] + + self.track_thresh = track_thresh + self.track_buffer = track_buffer + self.mot20 = mot20 + self.match_thresh = match_thresh + + self.frame_id = 0 + self.det_thresh = track_thresh + 0.1 + self.buffer_size = int(frame_rate / 30.0 * self.track_buffer) + self.max_time_lost = self.buffer_size + self.kalman_filter = KalmanFilter() + + def update(self, output_results, img_info, img_size): + self.frame_id += 1 + activated_starcks = [] + refind_stracks = [] + lost_stracks = [] + removed_stracks = [] + + if output_results.shape[1] == 5: + scores = output_results[:, 4] + bboxes = output_results[:, :4] + else: + output_results = output_results.cpu().numpy() + scores = output_results[:, 4] * output_results[:, 5] + bboxes = output_results[:, :4] # x1y1x2y2 + img_h, img_w = img_info[0], img_info[1] + scale = min(img_size[0] / float(img_h), img_size[1] / float(img_w)) + bboxes /= scale + + remain_inds = scores > self.track_thresh + inds_low = scores > 0.1 + inds_high = scores < self.track_thresh + + inds_second = np.logical_and(inds_low, inds_high) + dets_second = bboxes[inds_second] + dets = bboxes[remain_inds] + scores_keep = scores[remain_inds] + scores_second = scores[inds_second] + + if len(dets) > 0: + '''Detections''' + detections = [STrack(STrack.tlbr_to_tlwh(tlbr), s) for + (tlbr, s) in zip(dets, scores_keep)] + else: + detections = [] + + ''' Add newly detected tracklets to tracked_stracks''' + unconfirmed = [] + tracked_stracks = [] # type: list[STrack] + for track in self.tracked_stracks: + if not track.is_activated: + unconfirmed.append(track) + else: + tracked_stracks.append(track) + + ''' Step 2: First association, with high score detection boxes''' + strack_pool = joint_stracks(tracked_stracks, self.lost_stracks) + # Predict the current location with KF + STrack.multi_predict(strack_pool) + dists = matching.iou_distance(strack_pool, detections) + if not self.mot20: + dists = matching.fuse_score(dists, detections) + matches, u_track, u_detection = matching.linear_assignment(dists, thresh=self.match_thresh) + + for itracked, idet in matches: + track = strack_pool[itracked] + det = detections[idet] + if track.state == TrackState.Tracked: + track.update(detections[idet], self.frame_id) + activated_starcks.append(track) + else: + track.re_activate(det, self.frame_id, new_id=False) + refind_stracks.append(track) + + ''' Step 3: Second association, with low score detection boxes''' + # association the untrack to the low score detections + if len(dets_second) > 0: + '''Detections''' + detections_second = [STrack(STrack.tlbr_to_tlwh(tlbr), s) for + (tlbr, s) in zip(dets_second, scores_second)] + else: + detections_second = [] + r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked] + dists = matching.iou_distance(r_tracked_stracks, detections_second) + matches, u_track, u_detection_second = matching.linear_assignment(dists, thresh=0.5) + for itracked, idet in matches: + track = r_tracked_stracks[itracked] + det = detections_second[idet] + if track.state == TrackState.Tracked: + track.update(det, self.frame_id) + activated_starcks.append(track) + else: + track.re_activate(det, self.frame_id, new_id=False) + refind_stracks.append(track) + + for it in u_track: + track = r_tracked_stracks[it] + if not track.state == TrackState.Lost: + track.mark_lost() + lost_stracks.append(track) + + '''Deal with unconfirmed tracks, usually tracks with only one beginning frame''' + detections = [detections[i] for i in u_detection] + dists = matching.iou_distance(unconfirmed, detections) + if not self.mot20: + dists = matching.fuse_score(dists, detections) + matches, u_unconfirmed, u_detection = matching.linear_assignment(dists, thresh=0.7) + for itracked, idet in matches: + unconfirmed[itracked].update(detections[idet], self.frame_id) + activated_starcks.append(unconfirmed[itracked]) + for it in u_unconfirmed: + track = unconfirmed[it] + track.mark_removed() + removed_stracks.append(track) + + """ Step 4: Init new stracks""" + for inew in u_detection: + track = detections[inew] + if track.score < self.det_thresh: + continue + track.activate(self.kalman_filter, self.frame_id) + activated_starcks.append(track) + """ Step 5: Update state""" + for track in self.lost_stracks: + if self.frame_id - track.end_frame > self.max_time_lost: + track.mark_removed() + removed_stracks.append(track) + + # print('Ramained match {} s'.format(t4-t3)) + + self.tracked_stracks = [t for t in self.tracked_stracks if t.state == TrackState.Tracked] + self.tracked_stracks = joint_stracks(self.tracked_stracks, activated_starcks) + self.tracked_stracks = joint_stracks(self.tracked_stracks, refind_stracks) + self.lost_stracks = sub_stracks(self.lost_stracks, self.tracked_stracks) + self.lost_stracks.extend(lost_stracks) + self.lost_stracks = sub_stracks(self.lost_stracks, self.removed_stracks) + self.removed_stracks.extend(removed_stracks) + self.tracked_stracks, self.lost_stracks = remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks) + # get scores of lost tracks + output_stracks = [track for track in self.tracked_stracks if track.is_activated] + + return output_stracks + + +def joint_stracks(tlista, tlistb): + exists = {} + res = [] + for t in tlista: + exists[t.track_id] = 1 + res.append(t) + for t in tlistb: + tid = t.track_id + if not exists.get(tid, 0): + exists[tid] = 1 + res.append(t) + return res + + +def sub_stracks(tlista, tlistb): + stracks = {} + for t in tlista: + stracks[t.track_id] = t + for t in tlistb: + tid = t.track_id + if stracks.get(tid, 0): + del stracks[tid] + return list(stracks.values()) + + +def remove_duplicate_stracks(stracksa, stracksb): + pdist = matching.iou_distance(stracksa, stracksb) + pairs = np.where(pdist < 0.15) + dupa, dupb = list(), list() + for p, q in zip(*pairs): + timep = stracksa[p].frame_id - stracksa[p].start_frame + timeq = stracksb[q].frame_id - stracksb[q].start_frame + if timep > timeq: + dupb.append(q) + else: + dupa.append(p) + resa = [t for i, t in enumerate(stracksa) if not i in dupa] + resb = [t for i, t in enumerate(stracksb) if not i in dupb] + return resa, resb diff --git a/byte_track/tracker/kalman_filter.py b/byte_track/tracker/kalman_filter.py new file mode 100644 index 0000000000000000000000000000000000000000..deda8a26292b81bc6512a8f6145afabde6c16d7a --- /dev/null +++ b/byte_track/tracker/kalman_filter.py @@ -0,0 +1,270 @@ +# vim: expandtab:ts=4:sw=4 +import numpy as np +import scipy.linalg + + +""" +Table for the 0.95 quantile of the chi-square distribution with N degrees of +freedom (contains values for N=1, ..., 9). Taken from MATLAB/Octave's chi2inv +function and used as Mahalanobis gating threshold. +""" +chi2inv95 = { + 1: 3.8415, + 2: 5.9915, + 3: 7.8147, + 4: 9.4877, + 5: 11.070, + 6: 12.592, + 7: 14.067, + 8: 15.507, + 9: 16.919} + + +class KalmanFilter(object): + """ + A simple Kalman filter for tracking bounding boxes in image space. + + The 8-dimensional state space + + x, y, a, h, vx, vy, va, vh + + contains the bounding box center position (x, y), aspect ratio a, height h, + and their respective velocities. + + Object motion follows a constant velocity model. The bounding box location + (x, y, a, h) is taken as direct observation of the state space (linear + observation model). + + """ + + def __init__(self): + ndim, dt = 4, 1. + + # Create Kalman filter model matrices. + self._motion_mat = np.eye(2 * ndim, 2 * ndim) + for i in range(ndim): + self._motion_mat[i, ndim + i] = dt + self._update_mat = np.eye(ndim, 2 * ndim) + + # Motion and observation uncertainty are chosen relative to the current + # state estimate. These weights control the amount of uncertainty in + # the model. This is a bit hacky. + self._std_weight_position = 1. / 20 + self._std_weight_velocity = 1. / 160 + + def initiate(self, measurement): + """Create track from unassociated measurement. + + Parameters + ---------- + measurement : ndarray + Bounding box coordinates (x, y, a, h) with center position (x, y), + aspect ratio a, and height h. + + Returns + ------- + (ndarray, ndarray) + Returns the mean vector (8 dimensional) and covariance matrix (8x8 + dimensional) of the new track. Unobserved velocities are initialized + to 0 mean. + + """ + mean_pos = measurement + mean_vel = np.zeros_like(mean_pos) + mean = np.r_[mean_pos, mean_vel] + + std = [ + 2 * self._std_weight_position * measurement[3], + 2 * self._std_weight_position * measurement[3], + 1e-2, + 2 * self._std_weight_position * measurement[3], + 10 * self._std_weight_velocity * measurement[3], + 10 * self._std_weight_velocity * measurement[3], + 1e-5, + 10 * self._std_weight_velocity * measurement[3]] + covariance = np.diag(np.square(std)) + return mean, covariance + + def predict(self, mean, covariance): + """Run Kalman filter prediction step. + + Parameters + ---------- + mean : ndarray + The 8 dimensional mean vector of the object state at the previous + time step. + covariance : ndarray + The 8x8 dimensional covariance matrix of the object state at the + previous time step. + + Returns + ------- + (ndarray, ndarray) + Returns the mean vector and covariance matrix of the predicted + state. Unobserved velocities are initialized to 0 mean. + + """ + std_pos = [ + self._std_weight_position * mean[3], + self._std_weight_position * mean[3], + 1e-2, + self._std_weight_position * mean[3]] + std_vel = [ + self._std_weight_velocity * mean[3], + self._std_weight_velocity * mean[3], + 1e-5, + self._std_weight_velocity * mean[3]] + motion_cov = np.diag(np.square(np.r_[std_pos, std_vel])) + + #mean = np.dot(self._motion_mat, mean) + mean = np.dot(mean, self._motion_mat.T) + covariance = np.linalg.multi_dot(( + self._motion_mat, covariance, self._motion_mat.T)) + motion_cov + + return mean, covariance + + def project(self, mean, covariance): + """Project state distribution to measurement space. + + Parameters + ---------- + mean : ndarray + The state's mean vector (8 dimensional array). + covariance : ndarray + The state's covariance matrix (8x8 dimensional). + + Returns + ------- + (ndarray, ndarray) + Returns the projected mean and covariance matrix of the given state + estimate. + + """ + std = [ + self._std_weight_position * mean[3], + self._std_weight_position * mean[3], + 1e-1, + self._std_weight_position * mean[3]] + innovation_cov = np.diag(np.square(std)) + + mean = np.dot(self._update_mat, mean) + covariance = np.linalg.multi_dot(( + self._update_mat, covariance, self._update_mat.T)) + return mean, covariance + innovation_cov + + def multi_predict(self, mean, covariance): + """Run Kalman filter prediction step (Vectorized version). + Parameters + ---------- + mean : ndarray + The Nx8 dimensional mean matrix of the object states at the previous + time step. + covariance : ndarray + The Nx8x8 dimensional covariance matrics of the object states at the + previous time step. + Returns + ------- + (ndarray, ndarray) + Returns the mean vector and covariance matrix of the predicted + state. Unobserved velocities are initialized to 0 mean. + """ + std_pos = [ + self._std_weight_position * mean[:, 3], + self._std_weight_position * mean[:, 3], + 1e-2 * np.ones_like(mean[:, 3]), + self._std_weight_position * mean[:, 3]] + std_vel = [ + self._std_weight_velocity * mean[:, 3], + self._std_weight_velocity * mean[:, 3], + 1e-5 * np.ones_like(mean[:, 3]), + self._std_weight_velocity * mean[:, 3]] + sqr = np.square(np.r_[std_pos, std_vel]).T + + motion_cov = [] + for i in range(len(mean)): + motion_cov.append(np.diag(sqr[i])) + motion_cov = np.asarray(motion_cov) + + mean = np.dot(mean, self._motion_mat.T) + left = np.dot(self._motion_mat, covariance).transpose((1, 0, 2)) + covariance = np.dot(left, self._motion_mat.T) + motion_cov + + return mean, covariance + + def update(self, mean, covariance, measurement): + """Run Kalman filter correction step. + + Parameters + ---------- + mean : ndarray + The predicted state's mean vector (8 dimensional). + covariance : ndarray + The state's covariance matrix (8x8 dimensional). + measurement : ndarray + The 4 dimensional measurement vector (x, y, a, h), where (x, y) + is the center position, a the aspect ratio, and h the height of the + bounding box. + + Returns + ------- + (ndarray, ndarray) + Returns the measurement-corrected state distribution. + + """ + projected_mean, projected_cov = self.project(mean, covariance) + + chol_factor, lower = scipy.linalg.cho_factor( + projected_cov, lower=True, check_finite=False) + kalman_gain = scipy.linalg.cho_solve( + (chol_factor, lower), np.dot(covariance, self._update_mat.T).T, + check_finite=False).T + innovation = measurement - projected_mean + + new_mean = mean + np.dot(innovation, kalman_gain.T) + new_covariance = covariance - np.linalg.multi_dot(( + kalman_gain, projected_cov, kalman_gain.T)) + return new_mean, new_covariance + + def gating_distance(self, mean, covariance, measurements, + only_position=False, metric='maha'): + """Compute gating distance between state distribution and measurements. + A suitable distance threshold can be obtained from `chi2inv95`. If + `only_position` is False, the chi-square distribution has 4 degrees of + freedom, otherwise 2. + Parameters + ---------- + mean : ndarray + Mean vector over the state distribution (8 dimensional). + covariance : ndarray + Covariance of the state distribution (8x8 dimensional). + measurements : ndarray + An Nx4 dimensional matrix of N measurements, each in + format (x, y, a, h) where (x, y) is the bounding box center + position, a the aspect ratio, and h the height. + only_position : Optional[bool] + If True, distance computation is done with respect to the bounding + box center position only. + Returns + ------- + ndarray + Returns an array of length N, where the i-th element contains the + squared Mahalanobis distance between (mean, covariance) and + `measurements[i]`. + """ + mean, covariance = self.project(mean, covariance) + if only_position: + mean, covariance = mean[:2], covariance[:2, :2] + measurements = measurements[:, :2] + + d = measurements - mean + if metric == 'gaussian': + return np.sum(d * d, axis=1) + elif metric == 'maha': + cholesky_factor = np.linalg.cholesky(covariance) + z = scipy.linalg.solve_triangular( + cholesky_factor, d.T, lower=True, check_finite=False, + overwrite_b=True) + squared_maha = np.sum(z * z, axis=0) + return squared_maha + else: + raise ValueError('invalid distance metric') \ No newline at end of file diff --git a/byte_track/tracker/matching.py b/byte_track/tracker/matching.py new file mode 100644 index 0000000000000000000000000000000000000000..6f64acea86f1edbfa85e3fcf97f737faf687cf06 --- /dev/null +++ b/byte_track/tracker/matching.py @@ -0,0 +1,178 @@ +import numpy as np +import scipy +import lap +from scipy.spatial.distance import cdist +from cython_bbox import bbox_overlaps as bbox_ious +import kalman_filter + +def merge_matches(m1, m2, shape): + O,P,Q = shape + m1 = np.asarray(m1) + m2 = np.asarray(m2) + + M1 = scipy.sparse.coo_matrix((np.ones(len(m1)), (m1[:, 0], m1[:, 1])), shape=(O, P)) + M2 = scipy.sparse.coo_matrix((np.ones(len(m2)), (m2[:, 0], m2[:, 1])), shape=(P, Q)) + + mask = M1*M2 + match = mask.nonzero() + match = list(zip(match[0], match[1])) + unmatched_O = tuple(set(range(O)) - set([i for i, j in match])) + unmatched_Q = tuple(set(range(Q)) - set([j for i, j in match])) + + return match, unmatched_O, unmatched_Q + + +def _indices_to_matches(cost_matrix, indices, thresh): + matched_cost = cost_matrix[tuple(zip(*indices))] + matched_mask = (matched_cost <= thresh) + + matches = indices[matched_mask] + unmatched_a = tuple(set(range(cost_matrix.shape[0])) - set(matches[:, 0])) + unmatched_b = tuple(set(range(cost_matrix.shape[1])) - set(matches[:, 1])) + + return matches, unmatched_a, unmatched_b + + +def linear_assignment(cost_matrix, thresh): + if cost_matrix.size == 0: + return np.empty((0, 2), dtype=int), tuple(range(cost_matrix.shape[0])), tuple(range(cost_matrix.shape[1])) + matches, unmatched_a, unmatched_b = [], [], [] + cost, x, y = lap.lapjv(cost_matrix, extend_cost=True, cost_limit=thresh) + for ix, mx in enumerate(x): + if mx >= 0: + matches.append([ix, mx]) + unmatched_a = np.where(x < 0)[0] + unmatched_b = np.where(y < 0)[0] + matches = np.asarray(matches) + return matches, unmatched_a, unmatched_b + + +def ious(atlbrs, btlbrs): + """ + Compute cost based on IoU + :type atlbrs: list[tlbr] | np.ndarray + :type atlbrs: list[tlbr] | np.ndarray + + :rtype ious np.ndarray + """ + ious = np.zeros((len(atlbrs), len(btlbrs)), dtype=np.float) + if ious.size == 0: + return ious + + ious = bbox_ious( + np.ascontiguousarray(atlbrs, dtype=np.float), + np.ascontiguousarray(btlbrs, dtype=np.float) + ) + + return ious + + +def iou_distance(atracks, btracks): + """ + Compute cost based on IoU + :type atracks: list[STrack] + :type btracks: list[STrack] + + :rtype cost_matrix np.ndarray + """ + + if (len(atracks)>0 and isinstance(atracks[0], np.ndarray)) or (len(btracks) > 0 and isinstance(btracks[0], np.ndarray)): + atlbrs = atracks + btlbrs = btracks + else: + atlbrs = [track.tlbr for track in atracks] + btlbrs = [track.tlbr for track in btracks] + _ious = ious(atlbrs, btlbrs) + cost_matrix = 1 - _ious + + return cost_matrix + +def v_iou_distance(atracks, btracks): + """ + Compute cost based on IoU + :type atracks: list[STrack] + :type btracks: list[STrack] + + :rtype cost_matrix np.ndarray + """ + + if (len(atracks)>0 and isinstance(atracks[0], np.ndarray)) or (len(btracks) > 0 and isinstance(btracks[0], np.ndarray)): + atlbrs = atracks + btlbrs = btracks + else: + atlbrs = [track.tlwh_to_tlbr(track.pred_bbox) for track in atracks] + btlbrs = [track.tlwh_to_tlbr(track.pred_bbox) for track in btracks] + _ious = ious(atlbrs, btlbrs) + cost_matrix = 1 - _ious + + return cost_matrix + +def embedding_distance(tracks, detections, metric='cosine'): + """ + :param tracks: list[STrack] + :param detections: list[BaseTrack] + :param metric: + :return: cost_matrix np.ndarray + """ + + cost_matrix = np.zeros((len(tracks), len(detections)), dtype=np.float) + if cost_matrix.size == 0: + return cost_matrix + det_features = np.asarray([track.curr_feat for track in detections], dtype=np.float) + #for i, track in enumerate(tracks): + #cost_matrix[i, :] = np.maximum(0.0, cdist(track.smooth_feat.reshape(1,-1), det_features, metric)) + track_features = np.asarray([track.smooth_feat for track in tracks], dtype=np.float) + cost_matrix = np.maximum(0.0, cdist(track_features, det_features, metric)) # Nomalized features + return cost_matrix + + +def gate_cost_matrix(kf, cost_matrix, tracks, detections, only_position=False): + if cost_matrix.size == 0: + return cost_matrix + gating_dim = 2 if only_position else 4 + gating_threshold = kalman_filter.chi2inv95[gating_dim] + measurements = np.asarray([det.to_xyah() for det in detections]) + for row, track in enumerate(tracks): + gating_distance = kf.gating_distance( + track.mean, track.covariance, measurements, only_position) + cost_matrix[row, gating_distance > gating_threshold] = np.inf + return cost_matrix + + +def fuse_motion(kf, cost_matrix, tracks, detections, only_position=False, lambda_=0.98): + if cost_matrix.size == 0: + return cost_matrix + gating_dim = 2 if only_position else 4 + gating_threshold = kalman_filter.chi2inv95[gating_dim] + measurements = np.asarray([det.to_xyah() for det in detections]) + for row, track in enumerate(tracks): + gating_distance = kf.gating_distance( + track.mean, track.covariance, measurements, only_position, metric='maha') + cost_matrix[row, gating_distance > gating_threshold] = np.inf + cost_matrix[row] = lambda_ * cost_matrix[row] + (1 - lambda_) * gating_distance + return cost_matrix + + +def fuse_iou(cost_matrix, tracks, detections): + if cost_matrix.size == 0: + return cost_matrix + reid_sim = 1 - cost_matrix + iou_dist = iou_distance(tracks, detections) + iou_sim = 1 - iou_dist + fuse_sim = reid_sim * (1 + iou_sim) / 2 + det_scores = np.array([det.score for det in detections]) + det_scores = np.expand_dims(det_scores, axis=0).repeat(cost_matrix.shape[0], axis=0) + #fuse_sim = fuse_sim * (1 + det_scores) / 2 + fuse_cost = 1 - fuse_sim + return fuse_cost + + +def fuse_score(cost_matrix, detections): + if cost_matrix.size == 0: + return cost_matrix + iou_sim = 1 - cost_matrix + det_scores = np.array([det.score for det in detections]) + det_scores = np.expand_dims(det_scores, axis=0).repeat(cost_matrix.shape[0], axis=0) + fuse_sim = iou_sim * det_scores + fuse_cost = 1 - fuse_sim + return fuse_cost \ No newline at end of file diff --git a/cfg/yolor_csp.cfg b/cfg/yolor_csp.cfg new file mode 100644 index 0000000000000000000000000000000000000000..9f5f3ab421200036bf5d5c58f9be964f6d2e47a2 --- /dev/null +++ b/cfg/yolor_csp.cfg @@ -0,0 +1,1376 @@ +[net] +# Testing +#batch=1 +#subdivisions=1 +# Training +batch=64 +subdivisions=8 +width=512 +height=512 +channels=3 +momentum=0.949 +decay=0.0005 +angle=0 +saturation = 1.5 +exposure = 1.5 +hue=.1 + +learning_rate=0.00261 +burn_in=1000 +max_batches = 500500 +policy=steps +steps=400000,450000 +scales=.1,.1 + +#cutmix=1 +mosaic=1 + + +# ============ Backbone ============ # + +# Stem + +# 0 +[convolutional] +batch_normalize=1 +filters=32 +size=3 +stride=1 +pad=1 +activation=silu + +# P1 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=2 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=32 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +# 4 (previous+1+3k) +[shortcut] +from=-3 +activation=linear + +# P2 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-10 + +# Transition last + +# 17 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# P3 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(4+3k)] + +[route] +layers = -1,-28 + +# Transition last + +# 48 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# P4 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(3k+4)] + +[route] +layers = -1,-28 + +# Transition last + +# 79 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# P5 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1024 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(3k+4)] + +[route] +layers = -1,-16 + +# Transition last + +# 98 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1024 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Backbone ============ # + +# ============ Neck ============ # + +# CSPSPP + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +### SPP ### +[maxpool] +stride=1 +size=5 + +[route] +layers=-2 + +[maxpool] +stride=1 +size=9 + +[route] +layers=-4 + +[maxpool] +stride=1 +size=13 + +[route] +layers=-1,-3,-5,-6 +### End SPP ### + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1, -13 + +# 113 (previous+6+5+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# End of CSPSPP + + +# FPN-4 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 79 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -6 + +# Transition last + +# 127 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# FPN-3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 48 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -6 + +# Transition last + +# 141 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-4 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=256 +activation=silu + +[route] +layers = -1, 127 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[route] +layers = -1,-6 + +# Transition last + +# 152 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-5 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1, 113 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1,-6 + +# Transition last + +# 163 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Neck ============ # + +# 164 +[implicit_add] +filters=256 + +# 165 +[implicit_add] +filters=512 + +# 166 +[implicit_add] +filters=1024 + +# 167 +[implicit_mul] +filters=255 + +# 168 +[implicit_mul] +filters=255 + +# 169 +[implicit_mul] +filters=255 + +# ============ Head ============ # + +# YOLO-3 + +[route] +layers = 141 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[shift_channels] +from=164 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=167 + +[yolo] +mask = 0,1,2 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-4 + +[route] +layers = 152 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[shift_channels] +from=165 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=168 + +[yolo] +mask = 3,4,5 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-5 + +[route] +layers = 163 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1024 +activation=silu + +[shift_channels] +from=166 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=169 + +[yolo] +mask = 6,7,8 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 diff --git a/cfg/yolor_csp_x.cfg b/cfg/yolor_csp_x.cfg new file mode 100644 index 0000000000000000000000000000000000000000..55a54109bf4882055ebc02b5a8688bfd3d618e4d --- /dev/null +++ b/cfg/yolor_csp_x.cfg @@ -0,0 +1,1576 @@ +[net] +# Testing +#batch=1 +#subdivisions=1 +# Training +batch=64 +subdivisions=8 +width=512 +height=512 +channels=3 +momentum=0.949 +decay=0.0005 +angle=0 +saturation = 1.5 +exposure = 1.5 +hue=.1 + +learning_rate=0.00261 +burn_in=1000 +max_batches = 500500 +policy=steps +steps=400000,450000 +scales=.1,.1 + +#cutmix=1 +mosaic=1 + + +# ============ Backbone ============ # + +# Stem + +# 0 +[convolutional] +batch_normalize=1 +filters=32 +size=3 +stride=1 +pad=1 +activation=silu + +# P1 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=2 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=40 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=silu + +# 4 (previous+1+3k) +[shortcut] +from=-3 +activation=linear + +# P2 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-13 + +# Transition last + +# 20 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +# P3 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(4+3k)] + +[route] +layers = -1,-34 + +# Transition last + +# 57 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# P4 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(3k+4)] + +[route] +layers = -1,-34 + +# Transition last + +# 94 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# P5 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1280 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(3k+4)] + +[route] +layers = -1,-19 + +# Transition last + +# 116 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1280 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Backbone ============ # + +# ============ Neck ============ # + +# CSPSPP + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +### SPP ### +[maxpool] +stride=1 +size=5 + +[route] +layers=-2 + +[maxpool] +stride=1 +size=9 + +[route] +layers=-4 + +[maxpool] +stride=1 +size=13 + +[route] +layers=-1,-3,-5,-6 +### End SPP ### + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[route] +layers = -1, -15 + +# 133 (previous+6+5+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# End of CSPSPP + + +# FPN-4 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 94 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 149 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + + +# FPN-3 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 57 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 165 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-4 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=320 +activation=silu + +[route] +layers = -1, 149 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 178 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-5 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=640 +activation=silu + +[route] +layers = -1, 133 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 191 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Neck ============ # + +# 192 +[implicit_add] +filters=320 + +# 193 +[implicit_add] +filters=640 + +# 194 +[implicit_add] +filters=1280 + +# 195 +[implicit_mul] +filters=255 + +# 196 +[implicit_mul] +filters=255 + +# 197 +[implicit_mul] +filters=255 + +# ============ Head ============ # + +# YOLO-3 + +[route] +layers = 165 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[shift_channels] +from=192 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=195 + +[yolo] +mask = 0,1,2 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-4 + +[route] +layers = 178 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[shift_channels] +from=193 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=196 + +[yolo] +mask = 3,4,5 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-5 + +[route] +layers = 191 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1280 +activation=silu + +[shift_channels] +from=194 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=197 + +[yolo] +mask = 6,7,8 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 diff --git a/cfg/yolor_p6.cfg b/cfg/yolor_p6.cfg new file mode 100644 index 0000000000000000000000000000000000000000..c7fe50c1c5e22c047194c83c8809d4f223a557e9 --- /dev/null +++ b/cfg/yolor_p6.cfg @@ -0,0 +1,1760 @@ +[net] +batch=64 +subdivisions=8 +width=1280 +height=1280 +channels=3 +momentum=0.949 +decay=0.0005 +angle=0 +saturation = 1.5 +exposure = 1.5 +hue=.1 + +learning_rate=0.00261 +burn_in=1000 +max_batches = 500500 +policy=steps +steps=400000,450000 +scales=.1,.1 + +mosaic=1 + + +# ============ Backbone ============ # + +# Stem + +# P1 + +# Downsample + +# 0 +[reorg] + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + + +# P2 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=64 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-12 + +# Transition last + +# 16 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + + +# P3 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=128 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-24 + +# Transition last + +# 43 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# P4 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=384 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=192 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-24 + +# Transition last + +# 70 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + + +# P5 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=256 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-12 + +# Transition last + +# 85 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + + +# P6 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=320 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-12 + +# Transition last + +# 100 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Backbone ============ # + +# ============ Neck ============ # + +# CSPSPP + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +### SPP ### +[maxpool] +stride=1 +size=5 + +[route] +layers=-2 + +[maxpool] +stride=1 +size=9 + +[route] +layers=-4 + +[maxpool] +stride=1 +size=13 + +[route] +layers=-1,-3,-5,-6 +### End SPP ### + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[route] +layers = -1, -13 + +# 115 (previous+6+5+2k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# End of CSPSPP + + +# FPN-5 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 85 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 131 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# FPN-4 + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 70 + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=192 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=192 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=192 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 147 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + + +# FPN-3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 43 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 163 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-4 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=192 +activation=silu + +[route] +layers = -1, 147 + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=192 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=192 +activation=silu + +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=192 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 176 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=192 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-5 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=256 +activation=silu + +[route] +layers = -1, 131 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 189 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-6 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=320 +activation=silu + +[route] +layers = -1, 115 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 202 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Neck ============ # + +# 203 +[implicit_add] +filters=256 + +# 204 +[implicit_add] +filters=384 + +# 205 +[implicit_add] +filters=512 + +# 206 +[implicit_add] +filters=640 + +# 207 +[implicit_mul] +filters=255 + +# 208 +[implicit_mul] +filters=255 + +# 209 +[implicit_mul] +filters=255 + +# 210 +[implicit_mul] +filters=255 + +# ============ Head ============ # + +# YOLO-3 + +[route] +layers = 163 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[shift_channels] +from=203 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=207 + +[yolo] +mask = 0,1,2 +anchors = 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +classes=80 +num=12 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-4 + +[route] +layers = 176 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=384 +activation=silu + +[shift_channels] +from=204 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=208 + +[yolo] +mask = 3,4,5 +anchors = 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +classes=80 +num=12 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-5 + +[route] +layers = 189 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[shift_channels] +from=205 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=209 + +[yolo] +mask = 6,7,8 +anchors = 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +classes=80 +num=12 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-6 + +[route] +layers = 202 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[shift_channels] +from=206 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=210 + +[yolo] +mask = 9,10,11 +anchors = 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +classes=80 +num=12 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + +# ============ End of Head ============ # diff --git a/cfg/yolor_w6.cfg b/cfg/yolor_w6.cfg new file mode 100644 index 0000000000000000000000000000000000000000..b91167a2e06a1f0f15d9c88234d9c5971c3ad29c --- /dev/null +++ b/cfg/yolor_w6.cfg @@ -0,0 +1,1760 @@ +[net] +batch=64 +subdivisions=8 +width=1280 +height=1280 +channels=3 +momentum=0.949 +decay=0.0005 +angle=0 +saturation = 1.5 +exposure = 1.5 +hue=.1 + +learning_rate=0.00261 +burn_in=1000 +max_batches = 500500 +policy=steps +steps=400000,450000 +scales=.1,.1 + +mosaic=1 + + +# ============ Backbone ============ # + +# Stem + +# P1 + +# Downsample + +# 0 +[reorg] + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + + +# P2 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=64 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-12 + +# Transition last + +# 16 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + + +# P3 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=128 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-24 + +# Transition last + +# 43 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# P4 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=256 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-24 + +# Transition last + +# 70 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + + +# P5 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=768 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=384 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=384 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=384 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=384 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-12 + +# Transition last + +# 85 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=768 +size=1 +stride=1 +pad=1 +activation=silu + + +# P6 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1024 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first +# +#[convolutional] +#batch_normalize=1 +#filters=512 +#size=1 +#stride=1 +#pad=1 +#activation=silu + +# Merge [-1, -(3k+3)] + +[route] +layers = -1,-12 + +# Transition last + +# 100 (previous+6+3k) +[convolutional] +batch_normalize=1 +filters=1024 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Backbone ============ # + +# ============ Neck ============ # + +# CSPSPP + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +### SPP ### +[maxpool] +stride=1 +size=5 + +[route] +layers=-2 + +[maxpool] +stride=1 +size=9 + +[route] +layers=-4 + +[maxpool] +stride=1 +size=13 + +[route] +layers=-1,-3,-5,-6 +### End SPP ### + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1, -13 + +# 115 (previous+6+5+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# End of CSPSPP + + +# FPN-5 + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 85 + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=384 +activation=silu + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=384 +activation=silu + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=384 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 131 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + + +# FPN-4 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 70 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 147 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# FPN-3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 43 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 163 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-4 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=256 +activation=silu + +[route] +layers = -1, 147 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 176 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-5 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=384 +activation=silu + +[route] +layers = -1, 131 + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=384 +activation=silu + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=384 +activation=silu + +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=384 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 189 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=384 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-6 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1, 115 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 202 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Neck ============ # + +# 203 +[implicit_add] +filters=256 + +# 204 +[implicit_add] +filters=512 + +# 205 +[implicit_add] +filters=768 + +# 206 +[implicit_add] +filters=1024 + +# 207 +[implicit_mul] +filters=255 + +# 208 +[implicit_mul] +filters=255 + +# 209 +[implicit_mul] +filters=255 + +# 210 +[implicit_mul] +filters=255 + +# ============ Head ============ # + +# YOLO-3 + +[route] +layers = 163 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[shift_channels] +from=203 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=207 + +[yolo] +mask = 0,1,2 +anchors = 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +classes=80 +num=12 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-4 + +[route] +layers = 176 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[shift_channels] +from=204 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=208 + +[yolo] +mask = 3,4,5 +anchors = 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +classes=80 +num=12 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-5 + +[route] +layers = 189 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=768 +activation=silu + +[shift_channels] +from=205 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=209 + +[yolo] +mask = 6,7,8 +anchors = 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +classes=80 +num=12 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-6 + +[route] +layers = 202 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1024 +activation=silu + +[shift_channels] +from=206 + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[control_channels] +from=210 + +[yolo] +mask = 9,10,11 +anchors = 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +classes=80 +num=12 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + +# ============ End of Head ============ # diff --git a/cfg/yolov4_csp.cfg b/cfg/yolov4_csp.cfg new file mode 100644 index 0000000000000000000000000000000000000000..c387ce968e193fa396e920c40914fb3fa5640df1 --- /dev/null +++ b/cfg/yolov4_csp.cfg @@ -0,0 +1,1334 @@ +[net] +# Testing +#batch=1 +#subdivisions=1 +# Training +batch=64 +subdivisions=8 +width=512 +height=512 +channels=3 +momentum=0.949 +decay=0.0005 +angle=0 +saturation = 1.5 +exposure = 1.5 +hue=.1 + +learning_rate=0.00261 +burn_in=1000 +max_batches = 500500 +policy=steps +steps=400000,450000 +scales=.1,.1 + +#cutmix=1 +mosaic=1 + + +# ============ Backbone ============ # + +# Stem + +# 0 +[convolutional] +batch_normalize=1 +filters=32 +size=3 +stride=1 +pad=1 +activation=silu + +# P1 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=2 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=32 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +# 4 (previous+1+3k) +[shortcut] +from=-3 +activation=linear + +# P2 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-10 + +# Transition last + +# 17 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# P3 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(4+3k)] + +[route] +layers = -1,-28 + +# Transition last + +# 48 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# P4 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(3k+4)] + +[route] +layers = -1,-28 + +# Transition last + +# 79 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# P5 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1024 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(3k+4)] + +[route] +layers = -1,-16 + +# Transition last + +# 98 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1024 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Backbone ============ # + +# ============ Neck ============ # + +# CSPSPP + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +### SPP ### +[maxpool] +stride=1 +size=5 + +[route] +layers=-2 + +[maxpool] +stride=1 +size=9 + +[route] +layers=-4 + +[maxpool] +stride=1 +size=13 + +[route] +layers=-1,-3,-5,-6 +### End SPP ### + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1, -13 + +# 113 (previous+6+5+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# End of CSPSPP + + +# FPN-4 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 79 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -6 + +# Transition last + +# 127 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# FPN-3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 48 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -6 + +# Transition last + +# 141 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-4 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=256 +activation=silu + +[route] +layers = -1, 127 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[route] +layers = -1,-6 + +# Transition last + +# 152 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-5 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1, 113 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[route] +layers = -1,-6 + +# Transition last + +# 163 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Neck ============ # + +# ============ Head ============ # + +# YOLO-3 + +[route] +layers = 141 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=silu + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[yolo] +mask = 0,1,2 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-4 + +[route] +layers = 152 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=silu + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[yolo] +mask = 3,4,5 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-5 + +[route] +layers = 163 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1024 +activation=silu + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[yolo] +mask = 6,7,8 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 diff --git a/cfg/yolov4_csp_x.cfg b/cfg/yolov4_csp_x.cfg new file mode 100644 index 0000000000000000000000000000000000000000..285abc4d871f4313e631fcf6c1d090f2e389d636 --- /dev/null +++ b/cfg/yolov4_csp_x.cfg @@ -0,0 +1,1534 @@ +[net] +# Testing +#batch=1 +#subdivisions=1 +# Training +batch=64 +subdivisions=8 +width=512 +height=512 +channels=3 +momentum=0.949 +decay=0.0005 +angle=0 +saturation = 1.5 +exposure = 1.5 +hue=.1 + +learning_rate=0.00261 +burn_in=1000 +max_batches = 500500 +policy=steps +steps=400000,450000 +scales=.1,.1 + +#cutmix=1 +mosaic=1 + + +# ============ Backbone ============ # + +# Stem + +# 0 +[convolutional] +batch_normalize=1 +filters=32 +size=3 +stride=1 +pad=1 +activation=silu + +# P1 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=2 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=40 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=silu + +# 4 (previous+1+3k) +[shortcut] +from=-3 +activation=linear + +# P2 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-13 + +# Transition last + +# 20 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +# P3 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(4+3k)] + +[route] +layers = -1,-34 + +# Transition last + +# 57 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# P4 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(3k+4)] + +[route] +layers = -1,-34 + +# Transition last + +# 94 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# P5 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1280 +size=3 +stride=2 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=silu + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# Merge [-1 -(3k+4)] + +[route] +layers = -1,-19 + +# Transition last + +# 116 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1280 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Backbone ============ # + +# ============ Neck ============ # + +# CSPSPP + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +### SPP ### +[maxpool] +stride=1 +size=5 + +[route] +layers=-2 + +[maxpool] +stride=1 +size=9 + +[route] +layers=-4 + +[maxpool] +stride=1 +size=13 + +[route] +layers=-1,-3,-5,-6 +### End SPP ### + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[route] +layers = -1, -15 + +# 133 (previous+6+5+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# End of CSPSPP + + +# FPN-4 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 94 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 149 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + + +# FPN-3 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[upsample] +stride=2 + +[route] +layers = 57 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=silu + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=silu + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 165 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-4 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=320 +activation=silu + +[route] +layers = -1, 149 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 178 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=silu + + +# PAN-5 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=640 +activation=silu + +[route] +layers = -1, 133 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[route] +layers = -1,-8 + +# Transition last + +# 191 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=silu + +# ============ End of Neck ============ # + +# ============ Head ============ # + +# YOLO-3 + +[route] +layers = 165 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=silu + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[yolo] +mask = 0,1,2 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-4 + +[route] +layers = 178 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=silu + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[yolo] +mask = 3,4,5 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-5 + +[route] +layers = 191 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1280 +activation=silu + +[convolutional] +size=1 +stride=1 +pad=1 +filters=255 +activation=linear + +[yolo] +mask = 6,7,8 +anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 +classes=80 +num=9 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 diff --git a/cfg/yolov4_p6.cfg b/cfg/yolov4_p6.cfg new file mode 100644 index 0000000000000000000000000000000000000000..1a4088414ba37efa2aca4cf9d20c45aa21458d3d --- /dev/null +++ b/cfg/yolov4_p6.cfg @@ -0,0 +1,2260 @@ +[net] +batch=64 +subdivisions=8 +width=1280 +height=1280 +channels=3 +momentum=0.949 +decay=0.0005 +angle=0 +saturation = 1.5 +exposure = 1.5 +hue=.1 + +learning_rate=0.00261 +burn_in=1000 +max_batches = 500500 +policy=steps +steps=400000,450000 +scales=.1,.1 + +mosaic=1 + + +# ============ Backbone ============ # + +# Stem + +# 0 +[convolutional] +batch_normalize=1 +filters=32 +size=3 +stride=1 +pad=1 +activation=mish + + +# P1 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=32 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=32 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=32 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=32 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=32 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-7 + +# Transition last + +# 10 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=mish + + +# P2 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-13 + +# Transition last + +# 26 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + + +# P3 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-49 + +# Transition last + +# 78 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + + +# P4 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-49 + +# Transition last + +# 130 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + + +# P5 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1024 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-25 + +# Transition last + +# 158 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1024 +size=1 +stride=1 +pad=1 +activation=mish + + +# P6 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1024 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-25 + +# Transition last + +# 186 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1024 +size=1 +stride=1 +pad=1 +activation=mish + +# ============ End of Backbone ============ # + +# ============ Neck ============ # + +# CSPSPP + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +### SPP ### +[maxpool] +stride=1 +size=5 + +[route] +layers=-2 + +[maxpool] +stride=1 +size=9 + +[route] +layers=-4 + +[maxpool] +stride=1 +size=13 + +[route] +layers=-1,-3,-5,-6 +### End SPP ### + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[route] +layers = -1, -13 + +# 201 (previous+6+5+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# End of CSPSPP + + +# FPN-5 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[upsample] +stride=2 + +[route] +layers = 158 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 217 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + + +# FPN-4 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[upsample] +stride=2 + +[route] +layers = 130 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=mish + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 233 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + + +# FPN-3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[upsample] +stride=2 + +[route] +layers = 78 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=mish + +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=128 +activation=mish + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 249 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=mish + + +# PAN-4 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=256 +activation=mish + +[route] +layers = -1, 233 + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=mish + +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=mish + +[route] +layers = -1,-8 + +# Transition last + +# 262 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=mish + + +# PAN-5 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=512 +activation=mish + +[route] +layers = -1, 217 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[route] +layers = -1,-8 + +# Transition last + +# 275 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + + +# PAN-6 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=512 +activation=mish + +[route] +layers = -1, 201 + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[route] +layers = -1,-8 + +# Transition last + +# 288 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=mish + +# ============ End of Neck ============ # + +# ============ Head ============ # + +# YOLO-3 + +[route] +layers = 249 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=256 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 0,1,2,3 +anchors = 13,17, 31,25, 24,51, 61,45, 61,45, 48,102, 119,96, 97,189, 97,189, 217,184, 171,384, 324,451, 324,451, 545,357, 616,618, 1024,1024 +classes=80 +num=16 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-4 + +[route] +layers = 262 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=512 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 4,5,6,7 +anchors = 13,17, 31,25, 24,51, 61,45, 61,45, 48,102, 119,96, 97,189, 97,189, 217,184, 171,384, 324,451, 324,451, 545,357, 616,618, 1024,1024 +classes=80 +num=16 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-5 + +[route] +layers = 275 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1024 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 8,9,10,11 +anchors = 13,17, 31,25, 24,51, 61,45, 61,45, 48,102, 119,96, 97,189, 97,189, 217,184, 171,384, 324,451, 324,451, 545,357, 616,618, 1024,1024 +classes=80 +num=16 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-6 + +[route] +layers = 288 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1024 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 12,13,14,15 +anchors = 13,17, 31,25, 24,51, 61,45, 61,45, 48,102, 119,96, 97,189, 97,189, 217,184, 171,384, 324,451, 324,451, 545,357, 616,618, 1024,1024 +classes=80 +num=16 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + +# ============ End of Head ============ # diff --git a/cfg/yolov4_p7.cfg b/cfg/yolov4_p7.cfg new file mode 100644 index 0000000000000000000000000000000000000000..10379a0e759265d9cc39c8926e2606f46fa1083b --- /dev/null +++ b/cfg/yolov4_p7.cfg @@ -0,0 +1,2714 @@ +[net] +batch=64 +subdivisions=8 +width=1536 +height=1536 +channels=3 +momentum=0.949 +decay=0.0005 +angle=0 +saturation = 1.5 +exposure = 1.5 +hue=.1 + +learning_rate=0.00261 +burn_in=1000 +max_batches = 500500 +policy=steps +steps=400000,450000 +scales=.1,.1 + +mosaic=1 + + +# ============ Backbone ============ # + +# Stem + +# 0 +[convolutional] +batch_normalize=1 +filters=40 +size=3 +stride=1 +pad=1 +activation=mish + + +# P1 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=40 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=40 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=40 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=40 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=40 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-7 + +# Transition last + +# 10 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=mish + + +# P2 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=80 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=80 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-13 + +# Transition last + +# 26 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + + +# P3 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-49 + +# Transition last + +# 78 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + + +# P4 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-49 + +# Transition last + +# 130 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + + +# P5 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1280 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-25 + +# Transition last + +# 158 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1280 +size=1 +stride=1 +pad=1 +activation=mish + + +# P6 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1280 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-25 + +# Transition last + +# 186 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1280 +size=1 +stride=1 +pad=1 +activation=mish + + +# P7 + +# Downsample + +[convolutional] +batch_normalize=1 +filters=1280 +size=3 +stride=2 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Residual Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=3 +stride=1 +pad=1 +activation=mish + +[shortcut] +from=-3 +activation=linear + +# Transition first + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Merge [-1, -(3k+4)] + +[route] +layers = -1,-25 + +# Transition last + +# 214 (previous+7+3k) +[convolutional] +batch_normalize=1 +filters=1280 +size=1 +stride=1 +pad=1 +activation=mish + +# ============ End of Backbone ============ # + +# ============ Neck ============ # + +# CSPSPP + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +### SPP ### +[maxpool] +stride=1 +size=5 + +[route] +layers=-2 + +[maxpool] +stride=1 +size=9 + +[route] +layers=-4 + +[maxpool] +stride=1 +size=13 + +[route] +layers=-1,-3,-5,-6 +### End SPP ### + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[route] +layers = -1, -13 + +# 229 (previous+6+5+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# End of CSPSPP + + +# FPN-6 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[upsample] +stride=2 + +[route] +layers = 186 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 245 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + + +# FPN-5 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[upsample] +stride=2 + +[route] +layers = 158 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 261 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + + +# FPN-4 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[upsample] +stride=2 + +[route] +layers = 130 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=mish + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 277 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + + +# FPN-3 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[upsample] +stride=2 + +[route] +layers = 78 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -1, -3 + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=mish + +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=160 +activation=mish + +# Merge [-1, -(2k+2)] + +[route] +layers = -1, -8 + +# Transition last + +# 293 (previous+6+4+2k) +[convolutional] +batch_normalize=1 +filters=160 +size=1 +stride=1 +pad=1 +activation=mish + + +# PAN-4 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=320 +activation=mish + +[route] +layers = -1, 277 + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=mish + +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=mish + +[route] +layers = -1,-8 + +# Transition last + +# 306 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=320 +size=1 +stride=1 +pad=1 +activation=mish + + +# PAN-5 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=640 +activation=mish + +[route] +layers = -1, 261 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[route] +layers = -1,-8 + +# Transition last + +# 319 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + + +# PAN-6 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=640 +activation=mish + +[route] +layers = -1, 245 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[route] +layers = -1,-8 + +# Transition last + +# 332 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + + +# PAN-7 + +[convolutional] +batch_normalize=1 +size=3 +stride=2 +pad=1 +filters=640 +activation=mish + +[route] +layers = -1, 229 + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# Split + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[route] +layers = -2 + +# Plain Block + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[route] +layers = -1,-8 + +# Transition last + +# 345 (previous+3+4+2k) +[convolutional] +batch_normalize=1 +filters=640 +size=1 +stride=1 +pad=1 +activation=mish + +# ============ End of Neck ============ # + +# ============ Head ============ # + +# YOLO-3 + +[route] +layers = 293 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=320 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 0,1,2,3 +anchors = 13,17, 22,25, 27,66, 55,41, 57,88, 112,69, 69,177, 136,138, 136,138, 287,114, 134,275, 268,248, 268,248, 232,504, 445,416, 640,640, 812,393, 477,808, 1070,908, 1408,1408 +classes=80 +num=20 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-4 + +[route] +layers = 306 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=640 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 4,5,6,7 +anchors = 13,17, 22,25, 27,66, 55,41, 57,88, 112,69, 69,177, 136,138, 136,138, 287,114, 134,275, 268,248, 268,248, 232,504, 445,416, 640,640, 812,393, 477,808, 1070,908, 1408,1408 +classes=80 +num=20 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-5 + +[route] +layers = 319 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1280 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 8,9,10,11 +anchors = 13,17, 22,25, 27,66, 55,41, 57,88, 112,69, 69,177, 136,138, 136,138, 287,114, 134,275, 268,248, 268,248, 232,504, 445,416, 640,640, 812,393, 477,808, 1070,908, 1408,1408 +classes=80 +num=20 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-6 + +[route] +layers = 332 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1280 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 12,13,14,15 +anchors = 13,17, 22,25, 27,66, 55,41, 57,88, 112,69, 69,177, 136,138, 136,138, 287,114, 134,275, 268,248, 268,248, 232,504, 445,416, 640,640, 812,393, 477,808, 1070,908, 1408,1408 +classes=80 +num=20 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + + +# YOLO-7 + +[route] +layers = 345 + +[convolutional] +batch_normalize=1 +size=3 +stride=1 +pad=1 +filters=1280 +activation=mish + +[convolutional] +size=1 +stride=1 +pad=1 +filters=340 +activation=linear + +[yolo] +mask = 16,17,18,19 +anchors = 13,17, 22,25, 27,66, 55,41, 57,88, 112,69, 69,177, 136,138, 136,138, 287,114, 134,275, 268,248, 268,248, 232,504, 445,416, 640,640, 812,393, 477,808, 1070,908, 1408,1408 +classes=80 +num=20 +jitter=.3 +ignore_thresh = .7 +truth_thresh = 1 +random=1 +scale_x_y = 1.05 +iou_thresh=0.213 +cls_normalizer=1.0 +iou_normalizer=0.07 +iou_loss=ciou +nms_kind=greedynms +beta_nms=0.6 + +# ============ End of Head ============ # diff --git a/data/coco.names b/data/coco.names new file mode 100644 index 0000000000000000000000000000000000000000..941cb4e1392266f6a6c09b1fdc5f79503b2e5df6 --- /dev/null +++ b/data/coco.names @@ -0,0 +1,80 @@ +person +bicycle +car +motorcycle +airplane +bus +train +truck +boat +traffic light +fire hydrant +stop sign +parking meter +bench +bird +cat +dog +horse +sheep +cow +elephant +bear +zebra +giraffe +backpack +umbrella +handbag +tie +suitcase +frisbee +skis +snowboard +sports ball +kite +baseball bat +baseball glove +skateboard +surfboard +tennis racket +bottle +wine glass +cup +fork +knife +spoon +bowl +banana +apple +sandwich +orange +broccoli +carrot +hot dog +pizza +donut +cake +chair +couch +potted plant +bed +dining table +toilet +tv +laptop +mouse +remote +keyboard +cell phone +microwave +oven +toaster +sink +refrigerator +book +clock +vase +scissors +teddy bear +hair drier +toothbrush diff --git a/data/coco.yaml b/data/coco.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9ecc707d85a9be0fc5e735f98e09c3931c4fcc96 --- /dev/null +++ b/data/coco.yaml @@ -0,0 +1,18 @@ +# train and val datasets (image directory or *.txt file with image paths) +train: ../coco/train2017.txt # 118k images +val: ../coco/val2017.txt # 5k images +test: ../coco/test-dev2017.txt # 20k images for submission to https://competitions.codalab.org/competitions/20794 + +# number of classes +nc: 80 + +# class names +names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', + 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', + 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', + 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', + 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', + 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', + 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', + 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', + 'hair drier', 'toothbrush'] diff --git a/data/hyp.finetune.1280.yaml b/data/hyp.finetune.1280.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d3ebbe10f1e6c70007eed0d38d31afba3c0348aa --- /dev/null +++ b/data/hyp.finetune.1280.yaml @@ -0,0 +1,28 @@ +lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) +lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf) +momentum: 0.937 # SGD momentum/Adam beta1 +weight_decay: 0.0005 # optimizer weight decay 5e-4 +warmup_epochs: 3.0 # warmup epochs (fractions ok) +warmup_momentum: 0.8 # warmup initial momentum +warmup_bias_lr: 0.1 # warmup initial bias lr +box: 0.05 # box loss gain +cls: 0.5 # cls loss gain +cls_pw: 1.0 # cls BCELoss positive_weight +obj: 1.0 # obj loss gain (scale with pixels) +obj_pw: 1.0 # obj BCELoss positive_weight +iou_t: 0.20 # IoU training threshold +anchor_t: 4.0 # anchor-multiple threshold +# anchors: 3 # anchors per output layer (0 to ignore) +fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) +hsv_h: 0.015 # image HSV-Hue augmentation (fraction) +hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) +hsv_v: 0.4 # image HSV-Value augmentation (fraction) +degrees: 0.0 # image rotation (+/- deg) +translate: 0.5 # image translation (+/- fraction) +scale: 0.8 # image scale (+/- gain) +shear: 0.0 # image shear (+/- deg) +perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 +flipud: 0.0 # image flip up-down (probability) +fliplr: 0.5 # image flip left-right (probability) +mosaic: 1.0 # image mosaic (probability) +mixup: 0.2 # image mixup (probability) diff --git a/data/hyp.scratch.1280.yaml b/data/hyp.scratch.1280.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3b0f84b96ade2d97bb91ab6e6e4765cb5a64606b --- /dev/null +++ b/data/hyp.scratch.1280.yaml @@ -0,0 +1,28 @@ +lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) +lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf) +momentum: 0.937 # SGD momentum/Adam beta1 +weight_decay: 0.0005 # optimizer weight decay 5e-4 +warmup_epochs: 3.0 # warmup epochs (fractions ok) +warmup_momentum: 0.8 # warmup initial momentum +warmup_bias_lr: 0.1 # warmup initial bias lr +box: 0.05 # box loss gain +cls: 0.5 # cls loss gain +cls_pw: 1.0 # cls BCELoss positive_weight +obj: 1.0 # obj loss gain (scale with pixels) +obj_pw: 1.0 # obj BCELoss positive_weight +iou_t: 0.20 # IoU training threshold +anchor_t: 4.0 # anchor-multiple threshold +# anchors: 3 # anchors per output layer (0 to ignore) +fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) +hsv_h: 0.015 # image HSV-Hue augmentation (fraction) +hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) +hsv_v: 0.4 # image HSV-Value augmentation (fraction) +degrees: 0.0 # image rotation (+/- deg) +translate: 0.5 # image translation (+/- fraction) +scale: 0.5 # image scale (+/- gain) +shear: 0.0 # image shear (+/- deg) +perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 +flipud: 0.0 # image flip up-down (probability) +fliplr: 0.5 # image flip left-right (probability) +mosaic: 1.0 # image mosaic (probability) +mixup: 0.0 # image mixup (probability) diff --git a/data/hyp.scratch.640.yaml b/data/hyp.scratch.640.yaml new file mode 100644 index 0000000000000000000000000000000000000000..00e458ae3a562bb1b03e832ca8d31703c7c24c4f --- /dev/null +++ b/data/hyp.scratch.640.yaml @@ -0,0 +1,28 @@ +lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) +lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf) +momentum: 0.937 # SGD momentum/Adam beta1 +weight_decay: 0.0005 # optimizer weight decay 5e-4 +warmup_epochs: 3.0 # warmup epochs (fractions ok) +warmup_momentum: 0.8 # warmup initial momentum +warmup_bias_lr: 0.1 # warmup initial bias lr +box: 0.05 # box loss gain +cls: 0.3 # cls loss gain +cls_pw: 1.0 # cls BCELoss positive_weight +obj: 0.7 # obj loss gain (scale with pixels) +obj_pw: 1.0 # obj BCELoss positive_weight +iou_t: 0.20 # IoU training threshold +anchor_t: 4.0 # anchor-multiple threshold +# anchors: 3 # anchors per output layer (0 to ignore) +fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) +hsv_h: 0.015 # image HSV-Hue augmentation (fraction) +hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) +hsv_v: 0.4 # image HSV-Value augmentation (fraction) +degrees: 0.0 # image rotation (+/- deg) +translate: 0.1 # image translation (+/- fraction) +scale: 0.9 # image scale (+/- gain) +shear: 0.0 # image shear (+/- deg) +perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 +flipud: 0.0 # image flip up-down (probability) +fliplr: 0.5 # image flip left-right (probability) +mosaic: 1.0 # image mosaic (probability) +mixup: 0.0 # image mixup (probability) diff --git a/deep_sort_pytorch/.DS_Store b/deep_sort_pytorch/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..03ce5b7b8f7e9d04f249929f023b58114b4ef969 Binary files /dev/null and b/deep_sort_pytorch/.DS_Store differ diff --git a/deep_sort_pytorch/.gitignore b/deep_sort_pytorch/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..37ed2f4dc4a1ca945a0d807274bfe2f6cc7e2fec --- /dev/null +++ b/deep_sort_pytorch/.gitignore @@ -0,0 +1,13 @@ +# Folders +__pycache__/ +build/ +*.egg-info + + +# Files +*.weights +*.t7 +*.mp4 +*.avi +*.so +*.txt diff --git a/deep_sort_pytorch/LICENSE b/deep_sort_pytorch/LICENSE new file mode 100644 index 0000000000000000000000000000000000000000..92a1ed5dc27676f33e306463d532e4969fbc42ae --- /dev/null +++ b/deep_sort_pytorch/LICENSE @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2020 Ziqiang + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. \ No newline at end of file diff --git a/deep_sort_pytorch/README.md b/deep_sort_pytorch/README.md new file mode 100644 index 0000000000000000000000000000000000000000..6073f8064faeaa5dfe6ec9642830b5506d02276f --- /dev/null +++ b/deep_sort_pytorch/README.md @@ -0,0 +1,137 @@ +# Deep Sort with PyTorch + +![](demo/demo.gif) + +## Update(1-1-2020) +Changes +- fix bugs +- refactor code +- accerate detection by adding nms on gpu + +## Latest Update(07-22) +Changes +- bug fix (Thanks @JieChen91 and @yingsen1 for bug reporting). +- using batch for feature extracting for each frame, which lead to a small speed up. +- code improvement. + +Futher improvement direction +- Train detector on specific dataset rather than the official one. +- Retrain REID model on pedestrain dataset for better performance. +- Replace YOLOv3 detector with advanced ones. + +**Any contributions to this repository is welcome!** + + +## Introduction +This is an implement of MOT tracking algorithm deep sort. Deep sort is basicly the same with sort but added a CNN model to extract features in image of human part bounded by a detector. This CNN model is indeed a RE-ID model and the detector used in [PAPER](https://arxiv.org/abs/1703.07402) is FasterRCNN , and the original source code is [HERE](https://github.com/nwojke/deep_sort). +However in original code, the CNN model is implemented with tensorflow, which I'm not familier with. SO I re-implemented the CNN feature extraction model with PyTorch, and changed the CNN model a little bit. Also, I use **YOLOv3** to generate bboxes instead of FasterRCNN. + +## Dependencies +- python 3 (python2 not sure) +- numpy +- scipy +- opencv-python +- sklearn +- torch >= 0.4 +- torchvision >= 0.1 +- pillow +- vizer +- edict + +## Quick Start +0. Check all dependencies installed +```bash +pip install -r requirements.txt +``` +for user in china, you can specify pypi source to accelerate install like: +```bash +pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple +``` + +1. Clone this repository +``` +git clone git@github.com:ZQPei/deep_sort_pytorch.git +``` + +2. Download YOLOv3 parameters +``` +cd detector/YOLOv3/weight/ +wget https://pjreddie.com/media/files/yolov3.weights +wget https://pjreddie.com/media/files/yolov3-tiny.weights +cd ../../../ +``` + +3. Download deepsort parameters ckpt.t7 +``` +cd deep_sort/deep/checkpoint +# download ckpt.t7 from +https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6 to this folder +cd ../../../ +``` + +4. Compile nms module +```bash +cd detector/YOLOv3/nms +sh build.sh +cd ../../.. +``` + +Notice: +If compiling failed, the simplist way is to **Upgrade your pytorch >= 1.1 and torchvision >= 0.3" and you can avoid the troublesome compiling problems which are most likely caused by either `gcc version too low` or `libraries missing`. + +5. Run demo +``` +usage: python yolov3_deepsort.py VIDEO_PATH + [--help] + [--frame_interval FRAME_INTERVAL] + [--config_detection CONFIG_DETECTION] + [--config_deepsort CONFIG_DEEPSORT] + [--display] + [--display_width DISPLAY_WIDTH] + [--display_height DISPLAY_HEIGHT] + [--save_path SAVE_PATH] + [--cpu] + +# yolov3 + deepsort +python yolov3_deepsort.py [VIDEO_PATH] + +# yolov3_tiny + deepsort +python yolov3_deepsort.py [VIDEO_PATH] --config_detection ./configs/yolov3_tiny.yaml + +# yolov3 + deepsort on webcam +python3 yolov3_deepsort.py /dev/video0 --camera 0 + +# yolov3_tiny + deepsort on webcam +python3 yolov3_deepsort.py /dev/video0 --config_detection ./configs/yolov3_tiny.yaml --camera 0 +``` +Use `--display` to enable display. +Results will be saved to `./output/results.avi` and `./output/results.txt`. + +All files above can also be accessed from BaiduDisk! +linker：[BaiduDisk](https://pan.baidu.com/s/1YJ1iPpdFTlUyLFoonYvozg) +passwd：fbuw + +## Training the RE-ID model +The original model used in paper is in original_model.py, and its parameter here [original_ckpt.t7](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6). + +To train the model, first you need download [Market1501](http://www.liangzheng.com.cn/Project/project_reid.html) dataset or [Mars](http://www.liangzheng.com.cn/Project/project_mars.html) dataset. + +Then you can try [train.py](deep_sort/deep/train.py) to train your own parameter and evaluate it using [test.py](deep_sort/deep/test.py) and [evaluate.py](deep_sort/deep/evalute.py). +![train.jpg](deep_sort/deep/train.jpg) + +## Demo videos and images +[demo.avi](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6) +[demo2.avi](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6) + +![1.jpg](demo/1.jpg) +![2.jpg](demo/2.jpg) + + +## References +- paper: [Simple Online and Realtime Tracking with a Deep Association Metric](https://arxiv.org/abs/1703.07402) + +- code: [nwojke/deep_sort](https://github.com/nwojke/deep_sort) + +- paper: [YOLOv3](https://pjreddie.com/media/files/papers/YOLOv3.pdf) + +- code: [Joseph Redmon/yolov3](https://pjreddie.com/darknet/yolo/) diff --git a/deep_sort_pytorch/configs/deep_sort.yaml b/deep_sort_pytorch/configs/deep_sort.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f91a9c1ac5d2b1d4e3030d42f4f9d4c3476738e3 --- /dev/null +++ b/deep_sort_pytorch/configs/deep_sort.yaml @@ -0,0 +1,10 @@ +DEEPSORT: + REID_CKPT: "deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7" + MAX_DIST: 0.2 + MIN_CONFIDENCE: 0.3 + NMS_MAX_OVERLAP: 0.5 + MAX_IOU_DISTANCE: 0.7 + MAX_AGE: 70 + N_INIT: 3 + NN_BUDGET: 100 + diff --git a/deep_sort_pytorch/deep_sort/.DS_Store b/deep_sort_pytorch/deep_sort/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..cade4b8f753bd97506811270e35eee6d3fc66860 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/.DS_Store differ diff --git a/deep_sort_pytorch/deep_sort/README.md b/deep_sort_pytorch/deep_sort/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e89c9b3ea08691210046fbb9184bf8e44e88f29e --- /dev/null +++ b/deep_sort_pytorch/deep_sort/README.md @@ -0,0 +1,3 @@ +# Deep Sort + +This is the implemention of deep sort with pytorch. \ No newline at end of file diff --git a/deep_sort_pytorch/deep_sort/__init__.py b/deep_sort_pytorch/deep_sort/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..5fe5d0fd796ec4f46dc4141f5e4f9f5092f7d321 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/__init__.py @@ -0,0 +1,21 @@ +from .deep_sort import DeepSort + + +__all__ = ['DeepSort', 'build_tracker'] + + +def build_tracker(cfg, use_cuda): + return DeepSort(cfg.DEEPSORT.REID_CKPT, + max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE, + nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE, + max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET, use_cuda=use_cuda) + + + + + + + + + + diff --git a/deep_sort_pytorch/deep_sort/__pycache__/__init__.cpython-310.pyc b/deep_sort_pytorch/deep_sort/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..dace3412f347f061d13f5e22ff925012ad3c2bfc Binary files /dev/null and b/deep_sort_pytorch/deep_sort/__pycache__/__init__.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/__pycache__/__init__.cpython-39.pyc b/deep_sort_pytorch/deep_sort/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..20c4c21070cb8cfdbb5a634820971db217080aa0 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/__pycache__/__init__.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/__pycache__/deep_sort.cpython-310.pyc b/deep_sort_pytorch/deep_sort/__pycache__/deep_sort.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..aefeb8c5e1138af22e5388de66f3c4b4f1a83754 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/__pycache__/deep_sort.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/__pycache__/deep_sort.cpython-39.pyc b/deep_sort_pytorch/deep_sort/__pycache__/deep_sort.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2c702f921d3eaea2cd031d49021fc0507f483556 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/__pycache__/deep_sort.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/deep/__init__.py b/deep_sort_pytorch/deep_sort/deep/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/deep_sort_pytorch/deep_sort/deep/__pycache__/__init__.cpython-310.pyc b/deep_sort_pytorch/deep_sort/deep/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f6daf740e8f6d3d21b4eda00b661e8c50ad25c9a Binary files /dev/null and b/deep_sort_pytorch/deep_sort/deep/__pycache__/__init__.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/deep/__pycache__/__init__.cpython-39.pyc b/deep_sort_pytorch/deep_sort/deep/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..22be394eee3b8ce3ac44de9bffd24793edc2e550 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/deep/__pycache__/__init__.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/deep/__pycache__/feature_extractor.cpython-310.pyc b/deep_sort_pytorch/deep_sort/deep/__pycache__/feature_extractor.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..948bb7221e7d4e65cc9596f3af880386baae3592 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/deep/__pycache__/feature_extractor.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/deep/__pycache__/feature_extractor.cpython-39.pyc b/deep_sort_pytorch/deep_sort/deep/__pycache__/feature_extractor.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7a29a5ef2b502cdc8a2e9305d5e47cbebf0cd6cc Binary files /dev/null and b/deep_sort_pytorch/deep_sort/deep/__pycache__/feature_extractor.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/deep/__pycache__/model.cpython-310.pyc b/deep_sort_pytorch/deep_sort/deep/__pycache__/model.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8689bbde61d542506788390dfd63e585acaf56cd Binary files /dev/null and b/deep_sort_pytorch/deep_sort/deep/__pycache__/model.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/deep/__pycache__/model.cpython-39.pyc b/deep_sort_pytorch/deep_sort/deep/__pycache__/model.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..69eeb91ad88e9d0dd282c2b7db93a4dd9ff99f35 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/deep/__pycache__/model.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/deep/checkpoint/.gitkeep b/deep_sort_pytorch/deep_sort/deep/checkpoint/.gitkeep new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7 b/deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7 new file mode 100644 index 0000000000000000000000000000000000000000..cd7ceebe86bdfaea299f31994844488295f00ca8 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df75ddef42c3d1bda67bc94b093e7ce61de7f75a89f36a8f868a428462198316 +size 46034619 diff --git a/deep_sort_pytorch/deep_sort/deep/evaluate.py b/deep_sort_pytorch/deep_sort/deep/evaluate.py new file mode 100644 index 0000000000000000000000000000000000000000..a0458ace6993dcae9f820e076f8c5dcc62d592ca --- /dev/null +++ b/deep_sort_pytorch/deep_sort/deep/evaluate.py @@ -0,0 +1,13 @@ +import torch + +features = torch.load("features.pth") +qf = features["qf"] +ql = features["ql"] +gf = features["gf"] +gl = features["gl"] + +scores = qf.mm(gf.t()) +res = scores.topk(5, dim=1)[1][:, 0] +top1correct = gl[res].eq(ql).sum().item() + +print("Acc top1:{:.3f}".format(top1correct / ql.size(0))) diff --git a/deep_sort_pytorch/deep_sort/deep/feature_extractor.py b/deep_sort_pytorch/deep_sort/deep/feature_extractor.py new file mode 100644 index 0000000000000000000000000000000000000000..a342cf5b6021dcc009ea7e4d35f6f28e298bda65 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/deep/feature_extractor.py @@ -0,0 +1,54 @@ +import torch +import torchvision.transforms as transforms +import numpy as np +import cv2 +import logging + +from .model import Net + + +class Extractor(object): + def __init__(self, model_path, use_cuda=True): + self.net = Net(reid=True) + self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu" + state_dict = torch.load(model_path, map_location=torch.device(self.device))[ + 'net_dict'] + self.net.load_state_dict(state_dict) + logger = logging.getLogger("root.tracker") + logger.info("Loading weights from {}... Done!".format(model_path)) + self.net.to(self.device) + self.size = (64, 128) + self.norm = transforms.Compose([ + transforms.ToTensor(), + transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]), + ]) + + def _preprocess(self, im_crops): + """ + TODO: + 1. to float with scale from 0 to 1 + 2. resize to (64, 128) as Market1501 dataset did + 3. concatenate to a numpy array + 3. to torch Tensor + 4. normalize + """ + def _resize(im, size): + return cv2.resize(im.astype(np.float32)/255., size) + + im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze( + 0) for im in im_crops], dim=0).float() + return im_batch + + def __call__(self, im_crops): + im_batch = self._preprocess(im_crops) + with torch.no_grad(): + im_batch = im_batch.to(self.device) + features = self.net(im_batch) + return features.cpu().numpy() + + +if __name__ == '__main__': + img = cv2.imread("demo.jpg")[:, :, (2, 1, 0)] + extr = Extractor("checkpoint/ckpt.t7") + feature = extr(img) + print(feature.shape) diff --git a/deep_sort_pytorch/deep_sort/deep/model.py b/deep_sort_pytorch/deep_sort/deep/model.py new file mode 100644 index 0000000000000000000000000000000000000000..b99247489627df09276b52f6d47ef866e0e5bd4a --- /dev/null +++ b/deep_sort_pytorch/deep_sort/deep/model.py @@ -0,0 +1,109 @@ +import torch +import torch.nn as nn +import torch.nn.functional as F + + +class BasicBlock(nn.Module): + def __init__(self, c_in, c_out, is_downsample=False): + super(BasicBlock, self).__init__() + self.is_downsample = is_downsample + if is_downsample: + self.conv1 = nn.Conv2d( + c_in, c_out, 3, stride=2, padding=1, bias=False) + else: + self.conv1 = nn.Conv2d( + c_in, c_out, 3, stride=1, padding=1, bias=False) + self.bn1 = nn.BatchNorm2d(c_out) + self.relu = nn.ReLU(True) + self.conv2 = nn.Conv2d(c_out, c_out, 3, stride=1, + padding=1, bias=False) + self.bn2 = nn.BatchNorm2d(c_out) + if is_downsample: + self.downsample = nn.Sequential( + nn.Conv2d(c_in, c_out, 1, stride=2, bias=False), + nn.BatchNorm2d(c_out) + ) + elif c_in != c_out: + self.downsample = nn.Sequential( + nn.Conv2d(c_in, c_out, 1, stride=1, bias=False), + nn.BatchNorm2d(c_out) + ) + self.is_downsample = True + + def forward(self, x): + y = self.conv1(x) + y = self.bn1(y) + y = self.relu(y) + y = self.conv2(y) + y = self.bn2(y) + if self.is_downsample: + x = self.downsample(x) + return F.relu(x.add(y), True) + + +def make_layers(c_in, c_out, repeat_times, is_downsample=False): + blocks = [] + for i in range(repeat_times): + if i == 0: + blocks += [BasicBlock(c_in, c_out, is_downsample=is_downsample), ] + else: + blocks += [BasicBlock(c_out, c_out), ] + return nn.Sequential(*blocks) + + +class Net(nn.Module): + def __init__(self, num_classes=751, reid=False): + super(Net, self).__init__() + # 3 128 64 + self.conv = nn.Sequential( + nn.Conv2d(3, 64, 3, stride=1, padding=1), + nn.BatchNorm2d(64), + nn.ReLU(inplace=True), + # nn.Conv2d(32,32,3,stride=1,padding=1), + # nn.BatchNorm2d(32), + # nn.ReLU(inplace=True), + nn.MaxPool2d(3, 2, padding=1), + ) + # 32 64 32 + self.layer1 = make_layers(64, 64, 2, False) + # 32 64 32 + self.layer2 = make_layers(64, 128, 2, True) + # 64 32 16 + self.layer3 = make_layers(128, 256, 2, True) + # 128 16 8 + self.layer4 = make_layers(256, 512, 2, True) + # 256 8 4 + self.avgpool = nn.AvgPool2d((8, 4), 1) + # 256 1 1 + self.reid = reid + self.classifier = nn.Sequential( + nn.Linear(512, 256), + nn.BatchNorm1d(256), + nn.ReLU(inplace=True), + nn.Dropout(), + nn.Linear(256, num_classes), + ) + + def forward(self, x): + x = self.conv(x) + x = self.layer1(x) + x = self.layer2(x) + x = self.layer3(x) + x = self.layer4(x) + x = self.avgpool(x) + x = x.view(x.size(0), -1) + # B x 128 + if self.reid: + x = x.div(x.norm(p=2, dim=1, keepdim=True)) + return x + # classifier + x = self.classifier(x) + return x + + +if __name__ == '__main__': + net = Net() + x = torch.randn(4, 3, 128, 64) + y = net(x) + import ipdb + ipdb.set_trace() diff --git a/deep_sort_pytorch/deep_sort/deep/original_model.py b/deep_sort_pytorch/deep_sort/deep/original_model.py new file mode 100644 index 0000000000000000000000000000000000000000..27734ad52b3b02d815416d998bae145a93dbf519 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/deep/original_model.py @@ -0,0 +1,111 @@ +import torch +import torch.nn as nn +import torch.nn.functional as F + + +class BasicBlock(nn.Module): + def __init__(self, c_in, c_out, is_downsample=False): + super(BasicBlock, self).__init__() + self.is_downsample = is_downsample + if is_downsample: + self.conv1 = nn.Conv2d( + c_in, c_out, 3, stride=2, padding=1, bias=False) + else: + self.conv1 = nn.Conv2d( + c_in, c_out, 3, stride=1, padding=1, bias=False) + self.bn1 = nn.BatchNorm2d(c_out) + self.relu = nn.ReLU(True) + self.conv2 = nn.Conv2d(c_out, c_out, 3, stride=1, + padding=1, bias=False) + self.bn2 = nn.BatchNorm2d(c_out) + if is_downsample: + self.downsample = nn.Sequential( + nn.Conv2d(c_in, c_out, 1, stride=2, bias=False), + nn.BatchNorm2d(c_out) + ) + elif c_in != c_out: + self.downsample = nn.Sequential( + nn.Conv2d(c_in, c_out, 1, stride=1, bias=False), + nn.BatchNorm2d(c_out) + ) + self.is_downsample = True + + def forward(self, x): + y = self.conv1(x) + y = self.bn1(y) + y = self.relu(y) + y = self.conv2(y) + y = self.bn2(y) + if self.is_downsample: + x = self.downsample(x) + return F.relu(x.add(y), True) + + +def make_layers(c_in, c_out, repeat_times, is_downsample=False): + blocks = [] + for i in range(repeat_times): + if i == 0: + blocks += [BasicBlock(c_in, c_out, is_downsample=is_downsample), ] + else: + blocks += [BasicBlock(c_out, c_out), ] + return nn.Sequential(*blocks) + + +class Net(nn.Module): + def __init__(self, num_classes=625, reid=False): + super(Net, self).__init__() + # 3 128 64 + self.conv = nn.Sequential( + nn.Conv2d(3, 32, 3, stride=1, padding=1), + nn.BatchNorm2d(32), + nn.ELU(inplace=True), + nn.Conv2d(32, 32, 3, stride=1, padding=1), + nn.BatchNorm2d(32), + nn.ELU(inplace=True), + nn.MaxPool2d(3, 2, padding=1), + ) + # 32 64 32 + self.layer1 = make_layers(32, 32, 2, False) + # 32 64 32 + self.layer2 = make_layers(32, 64, 2, True) + # 64 32 16 + self.layer3 = make_layers(64, 128, 2, True) + # 128 16 8 + self.dense = nn.Sequential( + nn.Dropout(p=0.6), + nn.Linear(128*16*8, 128), + nn.BatchNorm1d(128), + nn.ELU(inplace=True) + ) + # 256 1 1 + self.reid = reid + self.batch_norm = nn.BatchNorm1d(128) + self.classifier = nn.Sequential( + nn.Linear(128, num_classes), + ) + + def forward(self, x): + x = self.conv(x) + x = self.layer1(x) + x = self.layer2(x) + x = self.layer3(x) + + x = x.view(x.size(0), -1) + if self.reid: + x = self.dense[0](x) + x = self.dense[1](x) + x = x.div(x.norm(p=2, dim=1, keepdim=True)) + return x + x = self.dense(x) + # B x 128 + # classifier + x = self.classifier(x) + return x + + +if __name__ == '__main__': + net = Net(reid=True) + x = torch.randn(4, 3, 128, 64) + y = net(x) + import ipdb + ipdb.set_trace() diff --git a/deep_sort_pytorch/deep_sort/deep/test.py b/deep_sort_pytorch/deep_sort/deep/test.py new file mode 100644 index 0000000000000000000000000000000000000000..0ba3050cb441e6419112604657797c78b6aa9b74 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/deep/test.py @@ -0,0 +1,80 @@ +import torch +import torch.backends.cudnn as cudnn +import torchvision + +import argparse +import os + +from model import Net + +parser = argparse.ArgumentParser(description="Train on market1501") +parser.add_argument("--data-dir", default='data', type=str) +parser.add_argument("--no-cuda", action="store_true") +parser.add_argument("--gpu-id", default=0, type=int) +args = parser.parse_args() + +# device +device = "cuda:{}".format( + args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu" +if torch.cuda.is_available() and not args.no_cuda: + cudnn.benchmark = True + +# data loader +root = args.data_dir +query_dir = os.path.join(root, "query") +gallery_dir = os.path.join(root, "gallery") +transform = torchvision.transforms.Compose([ + torchvision.transforms.Resize((128, 64)), + torchvision.transforms.ToTensor(), + torchvision.transforms.Normalize( + [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) +]) +queryloader = torch.utils.data.DataLoader( + torchvision.datasets.ImageFolder(query_dir, transform=transform), + batch_size=64, shuffle=False +) +galleryloader = torch.utils.data.DataLoader( + torchvision.datasets.ImageFolder(gallery_dir, transform=transform), + batch_size=64, shuffle=False +) + +# net definition +net = Net(reid=True) +assert os.path.isfile( + "./checkpoint/ckpt.t7"), "Error: no checkpoint file found!" +print('Loading from checkpoint/ckpt.t7') +checkpoint = torch.load("./checkpoint/ckpt.t7") +net_dict = checkpoint['net_dict'] +net.load_state_dict(net_dict, strict=False) +net.eval() +net.to(device) + +# compute features +query_features = torch.tensor([]).float() +query_labels = torch.tensor([]).long() +gallery_features = torch.tensor([]).float() +gallery_labels = torch.tensor([]).long() + +with torch.no_grad(): + for idx, (inputs, labels) in enumerate(queryloader): + inputs = inputs.to(device) + features = net(inputs).cpu() + query_features = torch.cat((query_features, features), dim=0) + query_labels = torch.cat((query_labels, labels)) + + for idx, (inputs, labels) in enumerate(galleryloader): + inputs = inputs.to(device) + features = net(inputs).cpu() + gallery_features = torch.cat((gallery_features, features), dim=0) + gallery_labels = torch.cat((gallery_labels, labels)) + +gallery_labels -= 2 + +# save features +features = { + "qf": query_features, + "ql": query_labels, + "gf": gallery_features, + "gl": gallery_labels +} +torch.save(features, "features.pth") diff --git a/deep_sort_pytorch/deep_sort/deep/train.jpg b/deep_sort_pytorch/deep_sort/deep/train.jpg new file mode 100644 index 0000000000000000000000000000000000000000..3635a614738828b880aa862bc52423848ac8e472 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/deep/train.jpg differ diff --git a/deep_sort_pytorch/deep_sort/deep/train.py b/deep_sort_pytorch/deep_sort/deep/train.py new file mode 100644 index 0000000000000000000000000000000000000000..67f475634cea1997212ee37917397134c5c4173b --- /dev/null +++ b/deep_sort_pytorch/deep_sort/deep/train.py @@ -0,0 +1,206 @@ +import argparse +import os +import time + +import numpy as np +import matplotlib.pyplot as plt +import torch +import torch.backends.cudnn as cudnn +import torchvision + +from model import Net + +parser = argparse.ArgumentParser(description="Train on market1501") +parser.add_argument("--data-dir", default='data', type=str) +parser.add_argument("--no-cuda", action="store_true") +parser.add_argument("--gpu-id", default=0, type=int) +parser.add_argument("--lr", default=0.1, type=float) +parser.add_argument("--interval", '-i', default=20, type=int) +parser.add_argument('--resume', '-r', action='store_true') +args = parser.parse_args() + +# device +device = "cuda:{}".format( + args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu" +if torch.cuda.is_available() and not args.no_cuda: + cudnn.benchmark = True + +# data loading +root = args.data_dir +train_dir = os.path.join(root, "train") +test_dir = os.path.join(root, "test") +transform_train = torchvision.transforms.Compose([ + torchvision.transforms.RandomCrop((128, 64), padding=4), + torchvision.transforms.RandomHorizontalFlip(), + torchvision.transforms.ToTensor(), + torchvision.transforms.Normalize( + [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) +]) +transform_test = torchvision.transforms.Compose([ + torchvision.transforms.Resize((128, 64)), + torchvision.transforms.ToTensor(), + torchvision.transforms.Normalize( + [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) +]) +trainloader = torch.utils.data.DataLoader( + torchvision.datasets.ImageFolder(train_dir, transform=transform_train), + batch_size=64, shuffle=True +) +testloader = torch.utils.data.DataLoader( + torchvision.datasets.ImageFolder(test_dir, transform=transform_test), + batch_size=64, shuffle=True +) +num_classes = max(len(trainloader.dataset.classes), + len(testloader.dataset.classes)) + +# net definition +start_epoch = 0 +net = Net(num_classes=num_classes) +if args.resume: + assert os.path.isfile( + "./checkpoint/ckpt.t7"), "Error: no checkpoint file found!" + print('Loading from checkpoint/ckpt.t7') + checkpoint = torch.load("./checkpoint/ckpt.t7") + # import ipdb; ipdb.set_trace() + net_dict = checkpoint['net_dict'] + net.load_state_dict(net_dict) + best_acc = checkpoint['acc'] + start_epoch = checkpoint['epoch'] +net.to(device) + +# loss and optimizer +criterion = torch.nn.CrossEntropyLoss() +optimizer = torch.optim.SGD( + net.parameters(), args.lr, momentum=0.9, weight_decay=5e-4) +best_acc = 0. + +# train function for each epoch + + +def train(epoch): + print("\nEpoch : %d" % (epoch+1)) + net.train() + training_loss = 0. + train_loss = 0. + correct = 0 + total = 0 + interval = args.interval + start = time.time() + for idx, (inputs, labels) in enumerate(trainloader): + # forward + inputs, labels = inputs.to(device), labels.to(device) + outputs = net(inputs) + loss = criterion(outputs, labels) + + # backward + optimizer.zero_grad() + loss.backward() + optimizer.step() + + # accumurating + training_loss += loss.item() + train_loss += loss.item() + correct += outputs.max(dim=1)[1].eq(labels).sum().item() + total += labels.size(0) + + # print + if (idx+1) % interval == 0: + end = time.time() + print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format( + 100.*(idx+1)/len(trainloader), end-start, training_loss / + interval, correct, total, 100.*correct/total + )) + training_loss = 0. + start = time.time() + + return train_loss/len(trainloader), 1. - correct/total + + +def test(epoch): + global best_acc + net.eval() + test_loss = 0. + correct = 0 + total = 0 + start = time.time() + with torch.no_grad(): + for idx, (inputs, labels) in enumerate(testloader): + inputs, labels = inputs.to(device), labels.to(device) + outputs = net(inputs) + loss = criterion(outputs, labels) + + test_loss += loss.item() + correct += outputs.max(dim=1)[1].eq(labels).sum().item() + total += labels.size(0) + + print("Testing ...") + end = time.time() + print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format( + 100.*(idx+1)/len(testloader), end-start, test_loss / + len(testloader), correct, total, 100.*correct/total + )) + + # saving checkpoint + acc = 100.*correct/total + if acc > best_acc: + best_acc = acc + print("Saving parameters to checkpoint/ckpt.t7") + checkpoint = { + 'net_dict': net.state_dict(), + 'acc': acc, + 'epoch': epoch, + } + if not os.path.isdir('checkpoint'): + os.mkdir('checkpoint') + torch.save(checkpoint, './checkpoint/ckpt.t7') + + return test_loss/len(testloader), 1. - correct/total + + +# plot figure +x_epoch = [] +record = {'train_loss': [], 'train_err': [], 'test_loss': [], 'test_err': []} +fig = plt.figure() +ax0 = fig.add_subplot(121, title="loss") +ax1 = fig.add_subplot(122, title="top1err") + + +def draw_curve(epoch, train_loss, train_err, test_loss, test_err): + global record + record['train_loss'].append(train_loss) + record['train_err'].append(train_err) + record['test_loss'].append(test_loss) + record['test_err'].append(test_err) + + x_epoch.append(epoch) + ax0.plot(x_epoch, record['train_loss'], 'bo-', label='train') + ax0.plot(x_epoch, record['test_loss'], 'ro-', label='val') + ax1.plot(x_epoch, record['train_err'], 'bo-', label='train') + ax1.plot(x_epoch, record['test_err'], 'ro-', label='val') + if epoch == 0: + ax0.legend() + ax1.legend() + fig.savefig("train.jpg") + +# lr decay + + +def lr_decay(): + global optimizer + for params in optimizer.param_groups: + params['lr'] *= 0.1 + lr = params['lr'] + print("Learning rate adjusted to {}".format(lr)) + + +def main(): + for epoch in range(start_epoch, start_epoch+40): + train_loss, train_err = train(epoch) + test_loss, test_err = test(epoch) + draw_curve(epoch, train_loss, train_err, test_loss, test_err) + if (epoch+1) % 20 == 0: + lr_decay() + + +if __name__ == '__main__': + main() diff --git a/deep_sort_pytorch/deep_sort/deep_sort.py b/deep_sort_pytorch/deep_sort/deep_sort.py new file mode 100644 index 0000000000000000000000000000000000000000..070c02cd99ee86808593cbfe4864c84e9794e894 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/deep_sort.py @@ -0,0 +1,115 @@ +import numpy as np +import torch + +from .deep.feature_extractor import Extractor +from .sort.nn_matching import NearestNeighborDistanceMetric +from .sort.detection import Detection +from .sort.tracker import Tracker + + +__all__ = ['DeepSort'] + + +class DeepSort(object): + def __init__(self, model_path, max_dist=0.2, min_confidence=0.3, nms_max_overlap=1.0, max_iou_distance=0.7, max_age=70, n_init=3, nn_budget=100, use_cuda=True): + self.min_confidence = min_confidence + self.nms_max_overlap = nms_max_overlap + + self.extractor = Extractor(model_path, use_cuda=use_cuda) + + max_cosine_distance = max_dist + metric = NearestNeighborDistanceMetric( + "cosine", max_cosine_distance, nn_budget) + self.tracker = Tracker( + metric, max_iou_distance=max_iou_distance, max_age=max_age, n_init=n_init) + + def update(self, bbox_xywh, confidences, oids, ori_img): + self.height, self.width = ori_img.shape[:2] + # generate detections + features = self._get_features(bbox_xywh, ori_img) + bbox_tlwh = self._xywh_to_tlwh(bbox_xywh) + detections = [Detection(bbox_tlwh[i], conf, features[i], oid) for i, (conf,oid) in enumerate(zip(confidences,oids)) if conf > self.min_confidence] + + # print(detections) + # run on non-maximum supression + boxes = np.array([d.tlwh for d in detections]) + scores = np.array([d.confidence for d in detections]) + + # update tracker + self.tracker.predict() + self.tracker.update(detections) + print("len(scores):", len(scores)) + print("self.tracker.tracks",len(self.tracker.tracks)) + # output bbox identities + outputs = [] + for track in self.tracker.tracks: + if not track.is_confirmed() or track.time_since_update > 1: + continue + box = track.to_tlwh() + x1, y1, x2, y2 = self._tlwh_to_xyxy(box) + track_id = track.track_id + track_oid = track.oid + outputs.append(np.array([x1, y1, x2, y2, track_id, track_oid], dtype=np.int)) + if len(outputs) > 0: + outputs = np.stack(outputs, axis=0) + return outputs + + """ + TODO: + Convert bbox from xc_yc_w_h to xtl_ytl_w_h + Thanks JieChen91@github.com for reporting this bug! + """ + @staticmethod + def _xywh_to_tlwh(bbox_xywh): + if isinstance(bbox_xywh, np.ndarray): + bbox_tlwh = bbox_xywh.copy() + elif isinstance(bbox_xywh, torch.Tensor): + bbox_tlwh = bbox_xywh.clone() + bbox_tlwh[:, 0] = bbox_xywh[:, 0] - bbox_xywh[:, 2] / 2. + bbox_tlwh[:, 1] = bbox_xywh[:, 1] - bbox_xywh[:, 3] / 2. + return bbox_tlwh + + def _xywh_to_xyxy(self, bbox_xywh): + x, y, w, h = bbox_xywh + x1 = max(int(x - w / 2), 0) + x2 = min(int(x + w / 2), self.width - 1) + y1 = max(int(y - h / 2), 0) + y2 = min(int(y + h / 2), self.height - 1) + return x1, y1, x2, y2 + + def _tlwh_to_xyxy(self, bbox_tlwh): + """ + TODO: + Convert bbox from xtl_ytl_w_h to xc_yc_w_h + Thanks JieChen91@github.com for reporting this bug! + """ + x, y, w, h = bbox_tlwh + x1 = max(int(x), 0) + x2 = min(int(x+w), self.width - 1) + y1 = max(int(y), 0) + y2 = min(int(y+h), self.height - 1) + return x1, y1, x2, y2 + + def increment_ages(self): + self.tracker.increment_ages() + + def _xyxy_to_tlwh(self, bbox_xyxy): + x1, y1, x2, y2 = bbox_xyxy + + t = x1 + l = y1 + w = int(x2 - x1) + h = int(y2 - y1) + return t, l, w, h + + def _get_features(self, bbox_xywh, ori_img): + im_crops = [] + for box in bbox_xywh: + x1, y1, x2, y2 = self._xywh_to_xyxy(box) + im = ori_img[y1:y2, x1:x2] + im_crops.append(im) + if im_crops: + features = self.extractor(im_crops) + else: + features = np.array([]) + return features diff --git a/deep_sort_pytorch/deep_sort/sort/__init__.py b/deep_sort_pytorch/deep_sort/sort/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/__init__.cpython-310.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ee2df7d00368607ebc618b868f43555579d725ad Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/__init__.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/__init__.cpython-39.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2c9447171a22e67b64265f7943e71034fe1e381d Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/__init__.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/detection.cpython-310.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/detection.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b1c54fb7a734ae6f169fdd8798f454fe6739d384 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/detection.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/detection.cpython-39.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/detection.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..773b7031c474ecc2bf1387a6b9d201c95762fbe2 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/detection.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/iou_matching.cpython-310.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/iou_matching.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9a86b5ea9b5d97e4089584398c3832ddaf53df18 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/iou_matching.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/iou_matching.cpython-39.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/iou_matching.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1193d873ffe8d96544e9c54926cc91d45773b690 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/iou_matching.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/kalman_filter.cpython-310.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/kalman_filter.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..62b681280dc62553044a02a49e5338454b243044 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/kalman_filter.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/kalman_filter.cpython-39.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/kalman_filter.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d4ef0270cc072125a05964e4dabb7033fba35658 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/kalman_filter.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/linear_assignment.cpython-310.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/linear_assignment.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..27f8b7276827e7ccd24d5cf6888219ea5aeeefd3 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/linear_assignment.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/linear_assignment.cpython-39.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/linear_assignment.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..51433199e68d0ffb314cfd579c1b857b8ac214ed Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/linear_assignment.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/nn_matching.cpython-310.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/nn_matching.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d91df4c152c317462fed636857fdfa9d70254520 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/nn_matching.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/nn_matching.cpython-39.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/nn_matching.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..55fed9e0f0293cf1a1525ad9486227aac9cea364 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/nn_matching.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/track.cpython-310.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/track.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d21152decc23e0d6f638128a82ae00c45267cf9a Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/track.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/track.cpython-39.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/track.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c4fe1dd54172553a308396f64985938b53ff69d8 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/track.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/tracker.cpython-310.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/tracker.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..878d5d2c10e349629e31ec545702d53268319db5 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/tracker.cpython-310.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/__pycache__/tracker.cpython-39.pyc b/deep_sort_pytorch/deep_sort/sort/__pycache__/tracker.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ff7ecdb6761f34bd74c2572ddfd6e948e3738947 Binary files /dev/null and b/deep_sort_pytorch/deep_sort/sort/__pycache__/tracker.cpython-39.pyc differ diff --git a/deep_sort_pytorch/deep_sort/sort/detection.py b/deep_sort_pytorch/deep_sort/sort/detection.py new file mode 100644 index 0000000000000000000000000000000000000000..de29a7ac5d2d66aae328f2a5a0cd7ef822cc0403 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/sort/detection.py @@ -0,0 +1,50 @@ +# vim: expandtab:ts=4:sw=4 +import numpy as np + + +class Detection(object): + """ + This class represents a bounding box detection in a single image. + + Parameters + ---------- + tlwh : array_like + Bounding box in format `(x, y, w, h)`. + confidence : float + Detector confidence score. + feature : array_like + A feature vector that describes the object contained in this image. + + Attributes + ---------- + tlwh : ndarray + Bounding box in format `(top left x, top left y, width, height)`. + confidence : ndarray + Detector confidence score. + feature : ndarray | NoneType + A feature vector that describes the object contained in this image. + + """ + + def __init__(self, tlwh, confidence, feature, oid): + self.tlwh = np.asarray(tlwh, dtype=np.float) + self.confidence = float(confidence) + self.feature = np.asarray(feature, dtype=np.float32) + self.oid = oid + + def to_tlbr(self): + """Convert bounding box to format `(min x, min y, max x, max y)`, i.e., + `(top left, bottom right)`. + """ + ret = self.tlwh.copy() + ret[2:] += ret[:2] + return ret + + def to_xyah(self): + """Convert bounding box to format `(center x, center y, aspect ratio, + height)`, where the aspect ratio is `width / height`. + """ + ret = self.tlwh.copy() + ret[:2] += ret[2:] / 2 + ret[2] /= ret[3] + return ret diff --git a/deep_sort_pytorch/deep_sort/sort/iou_matching.py b/deep_sort_pytorch/deep_sort/sort/iou_matching.py new file mode 100644 index 0000000000000000000000000000000000000000..62d5a3f63b70db5e322b6f8766444dd824c010ae --- /dev/null +++ b/deep_sort_pytorch/deep_sort/sort/iou_matching.py @@ -0,0 +1,82 @@ +# vim: expandtab:ts=4:sw=4 +from __future__ import absolute_import +import numpy as np +from . import linear_assignment + + +def iou(bbox, candidates): + """Computer intersection over union. + + Parameters + ---------- + bbox : ndarray + A bounding box in format `(top left x, top left y, width, height)`. + candidates : ndarray + A matrix of candidate bounding boxes (one per row) in the same format + as `bbox`. + + Returns + ------- + ndarray + The intersection over union in [0, 1] between the `bbox` and each + candidate. A higher score means a larger fraction of the `bbox` is + occluded by the candidate. + + """ + bbox_tl, bbox_br = bbox[:2], bbox[:2] + bbox[2:] + candidates_tl = candidates[:, :2] + candidates_br = candidates[:, :2] + candidates[:, 2:] + + tl = np.c_[np.maximum(bbox_tl[0], candidates_tl[:, 0])[:, np.newaxis], + np.maximum(bbox_tl[1], candidates_tl[:, 1])[:, np.newaxis]] + br = np.c_[np.minimum(bbox_br[0], candidates_br[:, 0])[:, np.newaxis], + np.minimum(bbox_br[1], candidates_br[:, 1])[:, np.newaxis]] + wh = np.maximum(0., br - tl) + + area_intersection = wh.prod(axis=1) + area_bbox = bbox[2:].prod() + area_candidates = candidates[:, 2:].prod(axis=1) + return area_intersection / (area_bbox + area_candidates - area_intersection) + + +def iou_cost(tracks, detections, track_indices=None, + detection_indices=None): + """An intersection over union distance metric. + + Parameters + ---------- + tracks : List[deep_sort.track.Track] + A list of tracks. + detections : List[deep_sort.detection.Detection] + A list of detections. + track_indices : Optional[List[int]] + A list of indices to tracks that should be matched. Defaults to + all `tracks`. + detection_indices : Optional[List[int]] + A list of indices to detections that should be matched. Defaults + to all `detections`. + + Returns + ------- + ndarray + Returns a cost matrix of shape + len(track_indices), len(detection_indices) where entry (i, j) is + `1 - iou(tracks[track_indices[i]], detections[detection_indices[j]])`. + + """ + if track_indices is None: + track_indices = np.arange(len(tracks)) + if detection_indices is None: + detection_indices = np.arange(len(detections)) + + cost_matrix = np.zeros((len(track_indices), len(detection_indices))) + for row, track_idx in enumerate(track_indices): + if tracks[track_idx].time_since_update > 1: + cost_matrix[row, :] = linear_assignment.INFTY_COST + continue + + bbox = tracks[track_idx].to_tlwh() + candidates = np.asarray( + [detections[i].tlwh for i in detection_indices]) + cost_matrix[row, :] = 1. - iou(bbox, candidates) + return cost_matrix diff --git a/deep_sort_pytorch/deep_sort/sort/kalman_filter.py b/deep_sort_pytorch/deep_sort/sort/kalman_filter.py new file mode 100644 index 0000000000000000000000000000000000000000..787a76e6a43870a9538647b51fda6a5254ce2d43 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/sort/kalman_filter.py @@ -0,0 +1,229 @@ +# vim: expandtab:ts=4:sw=4 +import numpy as np +import scipy.linalg + + +""" +Table for the 0.95 quantile of the chi-square distribution with N degrees of +freedom (contains values for N=1, ..., 9). Taken from MATLAB/Octave's chi2inv +function and used as Mahalanobis gating threshold. +""" +chi2inv95 = { + 1: 3.8415, + 2: 5.9915, + 3: 7.8147, + 4: 9.4877, + 5: 11.070, + 6: 12.592, + 7: 14.067, + 8: 15.507, + 9: 16.919} + + +class KalmanFilter(object): + """ + A simple Kalman filter for tracking bounding boxes in image space. + + The 8-dimensional state space + + x, y, a, h, vx, vy, va, vh + + contains the bounding box center position (x, y), aspect ratio a, height h, + and their respective velocities. + + Object motion follows a constant velocity model. The bounding box location + (x, y, a, h) is taken as direct observation of the state space (linear + observation model). + + """ + + def __init__(self): + ndim, dt = 4, 1. + + # Create Kalman filter model matrices. + self._motion_mat = np.eye(2 * ndim, 2 * ndim) + for i in range(ndim): + self._motion_mat[i, ndim + i] = dt + self._update_mat = np.eye(ndim, 2 * ndim) + + # Motion and observation uncertainty are chosen relative to the current + # state estimate. These weights control the amount of uncertainty in + # the model. This is a bit hacky. + self._std_weight_position = 1. / 20 + self._std_weight_velocity = 1. / 160 + + def initiate(self, measurement): + """Create track from unassociated measurement. + + Parameters + ---------- + measurement : ndarray + Bounding box coordinates (x, y, a, h) with center position (x, y), + aspect ratio a, and height h. + + Returns + ------- + (ndarray, ndarray) + Returns the mean vector (8 dimensional) and covariance matrix (8x8 + dimensional) of the new track. Unobserved velocities are initialized + to 0 mean. + + """ + mean_pos = measurement + mean_vel = np.zeros_like(mean_pos) + mean = np.r_[mean_pos, mean_vel] + + std = [ + 2 * self._std_weight_position * measurement[3], + 2 * self._std_weight_position * measurement[3], + 1e-2, + 2 * self._std_weight_position * measurement[3], + 10 * self._std_weight_velocity * measurement[3], + 10 * self._std_weight_velocity * measurement[3], + 1e-5, + 10 * self._std_weight_velocity * measurement[3]] + covariance = np.diag(np.square(std)) + return mean, covariance + + def predict(self, mean, covariance): + """Run Kalman filter prediction step. + + Parameters + ---------- + mean : ndarray + The 8 dimensional mean vector of the object state at the previous + time step. + covariance : ndarray + The 8x8 dimensional covariance matrix of the object state at the + previous time step. + + Returns + ------- + (ndarray, ndarray) + Returns the mean vector and covariance matrix of the predicted + state. Unobserved velocities are initialized to 0 mean. + + """ + std_pos = [ + self._std_weight_position * mean[3], + self._std_weight_position * mean[3], + 1e-2, + self._std_weight_position * mean[3]] + std_vel = [ + self._std_weight_velocity * mean[3], + self._std_weight_velocity * mean[3], + 1e-5, + self._std_weight_velocity * mean[3]] + motion_cov = np.diag(np.square(np.r_[std_pos, std_vel])) + + mean = np.dot(self._motion_mat, mean) + covariance = np.linalg.multi_dot(( + self._motion_mat, covariance, self._motion_mat.T)) + motion_cov + + return mean, covariance + + def project(self, mean, covariance): + """Project state distribution to measurement space. + + Parameters + ---------- + mean : ndarray + The state's mean vector (8 dimensional array). + covariance : ndarray + The state's covariance matrix (8x8 dimensional). + + Returns + ------- + (ndarray, ndarray) + Returns the projected mean and covariance matrix of the given state + estimate. + + """ + std = [ + self._std_weight_position * mean[3], + self._std_weight_position * mean[3], + 1e-1, + self._std_weight_position * mean[3]] + innovation_cov = np.diag(np.square(std)) + + mean = np.dot(self._update_mat, mean) + covariance = np.linalg.multi_dot(( + self._update_mat, covariance, self._update_mat.T)) + return mean, covariance + innovation_cov + + def update(self, mean, covariance, measurement): + """Run Kalman filter correction step. + + Parameters + ---------- + mean : ndarray + The predicted state's mean vector (8 dimensional). + covariance : ndarray + The state's covariance matrix (8x8 dimensional). + measurement : ndarray + The 4 dimensional measurement vector (x, y, a, h), where (x, y) + is the center position, a the aspect ratio, and h the height of the + bounding box. + + Returns + ------- + (ndarray, ndarray) + Returns the measurement-corrected state distribution. + + """ + projected_mean, projected_cov = self.project(mean, covariance) + + chol_factor, lower = scipy.linalg.cho_factor( + projected_cov, lower=True, check_finite=False) + kalman_gain = scipy.linalg.cho_solve( + (chol_factor, lower), np.dot(covariance, self._update_mat.T).T, + check_finite=False).T + innovation = measurement - projected_mean + + new_mean = mean + np.dot(innovation, kalman_gain.T) + new_covariance = covariance - np.linalg.multi_dot(( + kalman_gain, projected_cov, kalman_gain.T)) + return new_mean, new_covariance + + def gating_distance(self, mean, covariance, measurements, + only_position=False): + """Compute gating distance between state distribution and measurements. + + A suitable distance threshold can be obtained from `chi2inv95`. If + `only_position` is False, the chi-square distribution has 4 degrees of + freedom, otherwise 2. + + Parameters + ---------- + mean : ndarray + Mean vector over the state distribution (8 dimensional). + covariance : ndarray + Covariance of the state distribution (8x8 dimensional). + measurements : ndarray + An Nx4 dimensional matrix of N measurements, each in + format (x, y, a, h) where (x, y) is the bounding box center + position, a the aspect ratio, and h the height. + only_position : Optional[bool] + If True, distance computation is done with respect to the bounding + box center position only. + + Returns + ------- + ndarray + Returns an array of length N, where the i-th element contains the + squared Mahalanobis distance between (mean, covariance) and + `measurements[i]`. + + """ + mean, covariance = self.project(mean, covariance) + if only_position: + mean, covariance = mean[:2], covariance[:2, :2] + measurements = measurements[:, :2] + + cholesky_factor = np.linalg.cholesky(covariance) + d = measurements - mean + z = scipy.linalg.solve_triangular( + cholesky_factor, d.T, lower=True, check_finite=False, + overwrite_b=True) + squared_maha = np.sum(z * z, axis=0) + return squared_maha diff --git a/deep_sort_pytorch/deep_sort/sort/linear_assignment.py b/deep_sort_pytorch/deep_sort/sort/linear_assignment.py new file mode 100644 index 0000000000000000000000000000000000000000..858b71a4ae32ca39f03ff5d0ca0fdcc5963171b0 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/sort/linear_assignment.py @@ -0,0 +1,192 @@ +# vim: expandtab:ts=4:sw=4 +from __future__ import absolute_import +import numpy as np +# from sklearn.utils.linear_assignment_ import linear_assignment +from scipy.optimize import linear_sum_assignment as linear_assignment +from . import kalman_filter + + +INFTY_COST = 1e+5 + + +def min_cost_matching( + distance_metric, max_distance, tracks, detections, track_indices=None, + detection_indices=None): + """Solve linear assignment problem. + + Parameters + ---------- + distance_metric : Callable[List[Track], List[Detection], List[int], List[int]) -> ndarray + The distance metric is given a list of tracks and detections as well as + a list of N track indices and M detection indices. The metric should + return the NxM dimensional cost matrix, where element (i, j) is the + association cost between the i-th track in the given track indices and + the j-th detection in the given detection_indices. + max_distance : float + Gating threshold. Associations with cost larger than this value are + disregarded. + tracks : List[track.Track] + A list of predicted tracks at the current time step. + detections : List[detection.Detection] + A list of detections at the current time step. + track_indices : List[int] + List of track indices that maps rows in `cost_matrix` to tracks in + `tracks` (see description above). + detection_indices : List[int] + List of detection indices that maps columns in `cost_matrix` to + detections in `detections` (see description above). + + Returns + ------- + (List[(int, int)], List[int], List[int]) + Returns a tuple with the following three entries: + * A list of matched track and detection indices. + * A list of unmatched track indices. + * A list of unmatched detection indices. + + """ + if track_indices is None: + track_indices = np.arange(len(tracks)) + if detection_indices is None: + detection_indices = np.arange(len(detections)) + + if len(detection_indices) == 0 or len(track_indices) == 0: + return [], track_indices, detection_indices # Nothing to match. + + cost_matrix = distance_metric( + tracks, detections, track_indices, detection_indices) + cost_matrix[cost_matrix > max_distance] = max_distance + 1e-5 + + row_indices, col_indices = linear_assignment(cost_matrix) + + matches, unmatched_tracks, unmatched_detections = [], [], [] + for col, detection_idx in enumerate(detection_indices): + if col not in col_indices: + unmatched_detections.append(detection_idx) + for row, track_idx in enumerate(track_indices): + if row not in row_indices: + unmatched_tracks.append(track_idx) + for row, col in zip(row_indices, col_indices): + track_idx = track_indices[row] + detection_idx = detection_indices[col] + if cost_matrix[row, col] > max_distance: + unmatched_tracks.append(track_idx) + unmatched_detections.append(detection_idx) + else: + matches.append((track_idx, detection_idx)) + return matches, unmatched_tracks, unmatched_detections + + +def matching_cascade( + distance_metric, max_distance, cascade_depth, tracks, detections, + track_indices=None, detection_indices=None): + """Run matching cascade. + + Parameters + ---------- + distance_metric : Callable[List[Track], List[Detection], List[int], List[int]) -> ndarray + The distance metric is given a list of tracks and detections as well as + a list of N track indices and M detection indices. The metric should + return the NxM dimensional cost matrix, where element (i, j) is the + association cost between the i-th track in the given track indices and + the j-th detection in the given detection indices. + max_distance : float + Gating threshold. Associations with cost larger than this value are + disregarded. + cascade_depth: int + The cascade depth, should be se to the maximum track age. + tracks : List[track.Track] + A list of predicted tracks at the current time step. + detections : List[detection.Detection] + A list of detections at the current time step. + track_indices : Optional[List[int]] + List of track indices that maps rows in `cost_matrix` to tracks in + `tracks` (see description above). Defaults to all tracks. + detection_indices : Optional[List[int]] + List of detection indices that maps columns in `cost_matrix` to + detections in `detections` (see description above). Defaults to all + detections. + + Returns + ------- + (List[(int, int)], List[int], List[int]) + Returns a tuple with the following three entries: + * A list of matched track and detection indices. + * A list of unmatched track indices. + * A list of unmatched detection indices. + + """ + if track_indices is None: + track_indices = list(range(len(tracks))) + if detection_indices is None: + detection_indices = list(range(len(detections))) + + unmatched_detections = detection_indices + matches = [] + for level in range(cascade_depth): + if len(unmatched_detections) == 0: # No detections left + break + + track_indices_l = [ + k for k in track_indices + if tracks[k].time_since_update == 1 + level + ] + if len(track_indices_l) == 0: # Nothing to match at this level + continue + + matches_l, _, unmatched_detections = \ + min_cost_matching( + distance_metric, max_distance, tracks, detections, + track_indices_l, unmatched_detections) + matches += matches_l + unmatched_tracks = list(set(track_indices) - set(k for k, _ in matches)) + return matches, unmatched_tracks, unmatched_detections + + +def gate_cost_matrix( + kf, cost_matrix, tracks, detections, track_indices, detection_indices, + gated_cost=INFTY_COST, only_position=False): + """Invalidate infeasible entries in cost matrix based on the state + distributions obtained by Kalman filtering. + + Parameters + ---------- + kf : The Kalman filter. + cost_matrix : ndarray + The NxM dimensional cost matrix, where N is the number of track indices + and M is the number of detection indices, such that entry (i, j) is the + association cost between `tracks[track_indices[i]]` and + `detections[detection_indices[j]]`. + tracks : List[track.Track] + A list of predicted tracks at the current time step. + detections : List[detection.Detection] + A list of detections at the current time step. + track_indices : List[int] + List of track indices that maps rows in `cost_matrix` to tracks in + `tracks` (see description above). + detection_indices : List[int] + List of detection indices that maps columns in `cost_matrix` to + detections in `detections` (see description above). + gated_cost : Optional[float] + Entries in the cost matrix corresponding to infeasible associations are + set this value. Defaults to a very large value. + only_position : Optional[bool] + If True, only the x, y position of the state distribution is considered + during gating. Defaults to False. + + Returns + ------- + ndarray + Returns the modified cost matrix. + + """ + gating_dim = 2 if only_position else 4 + gating_threshold = kalman_filter.chi2inv95[gating_dim] + measurements = np.asarray( + [detections[i].to_xyah() for i in detection_indices]) + for row, track_idx in enumerate(track_indices): + track = tracks[track_idx] + gating_distance = kf.gating_distance( + track.mean, track.covariance, measurements, only_position) + cost_matrix[row, gating_distance > gating_threshold] = gated_cost + return cost_matrix diff --git a/deep_sort_pytorch/deep_sort/sort/nn_matching.py b/deep_sort_pytorch/deep_sort/sort/nn_matching.py new file mode 100644 index 0000000000000000000000000000000000000000..21e5b4f478fead21d38227ce2eac34556bd1179e --- /dev/null +++ b/deep_sort_pytorch/deep_sort/sort/nn_matching.py @@ -0,0 +1,176 @@ +# vim: expandtab:ts=4:sw=4 +import numpy as np + + +def _pdist(a, b): + """Compute pair-wise squared distance between points in `a` and `b`. + + Parameters + ---------- + a : array_like + An NxM matrix of N samples of dimensionality M. + b : array_like + An LxM matrix of L samples of dimensionality M. + + Returns + ------- + ndarray + Returns a matrix of size len(a), len(b) such that eleement (i, j) + contains the squared distance between `a[i]` and `b[j]`. + + """ + a, b = np.asarray(a), np.asarray(b) + if len(a) == 0 or len(b) == 0: + return np.zeros((len(a), len(b))) + a2, b2 = np.square(a).sum(axis=1), np.square(b).sum(axis=1) + r2 = -2. * np.dot(a, b.T) + a2[:, None] + b2[None, :] + r2 = np.clip(r2, 0., float(np.inf)) + return r2 + + +def _cosine_distance(a, b, data_is_normalized=False): + """Compute pair-wise cosine distance between points in `a` and `b`. + + Parameters + ---------- + a : array_like + An NxM matrix of N samples of dimensionality M. + b : array_like + An LxM matrix of L samples of dimensionality M. + data_is_normalized : Optional[bool] + If True, assumes rows in a and b are unit length vectors. + Otherwise, a and b are explicitly normalized to lenght 1. + + Returns + ------- + ndarray + Returns a matrix of size len(a), len(b) such that eleement (i, j) + contains the squared distance between `a[i]` and `b[j]`. + + """ + if not data_is_normalized: + a = np.asarray(a) / np.linalg.norm(a, axis=1, keepdims=True) + b = np.asarray(b) / np.linalg.norm(b, axis=1, keepdims=True) + return 1. - np.dot(a, b.T) + + +def _nn_euclidean_distance(x, y): + """ Helper function for nearest neighbor distance metric (Euclidean). + + Parameters + ---------- + x : ndarray + A matrix of N row-vectors (sample points). + y : ndarray + A matrix of M row-vectors (query points). + + Returns + ------- + ndarray + A vector of length M that contains for each entry in `y` the + smallest Euclidean distance to a sample in `x`. + + """ + distances = _pdist(x, y) + return np.maximum(0.0, distances.min(axis=0)) + + +def _nn_cosine_distance(x, y): + """ Helper function for nearest neighbor distance metric (cosine). + + Parameters + ---------- + x : ndarray + A matrix of N row-vectors (sample points). + y : ndarray + A matrix of M row-vectors (query points). + + Returns + ------- + ndarray + A vector of length M that contains for each entry in `y` the + smallest cosine distance to a sample in `x`. + + """ + distances = _cosine_distance(x, y) + return distances.min(axis=0) + + +class NearestNeighborDistanceMetric(object): + """ + A nearest neighbor distance metric that, for each target, returns + the closest distance to any sample that has been observed so far. + + Parameters + ---------- + metric : str + Either "euclidean" or "cosine". + matching_threshold: float + The matching threshold. Samples with larger distance are considered an + invalid match. + budget : Optional[int] + If not None, fix samples per class to at most this number. Removes + the oldest samples when the budget is reached. + + Attributes + ---------- + samples : Dict[int -> List[ndarray]] + A dictionary that maps from target identities to the list of samples + that have been observed so far. + + """ + + def __init__(self, metric, matching_threshold, budget=None): + + if metric == "euclidean": + self._metric = _nn_euclidean_distance + elif metric == "cosine": + self._metric = _nn_cosine_distance + else: + raise ValueError( + "Invalid metric; must be either 'euclidean' or 'cosine'") + self.matching_threshold = matching_threshold + self.budget = budget + self.samples = {} + + def partial_fit(self, features, targets, active_targets): + """Update the distance metric with new data. + + Parameters + ---------- + features : ndarray + An NxM matrix of N features of dimensionality M. + targets : ndarray + An integer array of associated target identities. + active_targets : List[int] + A list of targets that are currently present in the scene. + + """ + for feature, target in zip(features, targets): + self.samples.setdefault(target, []).append(feature) + if self.budget is not None: + self.samples[target] = self.samples[target][-self.budget:] + self.samples = {k: self.samples[k] for k in active_targets} + + def distance(self, features, targets): + """Compute distance between features and targets. + + Parameters + ---------- + features : ndarray + An NxM matrix of N features of dimensionality M. + targets : List[int] + A list of targets to match the given `features` against. + + Returns + ------- + ndarray + Returns a cost matrix of shape len(targets), len(features), where + element (i, j) contains the closest squared distance between + `targets[i]` and `features[j]`. + + """ + cost_matrix = np.zeros((len(targets), len(features))) + for i, target in enumerate(targets): + cost_matrix[i, :] = self._metric(self.samples[target], features) + return cost_matrix diff --git a/deep_sort_pytorch/deep_sort/sort/preprocessing.py b/deep_sort_pytorch/deep_sort/sort/preprocessing.py new file mode 100644 index 0000000000000000000000000000000000000000..5493b127f602dec398efac4269c00d31a3650ce9 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/sort/preprocessing.py @@ -0,0 +1,73 @@ +# vim: expandtab:ts=4:sw=4 +import numpy as np +import cv2 + + +def non_max_suppression(boxes, max_bbox_overlap, scores=None): + """Suppress overlapping detections. + + Original code from [1]_ has been adapted to include confidence score. + + .. [1] http://www.pyimagesearch.com/2015/02/16/ + faster-non-maximum-suppression-python/ + + Examples + -------- + + >>> boxes = [d.roi for d in detections] + >>> scores = [d.confidence for d in detections] + >>> indices = non_max_suppression(boxes, max_bbox_overlap, scores) + >>> detections = [detections[i] for i in indices] + + Parameters + ---------- + boxes : ndarray + Array of ROIs (x, y, width, height). + max_bbox_overlap : float + ROIs that overlap more than this values are suppressed. + scores : Optional[array_like] + Detector confidence score. + + Returns + ------- + List[int] + Returns indices of detections that have survived non-maxima suppression. + + """ + if len(boxes) == 0: + return [] + + boxes = boxes.astype(np.float) + pick = [] + + x1 = boxes[:, 0] + y1 = boxes[:, 1] + x2 = boxes[:, 2] + boxes[:, 0] + y2 = boxes[:, 3] + boxes[:, 1] + + area = (x2 - x1 + 1) * (y2 - y1 + 1) + if scores is not None: + idxs = np.argsort(scores) + else: + idxs = np.argsort(y2) + + while len(idxs) > 0: + last = len(idxs) - 1 + i = idxs[last] + pick.append(i) + + xx1 = np.maximum(x1[i], x1[idxs[:last]]) + yy1 = np.maximum(y1[i], y1[idxs[:last]]) + xx2 = np.minimum(x2[i], x2[idxs[:last]]) + yy2 = np.minimum(y2[i], y2[idxs[:last]]) + + w = np.maximum(0, xx2 - xx1 + 1) + h = np.maximum(0, yy2 - yy1 + 1) + + overlap = (w * h) / area[idxs[:last]] + + idxs = np.delete( + idxs, np.concatenate( + ([last], np.where(overlap > max_bbox_overlap)[0]))) + + return pick diff --git a/deep_sort_pytorch/deep_sort/sort/track.py b/deep_sort_pytorch/deep_sort/sort/track.py new file mode 100644 index 0000000000000000000000000000000000000000..7ac5eb7c40f5ea4ef445e96bd1074f6b9ab345f5 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/sort/track.py @@ -0,0 +1,170 @@ +# vim: expandtab:ts=4:sw=4 + + +class TrackState: + """ + Enumeration type for the single target track state. Newly created tracks are + classified as `tentative` until enough evidence has been collected. Then, + the track state is changed to `confirmed`. Tracks that are no longer alive + are classified as `deleted` to mark them for removal from the set of active + tracks. + + """ + + Tentative = 1 + Confirmed = 2 + Deleted = 3 + + +class Track: + """ + A single target track with state space `(x, y, a, h)` and associated + velocities, where `(x, y)` is the center of the bounding box, `a` is the + aspect ratio and `h` is the height. + + Parameters + ---------- + mean : ndarray + Mean vector of the initial state distribution. + covariance : ndarray + Covariance matrix of the initial state distribution. + track_id : int + A unique track identifier. + n_init : int + Number of consecutive detections before the track is confirmed. The + track state is set to `Deleted` if a miss occurs within the first + `n_init` frames. + max_age : int + The maximum number of consecutive misses before the track state is + set to `Deleted`. + feature : Optional[ndarray] + Feature vector of the detection this track originates from. If not None, + this feature is added to the `features` cache. + + Attributes + ---------- + mean : ndarray + Mean vector of the initial state distribution. + covariance : ndarray + Covariance matrix of the initial state distribution. + track_id : int + A unique track identifier. + hits : int + Total number of measurement updates. + age : int + Total number of frames since first occurance. + time_since_update : int + Total number of frames since last measurement update. + state : TrackState + The current track state. + features : List[ndarray] + A cache of features. On each measurement update, the associated feature + vector is added to this list. + + """ + + def __init__(self, mean, covariance, track_id, n_init, max_age, oid, + feature=None): + self.mean = mean + self.covariance = covariance + self.track_id = track_id + self.oid = oid + self.hits = 1 + self.age = 1 + self.time_since_update = 0 + + self.state = TrackState.Tentative + self.features = [] + if feature is not None: + self.features.append(feature) + + self._n_init = n_init + self._max_age = max_age + + def to_tlwh(self): + """Get current position in bounding box format `(top left x, top left y, + width, height)`. + + Returns + ------- + ndarray + The bounding box. + + """ + ret = self.mean[:4].copy() + ret[2] *= ret[3] + ret[:2] -= ret[2:] / 2 + return ret + + def to_tlbr(self): + """Get current position in bounding box format `(min x, miny, max x, + max y)`. + + Returns + ------- + ndarray + The bounding box. + + """ + ret = self.to_tlwh() + ret[2:] = ret[:2] + ret[2:] + return ret + + def increment_age(self): + self.age += 1 + self.time_since_update += 1 + + def predict(self, kf): + """Propagate the state distribution to the current time step using a + Kalman filter prediction step. + + Parameters + ---------- + kf : kalman_filter.KalmanFilter + The Kalman filter. + + """ + self.mean, self.covariance = kf.predict(self.mean, self.covariance) + self.increment_age() + + def update(self, kf, detection): + """Perform Kalman filter measurement update step and update the feature + cache. + + Parameters + ---------- + kf : kalman_filter.KalmanFilter + The Kalman filter. + detection : Detection + The associated detection. + + """ + self.mean, self.covariance = kf.update( + self.mean, self.covariance, detection.to_xyah()) + self.features.append(detection.feature) + + self.hits += 1 + self.time_since_update = 0 + if self.state == TrackState.Tentative and self.hits >= self._n_init: + self.state = TrackState.Confirmed + + def mark_missed(self): + """Mark this track as missed (no association at the current time step). + """ + if self.state == TrackState.Tentative: + self.state = TrackState.Deleted + elif self.time_since_update > self._max_age: + self.state = TrackState.Deleted + + def is_tentative(self): + """Returns True if this track is tentative (unconfirmed). + """ + return self.state == TrackState.Tentative + + def is_confirmed(self): + """Returns True if this track is confirmed.""" + return self.state == TrackState.Confirmed + + def is_deleted(self): + """Returns True if this track is dead and should be deleted.""" + return self.state == TrackState.Deleted diff --git a/deep_sort_pytorch/deep_sort/sort/tracker.py b/deep_sort_pytorch/deep_sort/sort/tracker.py new file mode 100644 index 0000000000000000000000000000000000000000..0eb38495f30193f1732840a19f6f71e34c06f458 --- /dev/null +++ b/deep_sort_pytorch/deep_sort/sort/tracker.py @@ -0,0 +1,145 @@ +# vim: expandtab:ts=4:sw=4 +from __future__ import absolute_import +import numpy as np +from . import kalman_filter +from . import linear_assignment +from . import iou_matching +from .track import Track + + +class Tracker: + """ + This is the multi-target tracker. + + Parameters + ---------- + metric : nn_matching.NearestNeighborDistanceMetric + A distance metric for measurement-to-track association. + max_age : int + Maximum number of missed misses before a track is deleted. + n_init : int + Number of consecutive detections before the track is confirmed. The + track state is set to `Deleted` if a miss occurs within the first + `n_init` frames. + + Attributes + ---------- + metric : nn_matching.NearestNeighborDistanceMetric + The distance metric used for measurement to track association. + max_age : int + Maximum number of missed misses before a track is deleted. + n_init : int + Number of frames that a track remains in initialization phase. + kf : kalman_filter.KalmanFilter + A Kalman filter to filter target trajectories in image space. + tracks : List[Track] + The list of active tracks at the current time step. + + """ + + def __init__(self, metric, max_iou_distance=0.7, max_age=70, n_init=3): + self.metric = metric + self.max_iou_distance = max_iou_distance + self.max_age = max_age + self.n_init = n_init + + self.kf = kalman_filter.KalmanFilter() + self.tracks = [] + self._next_id = 1 + + def predict(self): + """Propagate track state distributions one time step forward. + + This function should be called once every time step, before `update`. + """ + for track in self.tracks: + track.predict(self.kf) + + def increment_ages(self): + for track in self.tracks: + track.increment_age() + track.mark_missed() + + def update(self, detections): + """Perform measurement update and track management. + + Parameters + ---------- + detections : List[deep_sort.detection.Detection] + A list of detections at the current time step. + + """ + # Run matching cascade. + matches, unmatched_tracks, unmatched_detections = \ + self._match(detections) + + # Update track set. + for track_idx, detection_idx in matches: + self.tracks[track_idx].update(self.kf, detections[detection_idx]) + for track_idx in unmatched_tracks: + self.tracks[track_idx].mark_missed() + for detection_idx in unmatched_detections: + self._initiate_track(detections[detection_idx]) + self.tracks = [t for t in self.tracks if not t.is_deleted()] + print("LEN self.tracks", len(self.tracks)) + # for t in self.tracks: + # if not t.is_deleted(): + # print(t.__dict__) + + # Update distance metric. + active_targets = [t.track_id for t in self.tracks if t.is_confirmed()] + print(active_targets) + features, targets, oids = [], [], [] + for track in self.tracks: + if not track.is_confirmed(): + continue + features += track.features + targets += [track.track_id for _ in track.features] + # oids += track.oid + track.features = [] + self.metric.partial_fit( + np.asarray(features), np.asarray(targets), active_targets) + + def _match(self, detections): + + def gated_metric(tracks, dets, track_indices, detection_indices): + features = np.array([dets[i].feature for i in detection_indices]) + targets = np.array([tracks[i].track_id for i in track_indices]) + cost_matrix = self.metric.distance(features, targets) + cost_matrix = linear_assignment.gate_cost_matrix( + self.kf, cost_matrix, tracks, dets, track_indices, + detection_indices) + + return cost_matrix + + # Split track set into confirmed and unconfirmed tracks. + confirmed_tracks = [ + i for i, t in enumerate(self.tracks) if t.is_confirmed()] + unconfirmed_tracks = [ + i for i, t in enumerate(self.tracks) if not t.is_confirmed()] + + # Associate confirmed tracks using appearance features. + matches_a, unmatched_tracks_a, unmatched_detections = linear_assignment.matching_cascade(gated_metric, self.metric.matching_threshold, self.max_age, self.tracks, detections, confirmed_tracks) + + # Associate remaining tracks together with unconfirmed tracks using IOU. + iou_track_candidates = unconfirmed_tracks + [ + k for k in unmatched_tracks_a if + self.tracks[k].time_since_update == 1] + unmatched_tracks_a = [ + k for k in unmatched_tracks_a if + self.tracks[k].time_since_update != 1] + matches_b, unmatched_tracks_b, unmatched_detections = \ + linear_assignment.min_cost_matching( + iou_matching.iou_cost, self.max_iou_distance, self.tracks, + detections, iou_track_candidates, unmatched_detections) + + matches = matches_a + matches_b + unmatched_tracks = list(set(unmatched_tracks_a + unmatched_tracks_b)) + return matches, unmatched_tracks, unmatched_detections + + def _initiate_track(self, detection): + mean, covariance = self.kf.initiate(detection.to_xyah()) + self.tracks.append(Track( + mean, covariance, self._next_id, self.n_init, self.max_age, detection.oid, + detection.feature)) + self._next_id += 1 diff --git a/deep_sort_pytorch/utils/__init__.py b/deep_sort_pytorch/utils/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/deep_sort_pytorch/utils/__pycache__/__init__.cpython-310.pyc b/deep_sort_pytorch/utils/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4ff5d0aabb338d8fa864b23aff37afd2044d8f7f Binary files /dev/null and b/deep_sort_pytorch/utils/__pycache__/__init__.cpython-310.pyc differ diff --git a/deep_sort_pytorch/utils/__pycache__/__init__.cpython-39.pyc b/deep_sort_pytorch/utils/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8ba5c405107356987ceb98bcaf60c65effa27ea6 Binary files /dev/null and b/deep_sort_pytorch/utils/__pycache__/__init__.cpython-39.pyc differ diff --git a/deep_sort_pytorch/utils/__pycache__/parser.cpython-310.pyc b/deep_sort_pytorch/utils/__pycache__/parser.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1357ab5501d8ad5b3c99ee69191787c61a57bd9f Binary files /dev/null and b/deep_sort_pytorch/utils/__pycache__/parser.cpython-310.pyc differ diff --git a/deep_sort_pytorch/utils/__pycache__/parser.cpython-39.pyc b/deep_sort_pytorch/utils/__pycache__/parser.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d57ebf066cbcb86e02dd0664309a153c9b5d6576 Binary files /dev/null and b/deep_sort_pytorch/utils/__pycache__/parser.cpython-39.pyc differ diff --git a/deep_sort_pytorch/utils/asserts.py b/deep_sort_pytorch/utils/asserts.py new file mode 100644 index 0000000000000000000000000000000000000000..59a73cc04025762d6490fcd2945a747d963def32 --- /dev/null +++ b/deep_sort_pytorch/utils/asserts.py @@ -0,0 +1,13 @@ +from os import environ + + +def assert_in(file, files_to_check): + if file not in files_to_check: + raise AssertionError("{} does not exist in the list".format(str(file))) + return True + + +def assert_in_env(check_list: list): + for item in check_list: + assert_in(item, environ.keys()) + return True diff --git a/deep_sort_pytorch/utils/draw.py b/deep_sort_pytorch/utils/draw.py new file mode 100644 index 0000000000000000000000000000000000000000..bc7cb537978e86805d5d9789785a8afe67df9030 --- /dev/null +++ b/deep_sort_pytorch/utils/draw.py @@ -0,0 +1,36 @@ +import numpy as np +import cv2 + +palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1) + + +def compute_color_for_labels(label): + """ + Simple function that adds fixed color depending on the class + """ + color = [int((p * (label ** 2 - label + 1)) % 255) for p in palette] + return tuple(color) + + +def draw_boxes(img, bbox, identities=None, offset=(0,0)): + for i,box in enumerate(bbox): + x1,y1,x2,y2 = [int(i) for i in box] + x1 += offset[0] + x2 += offset[0] + y1 += offset[1] + y2 += offset[1] + # box text and bar + id = int(identities[i]) if identities is not None else 0 + color = compute_color_for_labels(id) + label = '{}{:d}'.format("", id) + t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2 , 2)[0] + cv2.rectangle(img,(x1, y1),(x2,y2),color,3) + cv2.rectangle(img,(x1, y1),(x1+t_size[0]+3,y1+t_size[1]+4), color,-1) + cv2.putText(img,label,(x1,y1+t_size[1]+4), cv2.FONT_HERSHEY_PLAIN, 2, [255,255,255], 2) + return img + + + +if __name__ == '__main__': + for i in range(82): + print(compute_color_for_labels(i)) diff --git a/deep_sort_pytorch/utils/evaluation.py b/deep_sort_pytorch/utils/evaluation.py new file mode 100644 index 0000000000000000000000000000000000000000..100179407181933d59809b25400d115cfa789867 --- /dev/null +++ b/deep_sort_pytorch/utils/evaluation.py @@ -0,0 +1,103 @@ +import os +import numpy as np +import copy +import motmetrics as mm +mm.lap.default_solver = 'lap' +from utils.io import read_results, unzip_objs + + +class Evaluator(object): + + def __init__(self, data_root, seq_name, data_type): + self.data_root = data_root + self.seq_name = seq_name + self.data_type = data_type + + self.load_annotations() + self.reset_accumulator() + + def load_annotations(self): + assert self.data_type == 'mot' + + gt_filename = os.path.join(self.data_root, self.seq_name, 'gt', 'gt.txt') + self.gt_frame_dict = read_results(gt_filename, self.data_type, is_gt=True) + self.gt_ignore_frame_dict = read_results(gt_filename, self.data_type, is_ignore=True) + + def reset_accumulator(self): + self.acc = mm.MOTAccumulator(auto_id=True) + + def eval_frame(self, frame_id, trk_tlwhs, trk_ids, rtn_events=False): + # results + trk_tlwhs = np.copy(trk_tlwhs) + trk_ids = np.copy(trk_ids) + + # gts + gt_objs = self.gt_frame_dict.get(frame_id, []) + gt_tlwhs, gt_ids = unzip_objs(gt_objs)[:2] + + # ignore boxes + ignore_objs = self.gt_ignore_frame_dict.get(frame_id, []) + ignore_tlwhs = unzip_objs(ignore_objs)[0] + + + # remove ignored results + keep = np.ones(len(trk_tlwhs), dtype=bool) + iou_distance = mm.distances.iou_matrix(ignore_tlwhs, trk_tlwhs, max_iou=0.5) + if len(iou_distance) > 0: + match_is, match_js = mm.lap.linear_sum_assignment(iou_distance) + match_is, match_js = map(lambda a: np.asarray(a, dtype=int), [match_is, match_js]) + match_ious = iou_distance[match_is, match_js] + + match_js = np.asarray(match_js, dtype=int) + match_js = match_js[np.logical_not(np.isnan(match_ious))] + keep[match_js] = False + trk_tlwhs = trk_tlwhs[keep] + trk_ids = trk_ids[keep] + + # get distance matrix + iou_distance = mm.distances.iou_matrix(gt_tlwhs, trk_tlwhs, max_iou=0.5) + + # acc + self.acc.update(gt_ids, trk_ids, iou_distance) + + if rtn_events and iou_distance.size > 0 and hasattr(self.acc, 'last_mot_events'): + events = self.acc.last_mot_events # only supported by https://github.com/longcw/py-motmetrics + else: + events = None + return events + + def eval_file(self, filename): + self.reset_accumulator() + + result_frame_dict = read_results(filename, self.data_type, is_gt=False) + frames = sorted(list(set(self.gt_frame_dict.keys()) | set(result_frame_dict.keys()))) + for frame_id in frames: + trk_objs = result_frame_dict.get(frame_id, []) + trk_tlwhs, trk_ids = unzip_objs(trk_objs)[:2] + self.eval_frame(frame_id, trk_tlwhs, trk_ids, rtn_events=False) + + return self.acc + + @staticmethod + def get_summary(accs, names, metrics=('mota', 'num_switches', 'idp', 'idr', 'idf1', 'precision', 'recall')): + names = copy.deepcopy(names) + if metrics is None: + metrics = mm.metrics.motchallenge_metrics + metrics = copy.deepcopy(metrics) + + mh = mm.metrics.create() + summary = mh.compute_many( + accs, + metrics=metrics, + names=names, + generate_overall=True + ) + + return summary + + @staticmethod + def save_summary(summary, filename): + import pandas as pd + writer = pd.ExcelWriter(filename) + summary.to_excel(writer) + writer.save() diff --git a/deep_sort_pytorch/utils/io.py b/deep_sort_pytorch/utils/io.py new file mode 100644 index 0000000000000000000000000000000000000000..2dc9afd24019cd930eef6c21ab9f579313dd3b3a --- /dev/null +++ b/deep_sort_pytorch/utils/io.py @@ -0,0 +1,133 @@ +import os +from typing import Dict +import numpy as np + +# from utils.log import get_logger + + +def write_results(filename, results, data_type): + if data_type == 'mot': + save_format = '{frame},{id},{x1},{y1},{w},{h},-1,-1,-1,-1\n' + elif data_type == 'kitti': + save_format = '{frame} {id} pedestrian 0 0 -10 {x1} {y1} {x2} {y2} -10 -10 -10 -1000 -1000 -1000 -10\n' + else: + raise ValueError(data_type) + + with open(filename, 'w') as f: + for frame_id, tlwhs, track_ids in results: + if data_type == 'kitti': + frame_id -= 1 + for tlwh, track_id in zip(tlwhs, track_ids): + if track_id < 0: + continue + x1, y1, w, h = tlwh + x2, y2 = x1 + w, y1 + h + line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h) + f.write(line) + + +# def write_results(filename, results_dict: Dict, data_type: str): +# if not filename: +# return +# path = os.path.dirname(filename) +# if not os.path.exists(path): +# os.makedirs(path) + +# if data_type in ('mot', 'mcmot', 'lab'): +# save_format = '{frame},{id},{x1},{y1},{w},{h},1,-1,-1,-1\n' +# elif data_type == 'kitti': +# save_format = '{frame} {id} pedestrian -1 -1 -10 {x1} {y1} {x2} {y2} -1 -1 -1 -1000 -1000 -1000 -10 {score}\n' +# else: +# raise ValueError(data_type) + +# with open(filename, 'w') as f: +# for frame_id, frame_data in results_dict.items(): +# if data_type == 'kitti': +# frame_id -= 1 +# for tlwh, track_id in frame_data: +# if track_id < 0: +# continue +# x1, y1, w, h = tlwh +# x2, y2 = x1 + w, y1 + h +# line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h, score=1.0) +# f.write(line) +# logger.info('Save results to {}'.format(filename)) + + +def read_results(filename, data_type: str, is_gt=False, is_ignore=False): + if data_type in ('mot', 'lab'): + read_fun = read_mot_results + else: + raise ValueError('Unknown data type: {}'.format(data_type)) + + return read_fun(filename, is_gt, is_ignore) + + +""" +labels={'ped', ... % 1 +'person_on_vhcl', ... % 2 +'car', ... % 3 +'bicycle', ... % 4 +'mbike', ... % 5 +'non_mot_vhcl', ... % 6 +'static_person', ... % 7 +'distractor', ... % 8 +'occluder', ... % 9 +'occluder_on_grnd', ... %10 +'occluder_full', ... % 11 +'reflection', ... % 12 +'crowd' ... % 13 +}; +""" + + +def read_mot_results(filename, is_gt, is_ignore): + valid_labels = {1} + ignore_labels = {2, 7, 8, 12} + results_dict = dict() + if os.path.isfile(filename): + with open(filename, 'r') as f: + for line in f.readlines(): + linelist = line.split(',') + if len(linelist) < 7: + continue + fid = int(linelist[0]) + if fid < 1: + continue + results_dict.setdefault(fid, list()) + + if is_gt: + if 'MOT16-' in filename or 'MOT17-' in filename: + label = int(float(linelist[7])) + mark = int(float(linelist[6])) + if mark == 0 or label not in valid_labels: + continue + score = 1 + elif is_ignore: + if 'MOT16-' in filename or 'MOT17-' in filename: + label = int(float(linelist[7])) + vis_ratio = float(linelist[8]) + if label not in ignore_labels and vis_ratio >= 0: + continue + else: + continue + score = 1 + else: + score = float(linelist[6]) + + tlwh = tuple(map(float, linelist[2:6])) + target_id = int(linelist[1]) + + results_dict[fid].append((tlwh, target_id, score)) + + return results_dict + + +def unzip_objs(objs): + if len(objs) > 0: + tlwhs, ids, scores = zip(*objs) + else: + tlwhs, ids, scores = [], [], [] + tlwhs = np.asarray(tlwhs, dtype=float).reshape(-1, 4) + + return tlwhs, ids, scores \ No newline at end of file diff --git a/deep_sort_pytorch/utils/json_logger.py b/deep_sort_pytorch/utils/json_logger.py new file mode 100644 index 0000000000000000000000000000000000000000..0afd0b45df736866c49473db78286685d77660ac --- /dev/null +++ b/deep_sort_pytorch/utils/json_logger.py @@ -0,0 +1,383 @@ +""" +References: + https://medium.com/analytics-vidhya/creating-a-custom-logging-mechanism-for-real-time-object-detection-using-tdd-4ca2cfcd0a2f +""" +import json +from os import makedirs +from os.path import exists, join +from datetime import datetime + + +class JsonMeta(object): + HOURS = 3 + MINUTES = 59 + SECONDS = 59 + PATH_TO_SAVE = 'LOGS' + DEFAULT_FILE_NAME = 'remaining' + + +class BaseJsonLogger(object): + """ + This is the base class that returns __dict__ of its own + it also returns the dicts of objects in the attributes that are list instances + + """ + + def dic(self): + # returns dicts of objects + out = {} + for k, v in self.__dict__.items(): + if hasattr(v, 'dic'): + out[k] = v.dic() + elif isinstance(v, list): + out[k] = self.list(v) + else: + out[k] = v + return out + + @staticmethod + def list(values): + # applies the dic method on items in the list + return [v.dic() if hasattr(v, 'dic') else v for v in values] + + +class Label(BaseJsonLogger): + """ + For each bounding box there are various categories with confidences. Label class keeps track of that information. + """ + + def __init__(self, category: str, confidence: float): + self.category = category + self.confidence = confidence + + +class Bbox(BaseJsonLogger): + """ + This module stores the information for each frame and use them in JsonParser + Attributes: + labels (list): List of label module. + top (int): + left (int): + width (int): + height (int): + + Args: + bbox_id (float): + top (int): + left (int): + width (int): + height (int): + + References: + Check Label module for better understanding. + + + """ + + def __init__(self, bbox_id, top, left, width, height): + self.labels = [] + self.bbox_id = bbox_id + self.top = top + self.left = left + self.width = width + self.height = height + + def add_label(self, category, confidence): + # adds category and confidence only if top_k is not exceeded. + self.labels.append(Label(category, confidence)) + + def labels_full(self, value): + return len(self.labels) == value + + +class Frame(BaseJsonLogger): + """ + This module stores the information for each frame and use them in JsonParser + Attributes: + timestamp (float): The elapsed time of captured frame + frame_id (int): The frame number of the captured video + bboxes (list of Bbox objects): Stores the list of bbox objects. + + References: + Check Bbox class for better information + + Args: + timestamp (float): + frame_id (int): + + """ + + def __init__(self, frame_id: int, timestamp: float = None): + self.frame_id = frame_id + self.timestamp = timestamp + self.bboxes = [] + + def add_bbox(self, bbox_id: int, top: int, left: int, width: int, height: int): + bboxes_ids = [bbox.bbox_id for bbox in self.bboxes] + if bbox_id not in bboxes_ids: + self.bboxes.append(Bbox(bbox_id, top, left, width, height)) + else: + raise ValueError("Frame with id: {} already has a Bbox with id: {}".format(self.frame_id, bbox_id)) + + def add_label_to_bbox(self, bbox_id: int, category: str, confidence: float): + bboxes = {bbox.id: bbox for bbox in self.bboxes} + if bbox_id in bboxes.keys(): + res = bboxes.get(bbox_id) + res.add_label(category, confidence) + else: + raise ValueError('the bbox with id: {} does not exists!'.format(bbox_id)) + + +class BboxToJsonLogger(BaseJsonLogger): + """ + ُ This module is designed to automate the task of logging jsons. An example json is used + to show the contents of json file shortly + Example: + { + "video_details": { + "frame_width": 1920, + "frame_height": 1080, + "frame_rate": 20, + "video_name": "/home/gpu/codes/MSD/pedestrian_2/project/public/camera1.avi" + }, + "frames": [ + { + "frame_id": 329, + "timestamp": 3365.1254 + "bboxes": [ + { + "labels": [ + { + "category": "pedestrian", + "confidence": 0.9 + } + ], + "bbox_id": 0, + "top": 1257, + "left": 138, + "width": 68, + "height": 109 + } + ] + }], + + Attributes: + frames (dict): It's a dictionary that maps each frame_id to json attributes. + video_details (dict): information about video file. + top_k_labels (int): shows the allowed number of labels + start_time (datetime object): we use it to automate the json output by time. + + Args: + top_k_labels (int): shows the allowed number of labels + + """ + + def __init__(self, top_k_labels: int = 1): + self.frames = {} + self.video_details = self.video_details = dict(frame_width=None, frame_height=None, frame_rate=None, + video_name=None) + self.top_k_labels = top_k_labels + self.start_time = datetime.now() + + def set_top_k(self, value): + self.top_k_labels = value + + def frame_exists(self, frame_id: int) -> bool: + """ + Args: + frame_id (int): + + Returns: + bool: true if frame_id is recognized + """ + return frame_id in self.frames.keys() + + def add_frame(self, frame_id: int, timestamp: float = None) -> None: + """ + Args: + frame_id (int): + timestamp (float): opencv captured frame time property + + Raises: + ValueError: if frame_id would not exist in class frames attribute + + Returns: + None + + """ + if not self.frame_exists(frame_id): + self.frames[frame_id] = Frame(frame_id, timestamp) + else: + raise ValueError("Frame id: {} already exists".format(frame_id)) + + def bbox_exists(self, frame_id: int, bbox_id: int) -> bool: + """ + Args: + frame_id: + bbox_id: + + Returns: + bool: if bbox exists in frame bboxes list + """ + bboxes = [] + if self.frame_exists(frame_id=frame_id): + bboxes = [bbox.bbox_id for bbox in self.frames[frame_id].bboxes] + return bbox_id in bboxes + + def find_bbox(self, frame_id: int, bbox_id: int): + """ + + Args: + frame_id: + bbox_id: + + Returns: + bbox_id (int): + + Raises: + ValueError: if bbox_id does not exist in the bbox list of specific frame. + """ + if not self.bbox_exists(frame_id, bbox_id): + raise ValueError("frame with id: {} does not contain bbox with id: {}".format(frame_id, bbox_id)) + bboxes = {bbox.bbox_id: bbox for bbox in self.frames[frame_id].bboxes} + return bboxes.get(bbox_id) + + def add_bbox_to_frame(self, frame_id: int, bbox_id: int, top: int, left: int, width: int, height: int) -> None: + """ + + Args: + frame_id (int): + bbox_id (int): + top (int): + left (int): + width (int): + height (int): + + Returns: + None + + Raises: + ValueError: if bbox_id already exist in frame information with frame_id + ValueError: if frame_id does not exist in frames attribute + """ + if self.frame_exists(frame_id): + frame = self.frames[frame_id] + if not self.bbox_exists(frame_id, bbox_id): + frame.add_bbox(bbox_id, top, left, width, height) + else: + raise ValueError( + "frame with frame_id: {} already contains the bbox with id: {} ".format(frame_id, bbox_id)) + else: + raise ValueError("frame with frame_id: {} does not exist".format(frame_id)) + + def add_label_to_bbox(self, frame_id: int, bbox_id: int, category: str, confidence: float): + """ + Args: + frame_id: + bbox_id: + category: + confidence: the confidence value returned from yolo detection + + Returns: + None + + Raises: + ValueError: if labels quota (top_k_labels) exceeds. + """ + bbox = self.find_bbox(frame_id, bbox_id) + if not bbox.labels_full(self.top_k_labels): + bbox.add_label(category, confidence) + else: + raise ValueError("labels in frame_id: {}, bbox_id: {} is fulled".format(frame_id, bbox_id)) + + def add_video_details(self, frame_width: int = None, frame_height: int = None, frame_rate: int = None, + video_name: str = None): + self.video_details['frame_width'] = frame_width + self.video_details['frame_height'] = frame_height + self.video_details['frame_rate'] = frame_rate + self.video_details['video_name'] = video_name + + def output(self): + output = {'video_details': self.video_details} + result = list(self.frames.values()) + output['frames'] = [item.dic() for item in result] + return output + + def json_output(self, output_name): + """ + Args: + output_name: + + Returns: + None + + Notes: + It creates the json output with `output_name` name. + """ + if not output_name.endswith('.json'): + output_name += '.json' + with open(output_name, 'w') as file: + json.dump(self.output(), file) + file.close() + + def set_start(self): + self.start_time = datetime.now() + + def schedule_output_by_time(self, output_dir=JsonMeta.PATH_TO_SAVE, hours: int = 0, minutes: int = 0, + seconds: int = 60) -> None: + """ + Notes: + Creates folder and then periodically stores the jsons on that address. + + Args: + output_dir (str): the directory where output files will be stored + hours (int): + minutes (int): + seconds (int): + + Returns: + None + + """ + end = datetime.now() + interval = 0 + interval += abs(min([hours, JsonMeta.HOURS]) * 3600) + interval += abs(min([minutes, JsonMeta.MINUTES]) * 60) + interval += abs(min([seconds, JsonMeta.SECONDS])) + diff = (end - self.start_time).seconds + + if diff > interval: + output_name = self.start_time.strftime('%Y-%m-%d %H-%M-%S') + '.json' + if not exists(output_dir): + makedirs(output_dir) + output = join(output_dir, output_name) + self.json_output(output_name=output) + self.frames = {} + self.start_time = datetime.now() + + def schedule_output_by_frames(self, frames_quota, frame_counter, output_dir=JsonMeta.PATH_TO_SAVE): + """ + saves as the number of frames quota increases higher. + :param frames_quota: + :param frame_counter: + :param output_dir: + :return: + """ + pass + + def flush(self, output_dir): + """ + Notes: + We use this function to output jsons whenever possible. + like the time that we exit the while loop of opencv. + + Args: + output_dir: + + Returns: + None + + """ + filename = self.start_time.strftime('%Y-%m-%d %H-%M-%S') + '-remaining.json' + output = join(output_dir, filename) + self.json_output(output_name=output) diff --git a/deep_sort_pytorch/utils/log.py b/deep_sort_pytorch/utils/log.py new file mode 100644 index 0000000000000000000000000000000000000000..0d48757dca88f35e9ea2cd1ca16e41bac9976a45 --- /dev/null +++ b/deep_sort_pytorch/utils/log.py @@ -0,0 +1,17 @@ +import logging + + +def get_logger(name='root'): + formatter = logging.Formatter( + # fmt='%(asctime)s [%(levelname)s]: %(filename)s(%(funcName)s:%(lineno)s) >> %(message)s') + fmt='%(asctime)s [%(levelname)s]: %(message)s', datefmt='%Y-%m-%d %H:%M:%S') + + handler = logging.StreamHandler() + handler.setFormatter(formatter) + + logger = logging.getLogger(name) + logger.setLevel(logging.INFO) + logger.addHandler(handler) + return logger + + diff --git a/deep_sort_pytorch/utils/parser.py b/deep_sort_pytorch/utils/parser.py new file mode 100644 index 0000000000000000000000000000000000000000..449d1aaac85c917e223f61535e0f24bd9e197489 --- /dev/null +++ b/deep_sort_pytorch/utils/parser.py @@ -0,0 +1,41 @@ +import os +import yaml +from easydict import EasyDict as edict + + +class YamlParser(edict): + """ + This is yaml parser based on EasyDict. + """ + + def __init__(self, cfg_dict=None, config_file=None): + if cfg_dict is None: + cfg_dict = {} + + if config_file is not None: + assert(os.path.isfile(config_file)) + with open(config_file, 'r') as fo: + yaml_ = yaml.load(fo.read(), Loader=yaml.FullLoader) + cfg_dict.update(yaml_) + + super(YamlParser, self).__init__(cfg_dict) + + def merge_from_file(self, config_file): + with open(config_file, 'r') as fo: + yaml_ = yaml.load(fo.read(), Loader=yaml.FullLoader) + self.update(yaml_) + + def merge_from_dict(self, config_dict): + self.update(config_dict) + + +def get_config(config_file=None): + return YamlParser(config_file=config_file) + + +if __name__ == "__main__": + cfg = YamlParser(config_file="../configs/yolov3.yaml") + cfg.merge_from_file("../configs/deep_sort.yaml") + + import ipdb + ipdb.set_trace() diff --git a/deep_sort_pytorch/utils/tools.py b/deep_sort_pytorch/utils/tools.py new file mode 100644 index 0000000000000000000000000000000000000000..965fb69c2df41510fd740a4ab57d8fc7b81012de --- /dev/null +++ b/deep_sort_pytorch/utils/tools.py @@ -0,0 +1,39 @@ +from functools import wraps +from time import time + + +def is_video(ext: str): + """ + Returns true if ext exists in + allowed_exts for video files. + + Args: + ext: + + Returns: + + """ + + allowed_exts = ('.mp4', '.webm', '.ogg', '.avi', '.wmv', '.mkv', '.3gp') + return any((ext.endswith(x) for x in allowed_exts)) + + +def tik_tok(func): + """ + keep track of time for each process. + Args: + func: + + Returns: + + """ + @wraps(func) + def _time_it(*args, **kwargs): + start = time() + try: + return func(*args, **kwargs) + finally: + end_ = time() + print("time: {:.03f}s, fps: {:.03f}".format(end_ - start, 1 / (end_ - start))) + + return _time_it diff --git a/download_weights.py b/download_weights.py new file mode 100644 index 0000000000000000000000000000000000000000..86cab081a2f27a33e71cd34f9b1a63f22daf379b --- /dev/null +++ b/download_weights.py @@ -0,0 +1,34 @@ +import gdown +import zipfile +import os + +def exractfiles(file, dest): + with zipfile.ZipFile(file, 'r') as zip_ref: + zip_ref.extractall(dest) + + +def download_model(): + model_url = '1rbQtfTpDIiyRxsrW5uQbfSxnvzcN76Ab' + yolor = '1KEanvTOJoMlMDw0A-6Nw7nXmVylhnJu-' + url = f'https://drive.google.com/uc?id={model_url}' + gdown.download(url,output='weights.zip', quiet=False) + + url = f'https://drive.google.com/uc?id={yolor}' + gdown.download(url,output='yolor_p6.pt', quiet=False) + + deepsort = '1VZ05gzg249Q1m8BJVQxl3iHoNIbjzJf8' + url = f'https://drive.google.com/uc?id={deepsort}' + gdown.download(url,output='ckpt.zip', quiet=False) + + + print('Download Completed Successfully!') + + print('Extracting and Moving Weights....') + exractfiles('weights.zip', './yolov7/') + exractfiles('ckpt.zip', './deep_sort_pytorch/deep_sort/deep/checkpoint/') + print('Extracting and Moving Weights Completed!') + os.remove('weights.zip') + os.remove('ckpt.zip') + +if __name__ == "__main__": + download_model() \ No newline at end of file diff --git a/environment.yml b/environment.yml new file mode 100644 index 0000000000000000000000000000000000000000..687adb56d0b409a6ebfbd307822c3a42fa3537b0 --- /dev/null +++ b/environment.yml @@ -0,0 +1,35 @@ +name: yolov7_bytetrack +channels: + - pytorch + - defaults +dependencies: + - cudatoolkit=11.3.1 + - cython=0.29.30 + - ffmpeg=4.2.2 + - numpy=1.23.1 + - numpy-base=1.23.1 + - pytorch=1.12.1 + - pytorch-mutex=1.0 + - setuptools=63.4.1 + - streamlit=1.11.0 + - torchvision=0.13.1 + - tqdm=4.64.0 + - wheel=0.37.1 + - yaml=0.2.5 + - pip: + - click==8.1.3 + - coloredlogs==15.0.1 + - easydict==1.9 + - gdown==4.5.1 + - lap==0.4.0 + - matplotlib==3.5.3 + - onnxruntime-gpu==1.12.1 + - opencv-python==4.6.0.66 + - pycocotools==2.0.4 + - pytz==2022.2.1 + - pyyaml==6.0 + - scipy==1.9.1 + - tensorboard==2.10.0 + - tensorboard-data-server==0.6.1 + - tensorboard-plugin-wit==1.8.1 + - urllib3==1.26.12 \ No newline at end of file diff --git a/inference/.DS_Store b/inference/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..2d4e4732a813a17eedb740216e2dc68ee94e929c Binary files /dev/null and b/inference/.DS_Store differ diff --git a/inference/output/results.mp4 b/inference/output/results.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d60612e3ea75e2dbfa5e364cbcc129d585070531 --- /dev/null +++ b/inference/output/results.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:126eec207607d10d1dc9239bda7651b17ddb5c7d89b7cc2c9907e7e10824dc4d +size 5857623 diff --git a/models/__init__.py b/models/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc --- /dev/null +++ b/models/__init__.py @@ -0,0 +1 @@ + diff --git a/models/__pycache__/__init__.cpython-310.pyc b/models/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1af722fa7770d75f53f05d96b3fd8162de4b147e Binary files /dev/null and b/models/__pycache__/__init__.cpython-310.pyc differ diff --git a/models/__pycache__/__init__.cpython-39.pyc b/models/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..90c23101d7d753dd52a8b79b24cfaba9945384ea Binary files /dev/null and b/models/__pycache__/__init__.cpython-39.pyc differ diff --git a/models/__pycache__/models.cpython-310.pyc b/models/__pycache__/models.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..57955084bc57551addac5984c0de742e958c2ae7 Binary files /dev/null and b/models/__pycache__/models.cpython-310.pyc differ diff --git a/models/__pycache__/models.cpython-39.pyc b/models/__pycache__/models.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..df2c8fdae96967f4f24b69bb29597ae6c5dfcca5 Binary files /dev/null and b/models/__pycache__/models.cpython-39.pyc differ diff --git a/models/export.py b/models/export.py new file mode 100644 index 0000000000000000000000000000000000000000..d91813a0acaa9ab88a99ed5343a72e28d5cf275f --- /dev/null +++ b/models/export.py @@ -0,0 +1,68 @@ +import argparse + +import torch + +from utils.google_utils import attempt_download + +if __name__ == '__main__': + parser = argparse.ArgumentParser() + parser.add_argument('--weights', type=str, default='./yolov4.pt', help='weights path') + parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') + parser.add_argument('--batch-size', type=int, default=1, help='batch size') + opt = parser.parse_args() + opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand + print(opt) + + # Input + img = torch.zeros((opt.batch_size, 3, *opt.img_size)) # image size(1,3,320,192) iDetection + + # Load PyTorch model + attempt_download(opt.weights) + model = torch.load(opt.weights, map_location=torch.device('cpu'))['model'].float() + model.eval() + model.model[-1].export = True # set Detect() layer export=True + y = model(img) # dry run + + # TorchScript export + try: + print('\nStarting TorchScript export with torch %s...' % torch.__version__) + f = opt.weights.replace('.pt', '.torchscript.pt') # filename + ts = torch.jit.trace(model, img) + ts.save(f) + print('TorchScript export success, saved as %s' % f) + except Exception as e: + print('TorchScript export failure: %s' % e) + + # ONNX export + try: + import onnx + + print('\nStarting ONNX export with onnx %s...' % onnx.__version__) + f = opt.weights.replace('.pt', '.onnx') # filename + model.fuse() # only for ONNX + torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'], + output_names=['classes', 'boxes'] if y is None else ['output']) + + # Checks + onnx_model = onnx.load(f) # load onnx model + onnx.checker.check_model(onnx_model) # check onnx model + print(onnx.helper.printable_graph(onnx_model.graph)) # print a human readable model + print('ONNX export success, saved as %s' % f) + except Exception as e: + print('ONNX export failure: %s' % e) + + # CoreML export + try: + import coremltools as ct + + print('\nStarting CoreML export with coremltools %s...' % ct.__version__) + # convert model from torchscript and apply pixel scaling as per detect.py + model = ct.convert(ts, inputs=[ct.ImageType(name='images', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])]) + f = opt.weights.replace('.pt', '.mlmodel') # filename + model.save(f) + print('CoreML export success, saved as %s' % f) + except Exception as e: + print('CoreML export failure: %s' % e) + + # Finish + print('\nExport complete. Visualize with https://github.com/lutzroeder/netron.') diff --git a/models/models.py b/models/models.py new file mode 100644 index 0000000000000000000000000000000000000000..76c44b63a5e636932ab358d3b722aed2828303f4 --- /dev/null +++ b/models/models.py @@ -0,0 +1,761 @@ +from utils.google_utils import * +from utils.layers import * +from utils.parse_config import * +from utils import torch_utils + +ONNX_EXPORT = False + + +def create_modules(module_defs, img_size, cfg): + # Constructs module list of layer blocks from module configuration in module_defs + + img_size = [img_size] * 2 if isinstance(img_size, int) else img_size # expand if necessary + _ = module_defs.pop(0) # cfg training hyperparams (unused) + output_filters = [3] # input channels + module_list = nn.ModuleList() + routs = [] # list of layers which rout to deeper layers + yolo_index = -1 + + for i, mdef in enumerate(module_defs): + modules = nn.Sequential() + + if mdef['type'] == 'convolutional': + bn = mdef['batch_normalize'] + filters = mdef['filters'] + k = mdef['size'] # kernel size + stride = mdef['stride'] if 'stride' in mdef else (mdef['stride_y'], mdef['stride_x']) + if isinstance(k, int): # single-size conv + modules.add_module('Conv2d', nn.Conv2d(in_channels=output_filters[-1], + out_channels=filters, + kernel_size=k, + stride=stride, + padding=k // 2 if mdef['pad'] else 0, + groups=mdef['groups'] if 'groups' in mdef else 1, + bias=not bn)) + else: # multiple-size conv + modules.add_module('MixConv2d', MixConv2d(in_ch=output_filters[-1], + out_ch=filters, + k=k, + stride=stride, + bias=not bn)) + + if bn: + modules.add_module('BatchNorm2d', nn.BatchNorm2d(filters, momentum=0.03, eps=1E-4)) + else: + routs.append(i) # detection output (goes into yolo layer) + + if mdef['activation'] == 'leaky': # activation study https://github.com/ultralytics/yolov3/issues/441 + modules.add_module('activation', nn.LeakyReLU(0.1, inplace=True)) + elif mdef['activation'] == 'swish': + modules.add_module('activation', Swish()) + elif mdef['activation'] == 'mish': + modules.add_module('activation', Mish()) + elif mdef['activation'] == 'emb': + modules.add_module('activation', F.normalize()) + elif mdef['activation'] == 'logistic': + modules.add_module('activation', nn.Sigmoid()) + elif mdef['activation'] == 'silu': + modules.add_module('activation', nn.SiLU()) + + elif mdef['type'] == 'deformableconvolutional': + bn = mdef['batch_normalize'] + filters = mdef['filters'] + k = mdef['size'] # kernel size + stride = mdef['stride'] if 'stride' in mdef else (mdef['stride_y'], mdef['stride_x']) + if isinstance(k, int): # single-size conv + modules.add_module('DeformConv2d', DeformConv2d(output_filters[-1], + filters, + kernel_size=k, + padding=k // 2 if mdef['pad'] else 0, + stride=stride, + bias=not bn, + modulation=True)) + else: # multiple-size conv + modules.add_module('MixConv2d', MixConv2d(in_ch=output_filters[-1], + out_ch=filters, + k=k, + stride=stride, + bias=not bn)) + + if bn: + modules.add_module('BatchNorm2d', nn.BatchNorm2d(filters, momentum=0.03, eps=1E-4)) + else: + routs.append(i) # detection output (goes into yolo layer) + + if mdef['activation'] == 'leaky': # activation study https://github.com/ultralytics/yolov3/issues/441 + modules.add_module('activation', nn.LeakyReLU(0.1, inplace=True)) + elif mdef['activation'] == 'swish': + modules.add_module('activation', Swish()) + elif mdef['activation'] == 'mish': + modules.add_module('activation', Mish()) + elif mdef['activation'] == 'silu': + modules.add_module('activation', nn.SiLU()) + + elif mdef['type'] == 'dropout': + p = mdef['probability'] + modules = nn.Dropout(p) + + elif mdef['type'] == 'avgpool': + modules = GAP() + + elif mdef['type'] == 'silence': + filters = output_filters[-1] + modules = Silence() + + elif mdef['type'] == 'scale_channels': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = ScaleChannel(layers=layers) + + elif mdef['type'] == 'shift_channels': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = ShiftChannel(layers=layers) + + elif mdef['type'] == 'shift_channels_2d': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = ShiftChannel2D(layers=layers) + + elif mdef['type'] == 'control_channels': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = ControlChannel(layers=layers) + + elif mdef['type'] == 'control_channels_2d': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = ControlChannel2D(layers=layers) + + elif mdef['type'] == 'alternate_channels': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] * 2 + routs.extend([i + l if l < 0 else l for l in layers]) + modules = AlternateChannel(layers=layers) + + elif mdef['type'] == 'alternate_channels_2d': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] * 2 + routs.extend([i + l if l < 0 else l for l in layers]) + modules = AlternateChannel2D(layers=layers) + + elif mdef['type'] == 'select_channels': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = SelectChannel(layers=layers) + + elif mdef['type'] == 'select_channels_2d': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = SelectChannel2D(layers=layers) + + elif mdef['type'] == 'sam': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = ScaleSpatial(layers=layers) + + elif mdef['type'] == 'BatchNorm2d': + filters = output_filters[-1] + modules = nn.BatchNorm2d(filters, momentum=0.03, eps=1E-4) + if i == 0 and filters == 3: # normalize RGB image + # imagenet mean and var https://pytorch.org/docs/stable/torchvision/models.html#classification + modules.running_mean = torch.tensor([0.485, 0.456, 0.406]) + modules.running_var = torch.tensor([0.0524, 0.0502, 0.0506]) + + elif mdef['type'] == 'maxpool': + k = mdef['size'] # kernel size + stride = mdef['stride'] + maxpool = nn.MaxPool2d(kernel_size=k, stride=stride, padding=(k - 1) // 2) + if k == 2 and stride == 1: # yolov3-tiny + modules.add_module('ZeroPad2d', nn.ZeroPad2d((0, 1, 0, 1))) + modules.add_module('MaxPool2d', maxpool) + else: + modules = maxpool + + elif mdef['type'] == 'local_avgpool': + k = mdef['size'] # kernel size + stride = mdef['stride'] + avgpool = nn.AvgPool2d(kernel_size=k, stride=stride, padding=(k - 1) // 2) + if k == 2 and stride == 1: # yolov3-tiny + modules.add_module('ZeroPad2d', nn.ZeroPad2d((0, 1, 0, 1))) + modules.add_module('AvgPool2d', avgpool) + else: + modules = avgpool + + elif mdef['type'] == 'upsample': + if ONNX_EXPORT: # explicitly state size, avoid scale_factor + g = (yolo_index + 1) * 2 / 32 # gain + modules = nn.Upsample(size=tuple(int(x * g) for x in img_size)) # img_size = (320, 192) + else: + modules = nn.Upsample(scale_factor=mdef['stride']) + + elif mdef['type'] == 'route': # nn.Sequential() placeholder for 'route' layer + layers = mdef['layers'] + filters = sum([output_filters[l + 1 if l > 0 else l] for l in layers]) + routs.extend([i + l if l < 0 else l for l in layers]) + modules = FeatureConcat(layers=layers) + + elif mdef['type'] == 'route2': # nn.Sequential() placeholder for 'route' layer + layers = mdef['layers'] + filters = sum([output_filters[l + 1 if l > 0 else l] for l in layers]) + routs.extend([i + l if l < 0 else l for l in layers]) + modules = FeatureConcat2(layers=layers) + + elif mdef['type'] == 'route3': # nn.Sequential() placeholder for 'route' layer + layers = mdef['layers'] + filters = sum([output_filters[l + 1 if l > 0 else l] for l in layers]) + routs.extend([i + l if l < 0 else l for l in layers]) + modules = FeatureConcat3(layers=layers) + + elif mdef['type'] == 'route_lhalf': # nn.Sequential() placeholder for 'route' layer + layers = mdef['layers'] + filters = sum([output_filters[l + 1 if l > 0 else l] for l in layers])//2 + routs.extend([i + l if l < 0 else l for l in layers]) + modules = FeatureConcat_l(layers=layers) + + elif mdef['type'] == 'shortcut': # nn.Sequential() placeholder for 'shortcut' layer + layers = mdef['from'] + filters = output_filters[-1] + routs.extend([i + l if l < 0 else l for l in layers]) + modules = WeightedFeatureFusion(layers=layers, weight='weights_type' in mdef) + + elif mdef['type'] == 'reorg3d': # yolov3-spp-pan-scale + pass + + elif mdef['type'] == 'reorg': # yolov3-spp-pan-scale + filters = 4 * output_filters[-1] + modules.add_module('Reorg', Reorg()) + + elif mdef['type'] == 'dwt': # yolov3-spp-pan-scale + filters = 4 * output_filters[-1] + modules.add_module('DWT', DWT()) + + elif mdef['type'] == 'implicit_add': # yolov3-spp-pan-scale + filters = mdef['filters'] + modules = ImplicitA(channel=filters) + + elif mdef['type'] == 'implicit_mul': # yolov3-spp-pan-scale + filters = mdef['filters'] + modules = ImplicitM(channel=filters) + + elif mdef['type'] == 'implicit_cat': # yolov3-spp-pan-scale + filters = mdef['filters'] + modules = ImplicitC(channel=filters) + + elif mdef['type'] == 'implicit_add_2d': # yolov3-spp-pan-scale + channels = mdef['filters'] + filters = mdef['atoms'] + modules = Implicit2DA(atom=filters, channel=channels) + + elif mdef['type'] == 'implicit_mul_2d': # yolov3-spp-pan-scale + channels = mdef['filters'] + filters = mdef['atoms'] + modules = Implicit2DM(atom=filters, channel=channels) + + elif mdef['type'] == 'implicit_cat_2d': # yolov3-spp-pan-scale + channels = mdef['filters'] + filters = mdef['atoms'] + modules = Implicit2DC(atom=filters, channel=channels) + + elif mdef['type'] == 'yolo': + yolo_index += 1 + stride = [8, 16, 32, 64, 128] # P3, P4, P5, P6, P7 strides + if any(x in cfg for x in ['yolov4-tiny', 'fpn', 'yolov3']): # P5, P4, P3 strides + stride = [32, 16, 8] + layers = mdef['from'] if 'from' in mdef else [] + modules = YOLOLayer(anchors=mdef['anchors'][mdef['mask']], # anchor list + nc=mdef['classes'], # number of classes + img_size=img_size, # (416, 416) + yolo_index=yolo_index, # 0, 1, 2... + layers=layers, # output layers + stride=stride[yolo_index]) + + # Initialize preceding Conv2d() bias (https://arxiv.org/pdf/1708.02002.pdf section 3.3) + try: + j = layers[yolo_index] if 'from' in mdef else -2 + bias_ = module_list[j][0].bias # shape(255,) + bias = bias_[:modules.no * modules.na].view(modules.na, -1) # shape(3,85) + #bias[:, 4] += -4.5 # obj + bias.data[:, 4] += math.log(8 / (640 / stride[yolo_index]) ** 2) # obj (8 objects per 640 image) + bias.data[:, 5:] += math.log(0.6 / (modules.nc - 0.99)) # cls (sigmoid(p) = 1/nc) + module_list[j][0].bias = torch.nn.Parameter(bias_, requires_grad=bias_.requires_grad) + + #j = [-2, -5, -8] + #for sj in j: + # bias_ = module_list[sj][0].bias + # bias = bias_[:modules.no * 1].view(1, -1) + # bias.data[:, 4] += math.log(8 / (640 / stride[yolo_index]) ** 2) + # bias.data[:, 5:] += math.log(0.6 / (modules.nc - 0.99)) + # module_list[sj][0].bias = torch.nn.Parameter(bias_, requires_grad=bias_.requires_grad) + except: + print('WARNING: smart bias initialization failure.') + + elif mdef['type'] == 'jde': + yolo_index += 1 + stride = [8, 16, 32, 64, 128] # P3, P4, P5, P6, P7 strides + if any(x in cfg for x in ['yolov4-tiny', 'fpn', 'yolov3']): # P5, P4, P3 strides + stride = [32, 16, 8] + layers = mdef['from'] if 'from' in mdef else [] + modules = JDELayer(anchors=mdef['anchors'][mdef['mask']], # anchor list + nc=mdef['classes'], # number of classes + img_size=img_size, # (416, 416) + yolo_index=yolo_index, # 0, 1, 2... + layers=layers, # output layers + stride=stride[yolo_index]) + + # Initialize preceding Conv2d() bias (https://arxiv.org/pdf/1708.02002.pdf section 3.3) + try: + j = layers[yolo_index] if 'from' in mdef else -1 + bias_ = module_list[j][0].bias # shape(255,) + bias = bias_[:modules.no * modules.na].view(modules.na, -1) # shape(3,85) + #bias[:, 4] += -4.5 # obj + bias.data[:, 4] += math.log(8 / (640 / stride[yolo_index]) ** 2) # obj (8 objects per 640 image) + bias.data[:, 5:] += math.log(0.6 / (modules.nc - 0.99)) # cls (sigmoid(p) = 1/nc) + module_list[j][0].bias = torch.nn.Parameter(bias_, requires_grad=bias_.requires_grad) + except: + print('WARNING: smart bias initialization failure.') + + else: + print('Warning: Unrecognized Layer Type: ' + mdef['type']) + + # Register module list and number of output filters + module_list.append(modules) + output_filters.append(filters) + + routs_binary = [False] * (i + 1) + for i in routs: + routs_binary[i] = True + return module_list, routs_binary + + +class YOLOLayer(nn.Module): + def __init__(self, anchors, nc, img_size, yolo_index, layers, stride): + super(YOLOLayer, self).__init__() + self.anchors = torch.Tensor(anchors) + self.index = yolo_index # index of this layer in layers + self.layers = layers # model output layer indices + self.stride = stride # layer stride + self.nl = len(layers) # number of output layers (3) + self.na = len(anchors) # number of anchors (3) + self.nc = nc # number of classes (80) + self.no = nc + 5 # number of outputs (85) + self.nx, self.ny, self.ng = 0, 0, 0 # initialize number of x, y gridpoints + self.anchor_vec = self.anchors / self.stride + self.anchor_wh = self.anchor_vec.view(1, self.na, 1, 1, 2) + + if ONNX_EXPORT: + self.training = False + self.create_grids((img_size[1] // stride, img_size[0] // stride)) # number x, y grid points + + def create_grids(self, ng=(13, 13), device='cpu'): + self.nx, self.ny = ng # x and y grid size + self.ng = torch.tensor(ng, dtype=torch.float) + + # build xy offsets + if not self.training: + yv, xv = torch.meshgrid([torch.arange(self.ny, device=device), torch.arange(self.nx, device=device)]) + self.grid = torch.stack((xv, yv), 2).view((1, 1, self.ny, self.nx, 2)).float() + + if self.anchor_vec.device != device: + self.anchor_vec = self.anchor_vec.to(device) + self.anchor_wh = self.anchor_wh.to(device) + + def forward(self, p, out): + ASFF = False # https://arxiv.org/abs/1911.09516 + if ASFF: + i, n = self.index, self.nl # index in layers, number of layers + p = out[self.layers[i]] + bs, _, ny, nx = p.shape # bs, 255, 13, 13 + if (self.nx, self.ny) != (nx, ny): + self.create_grids((nx, ny), p.device) + + # outputs and weights + # w = F.softmax(p[:, -n:], 1) # normalized weights + w = torch.sigmoid(p[:, -n:]) * (2 / n) # sigmoid weights (faster) + # w = w / w.sum(1).unsqueeze(1) # normalize across layer dimension + + # weighted ASFF sum + p = out[self.layers[i]][:, :-n] * w[:, i:i + 1] + for j in range(n): + if j != i: + p += w[:, j:j + 1] * \ + F.interpolate(out[self.layers[j]][:, :-n], size=[ny, nx], mode='bilinear', align_corners=False) + + elif ONNX_EXPORT: + bs = 1 # batch size + else: + bs, _, ny, nx = p.shape # bs, 255, 13, 13 + if (self.nx, self.ny) != (nx, ny): + self.create_grids((nx, ny), p.device) + + # p.view(bs, 255, 13, 13) -- > (bs, 3, 13, 13, 85) # (bs, anchors, grid, grid, classes + xywh) + p = p.view(bs, self.na, self.no, self.ny, self.nx).permute(0, 1, 3, 4, 2).contiguous() # prediction + + if self.training: + return p + + elif ONNX_EXPORT: + # Avoid broadcasting for ANE operations + m = self.na * self.nx * self.ny + ng = 1. / self.ng.repeat(m, 1) + grid = self.grid.repeat(1, self.na, 1, 1, 1).view(m, 2) + anchor_wh = self.anchor_wh.repeat(1, 1, self.nx, self.ny, 1).view(m, 2) * ng + + p = p.view(m, self.no) + xy = torch.sigmoid(p[:, 0:2]) + grid # x, y + wh = torch.exp(p[:, 2:4]) * anchor_wh # width, height + p_cls = torch.sigmoid(p[:, 4:5]) if self.nc == 1 else \ + torch.sigmoid(p[:, 5:self.no]) * torch.sigmoid(p[:, 4:5]) # conf + return p_cls, xy * ng, wh + + else: # inference + io = p.sigmoid() + io[..., :2] = (io[..., :2] * 2. - 0.5 + self.grid) + io[..., 2:4] = (io[..., 2:4] * 2) ** 2 * self.anchor_wh + io[..., :4] *= self.stride + #io = p.clone() # inference output + #io[..., :2] = torch.sigmoid(io[..., :2]) + self.grid # xy + #io[..., 2:4] = torch.exp(io[..., 2:4]) * self.anchor_wh # wh yolo method + #io[..., :4] *= self.stride + #torch.sigmoid_(io[..., 4:]) + return io.view(bs, -1, self.no), p # view [1, 3, 13, 13, 85] as [1, 507, 85] + + +class JDELayer(nn.Module): + def __init__(self, anchors, nc, img_size, yolo_index, layers, stride): + super(JDELayer, self).__init__() + self.anchors = torch.Tensor(anchors) + self.index = yolo_index # index of this layer in layers + self.layers = layers # model output layer indices + self.stride = stride # layer stride + self.nl = len(layers) # number of output layers (3) + self.na = len(anchors) # number of anchors (3) + self.nc = nc # number of classes (80) + self.no = nc + 5 # number of outputs (85) + self.nx, self.ny, self.ng = 0, 0, 0 # initialize number of x, y gridpoints + self.anchor_vec = self.anchors / self.stride + self.anchor_wh = self.anchor_vec.view(1, self.na, 1, 1, 2) + + if ONNX_EXPORT: + self.training = False + self.create_grids((img_size[1] // stride, img_size[0] // stride)) # number x, y grid points + + def create_grids(self, ng=(13, 13), device='cpu'): + self.nx, self.ny = ng # x and y grid size + self.ng = torch.tensor(ng, dtype=torch.float) + + # build xy offsets + if not self.training: + yv, xv = torch.meshgrid([torch.arange(self.ny, device=device), torch.arange(self.nx, device=device)]) + self.grid = torch.stack((xv, yv), 2).view((1, 1, self.ny, self.nx, 2)).float() + + if self.anchor_vec.device != device: + self.anchor_vec = self.anchor_vec.to(device) + self.anchor_wh = self.anchor_wh.to(device) + + def forward(self, p, out): + ASFF = False # https://arxiv.org/abs/1911.09516 + if ASFF: + i, n = self.index, self.nl # index in layers, number of layers + p = out[self.layers[i]] + bs, _, ny, nx = p.shape # bs, 255, 13, 13 + if (self.nx, self.ny) != (nx, ny): + self.create_grids((nx, ny), p.device) + + # outputs and weights + # w = F.softmax(p[:, -n:], 1) # normalized weights + w = torch.sigmoid(p[:, -n:]) * (2 / n) # sigmoid weights (faster) + # w = w / w.sum(1).unsqueeze(1) # normalize across layer dimension + + # weighted ASFF sum + p = out[self.layers[i]][:, :-n] * w[:, i:i + 1] + for j in range(n): + if j != i: + p += w[:, j:j + 1] * \ + F.interpolate(out[self.layers[j]][:, :-n], size=[ny, nx], mode='bilinear', align_corners=False) + + elif ONNX_EXPORT: + bs = 1 # batch size + else: + bs, _, ny, nx = p.shape # bs, 255, 13, 13 + if (self.nx, self.ny) != (nx, ny): + self.create_grids((nx, ny), p.device) + + # p.view(bs, 255, 13, 13) -- > (bs, 3, 13, 13, 85) # (bs, anchors, grid, grid, classes + xywh) + p = p.view(bs, self.na, self.no, self.ny, self.nx).permute(0, 1, 3, 4, 2).contiguous() # prediction + + if self.training: + return p + + elif ONNX_EXPORT: + # Avoid broadcasting for ANE operations + m = self.na * self.nx * self.ny + ng = 1. / self.ng.repeat(m, 1) + grid = self.grid.repeat(1, self.na, 1, 1, 1).view(m, 2) + anchor_wh = self.anchor_wh.repeat(1, 1, self.nx, self.ny, 1).view(m, 2) * ng + + p = p.view(m, self.no) + xy = torch.sigmoid(p[:, 0:2]) + grid # x, y + wh = torch.exp(p[:, 2:4]) * anchor_wh # width, height + p_cls = torch.sigmoid(p[:, 4:5]) if self.nc == 1 else \ + torch.sigmoid(p[:, 5:self.no]) * torch.sigmoid(p[:, 4:5]) # conf + return p_cls, xy * ng, wh + + else: # inference + #io = p.sigmoid() + #io[..., :2] = (io[..., :2] * 2. - 0.5 + self.grid) + #io[..., 2:4] = (io[..., 2:4] * 2) ** 2 * self.anchor_wh + #io[..., :4] *= self.stride + io = p.clone() # inference output + io[..., :2] = torch.sigmoid(io[..., :2]) * 2. - 0.5 + self.grid # xy + io[..., 2:4] = (torch.sigmoid(io[..., 2:4]) * 2) ** 2 * self.anchor_wh # wh yolo method + io[..., :4] *= self.stride + io[..., 4:] = F.softmax(io[..., 4:]) + return io.view(bs, -1, self.no), p # view [1, 3, 13, 13, 85] as [1, 507, 85] + +class Darknet(nn.Module): + # YOLOv3 object detection model + + def __init__(self, cfg, img_size=(416, 416), verbose=False): + super(Darknet, self).__init__() + + self.module_defs = parse_model_cfg(cfg) + self.module_list, self.routs = create_modules(self.module_defs, img_size, cfg) + self.yolo_layers = get_yolo_layers(self) + # torch_utils.initialize_weights(self) + + # Darknet Header https://github.com/AlexeyAB/darknet/issues/2914#issuecomment-496675346 + self.version = np.array([0, 2, 5], dtype=np.int32) # (int32) version info: major, minor, revision + self.seen = np.array([0], dtype=np.int64) # (int64) number of images seen during training + self.info(verbose) if not ONNX_EXPORT else None # print model description + + def forward(self, x, augment=False, verbose=False): + + if not augment: + return self.forward_once(x) + else: # Augment images (inference and test only) https://github.com/ultralytics/yolov3/issues/931 + img_size = x.shape[-2:] # height, width + s = [0.83, 0.67] # scales + y = [] + for i, xi in enumerate((x, + torch_utils.scale_img(x.flip(3), s[0], same_shape=False), # flip-lr and scale + torch_utils.scale_img(x, s[1], same_shape=False), # scale + )): + # cv2.imwrite('img%g.jpg' % i, 255 * xi[0].numpy().transpose((1, 2, 0))[:, :, ::-1]) + y.append(self.forward_once(xi)[0]) + + y[1][..., :4] /= s[0] # scale + y[1][..., 0] = img_size[1] - y[1][..., 0] # flip lr + y[2][..., :4] /= s[1] # scale + + # for i, yi in enumerate(y): # coco small, medium, large = < 32**2 < 96**2 < + # area = yi[..., 2:4].prod(2)[:, :, None] + # if i == 1: + # yi *= (area < 96. ** 2).float() + # elif i == 2: + # yi *= (area > 32. ** 2).float() + # y[i] = yi + + y = torch.cat(y, 1) + return y, None + + def forward_once(self, x, augment=False, verbose=False): + img_size = x.shape[-2:] # height, width + yolo_out, out = [], [] + if verbose: + print('0', x.shape) + str = '' + + # Augment images (inference and test only) + if augment: # https://github.com/ultralytics/yolov3/issues/931 + nb = x.shape[0] # batch size + s = [0.83, 0.67] # scales + x = torch.cat((x, + torch_utils.scale_img(x.flip(3), s[0]), # flip-lr and scale + torch_utils.scale_img(x, s[1]), # scale + ), 0) + + for i, module in enumerate(self.module_list): + name = module.__class__.__name__ + #print(name) + if name in ['WeightedFeatureFusion', 'FeatureConcat', 'FeatureConcat2', 'FeatureConcat3', 'FeatureConcat_l', 'ScaleChannel', 'ShiftChannel', 'ShiftChannel2D', 'ControlChannel', 'ControlChannel2D', 'AlternateChannel', 'AlternateChannel2D', 'SelectChannel', 'SelectChannel2D', 'ScaleSpatial']: # sum, concat + if verbose: + l = [i - 1] + module.layers # layers + sh = [list(x.shape)] + [list(out[i].shape) for i in module.layers] # shapes + str = ' >> ' + ' + '.join(['layer %g %s' % x for x in zip(l, sh)]) + x = module(x, out) # WeightedFeatureFusion(), FeatureConcat() + elif name in ['ImplicitA', 'ImplicitM', 'ImplicitC', 'Implicit2DA', 'Implicit2DM', 'Implicit2DC']: + x = module() + elif name == 'YOLOLayer': + yolo_out.append(module(x, out)) + elif name == 'JDELayer': + yolo_out.append(module(x, out)) + else: # run module directly, i.e. mtype = 'convolutional', 'upsample', 'maxpool', 'batchnorm2d' etc. + #print(module) + #print(x.shape) + x = module(x) + + out.append(x if self.routs[i] else []) + if verbose: + print('%g/%g %s -' % (i, len(self.module_list), name), list(x.shape), str) + str = '' + + if self.training: # train + return yolo_out + elif ONNX_EXPORT: # export + x = [torch.cat(x, 0) for x in zip(*yolo_out)] + return x[0], torch.cat(x[1:3], 1) # scores, boxes: 3780x80, 3780x4 + else: # inference or test + x, p = zip(*yolo_out) # inference output, training output + x = torch.cat(x, 1) # cat yolo outputs + if augment: # de-augment results + x = torch.split(x, nb, dim=0) + x[1][..., :4] /= s[0] # scale + x[1][..., 0] = img_size[1] - x[1][..., 0] # flip lr + x[2][..., :4] /= s[1] # scale + x = torch.cat(x, 1) + return x, p + + def fuse(self): + # Fuse Conv2d + BatchNorm2d layers throughout model + print('Fusing layers...') + fused_list = nn.ModuleList() + for a in list(self.children())[0]: + if isinstance(a, nn.Sequential): + for i, b in enumerate(a): + if isinstance(b, nn.modules.batchnorm.BatchNorm2d): + # fuse this bn layer with the previous conv2d layer + conv = a[i - 1] + fused = torch_utils.fuse_conv_and_bn(conv, b) + a = nn.Sequential(fused, *list(a.children())[i + 1:]) + break + fused_list.append(a) + self.module_list = fused_list + self.info() if not ONNX_EXPORT else None # yolov3-spp reduced from 225 to 152 layers + + def info(self, verbose=False): + torch_utils.model_info(self, verbose) + + +def get_yolo_layers(model): + return [i for i, m in enumerate(model.module_list) if m.__class__.__name__ in ['YOLOLayer', 'JDELayer']] # [89, 101, 113] + + +def load_darknet_weights(self, weights, cutoff=-1): + # Parses and loads the weights stored in 'weights' + + # Establish cutoffs (load layers between 0 and cutoff. if cutoff = -1 all are loaded) + file = Path(weights).name + if file == 'darknet53.conv.74': + cutoff = 75 + elif file == 'yolov3-tiny.conv.15': + cutoff = 15 + + # Read weights file + with open(weights, 'rb') as f: + # Read Header https://github.com/AlexeyAB/darknet/issues/2914#issuecomment-496675346 + self.version = np.fromfile(f, dtype=np.int32, count=3) # (int32) version info: major, minor, revision + self.seen = np.fromfile(f, dtype=np.int64, count=1) # (int64) number of images seen during training + + weights = np.fromfile(f, dtype=np.float32) # the rest are weights + + ptr = 0 + for i, (mdef, module) in enumerate(zip(self.module_defs[:cutoff], self.module_list[:cutoff])): + if mdef['type'] == 'convolutional': + conv = module[0] + if mdef['batch_normalize']: + # Load BN bias, weights, running mean and running variance + bn = module[1] + nb = bn.bias.numel() # number of biases + # Bias + bn.bias.data.copy_(torch.from_numpy(weights[ptr:ptr + nb]).view_as(bn.bias)) + ptr += nb + # Weight + bn.weight.data.copy_(torch.from_numpy(weights[ptr:ptr + nb]).view_as(bn.weight)) + ptr += nb + # Running Mean + bn.running_mean.data.copy_(torch.from_numpy(weights[ptr:ptr + nb]).view_as(bn.running_mean)) + ptr += nb + # Running Var + bn.running_var.data.copy_(torch.from_numpy(weights[ptr:ptr + nb]).view_as(bn.running_var)) + ptr += nb + else: + # Load conv. bias + nb = conv.bias.numel() + conv_b = torch.from_numpy(weights[ptr:ptr + nb]).view_as(conv.bias) + conv.bias.data.copy_(conv_b) + ptr += nb + # Load conv. weights + nw = conv.weight.numel() # number of weights + conv.weight.data.copy_(torch.from_numpy(weights[ptr:ptr + nw]).view_as(conv.weight)) + ptr += nw + + +def save_weights(self, path='model.weights', cutoff=-1): + # Converts a PyTorch model to Darket format (*.pt to *.weights) + # Note: Does not work if model.fuse() is applied + with open(path, 'wb') as f: + # Write Header https://github.com/AlexeyAB/darknet/issues/2914#issuecomment-496675346 + self.version.tofile(f) # (int32) version info: major, minor, revision + self.seen.tofile(f) # (int64) number of images seen during training + + # Iterate through layers + for i, (mdef, module) in enumerate(zip(self.module_defs[:cutoff], self.module_list[:cutoff])): + if mdef['type'] == 'convolutional': + conv_layer = module[0] + # If batch norm, load bn first + if mdef['batch_normalize']: + bn_layer = module[1] + bn_layer.bias.data.cpu().numpy().tofile(f) + bn_layer.weight.data.cpu().numpy().tofile(f) + bn_layer.running_mean.data.cpu().numpy().tofile(f) + bn_layer.running_var.data.cpu().numpy().tofile(f) + # Load conv bias + else: + conv_layer.bias.data.cpu().numpy().tofile(f) + # Load conv weights + conv_layer.weight.data.cpu().numpy().tofile(f) + + +def convert(cfg='cfg/yolov3-spp.cfg', weights='weights/yolov3-spp.weights', saveto='converted.weights'): + # Converts between PyTorch and Darknet format per extension (i.e. *.weights convert to *.pt and vice versa) + # from models import *; convert('cfg/yolov3-spp.cfg', 'weights/yolov3-spp.weights') + + # Initialize model + model = Darknet(cfg) + ckpt = torch.load(weights) # load checkpoint + try: + ckpt['model'] = {k: v for k, v in ckpt['model'].items() if model.state_dict()[k].numel() == v.numel()} + model.load_state_dict(ckpt['model'], strict=False) + save_weights(model, path=saveto, cutoff=-1) + except KeyError as e: + print(e) + +def attempt_download(weights): + # Attempt to download pretrained weights if not found locally + weights = weights.strip() + msg = weights + ' missing, try downloading from https://drive.google.com/open?id=1LezFG5g3BCW6iYaV89B2i64cqEUZD7e0' + + if len(weights) > 0 and not os.path.isfile(weights): + d = {''} + + file = Path(weights).name + if file in d: + r = gdrive_download(id=d[file], name=weights) + else: # download from pjreddie.com + url = 'https://pjreddie.com/media/files/' + file + print('Downloading ' + url) + r = os.system('curl -f ' + url + ' -o ' + weights) + + # Error check + if not (r == 0 and os.path.exists(weights) and os.path.getsize(weights) > 1E6): # weights exist and > 1MB + os.system('rm ' + weights) # remove partial downloads + raise Exception(msg) diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..03354e3ee00eff51d032bfaa7931969078b08478 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,19 @@ +pycocotools +click +easydict +gdown +lap +matplotlib +onnxruntime-gpu +opencv-python +Pillow +PyYAML +scipy +streamlit +tensorboard +--extra-index-url https://download.pytorch.org/whl/cu113 +torch +torchaudio +torchvision +tqdm +zipp diff --git a/results.mp4 b/results.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d8c749d26df7034ef482451f1807c8a0f69ae99a --- /dev/null +++ b/results.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e831821f207b2cfc9396caff368fb264844e32f8f4eedcbeccb849d6a6dd7d6 +size 5441497 diff --git a/src/cython-bbox/.gitignore b/src/cython-bbox/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..894a44cc066a027465cd26d634948d56d13af9af --- /dev/null +++ b/src/cython-bbox/.gitignore @@ -0,0 +1,104 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +.hypothesis/ +.pytest_cache/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# pyenv +.python-version + +# celery beat schedule file +celerybeat-schedule + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ diff --git a/src/cython-bbox/LICENSE b/src/cython-bbox/LICENSE new file mode 100644 index 0000000000000000000000000000000000000000..4ccfe536a492c2e6dbeb9b7955d95f9cea07fd81 --- /dev/null +++ b/src/cython-bbox/LICENSE @@ -0,0 +1,103 @@ +Faster R-CNN + +The MIT License (MIT) + +Copyright (c) 2015 Microsoft Corporation + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in +all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN +THE SOFTWARE. + +************************************************************************ + +THIRD-PARTY SOFTWARE NOTICES AND INFORMATION + +This project, Faster R-CNN, incorporates material from the project(s) +listed below (collectively, "Third Party Code"). Microsoft is not the +original author of the Third Party Code. The original copyright notice +and license under which Microsoft received such Third Party Code are set +out below. This Third Party Code is licensed to you under their original +license terms set forth below. Microsoft reserves all other rights not +expressly granted, whether by implication, estoppel or otherwise. + +1. Caffe, (https://github.com/BVLC/caffe/) + +COPYRIGHT + +All contributions by the University of California: +Copyright (c) 2014, 2015, The Regents of the University of California (Regents) +All rights reserved. + +All other contributions: +Copyright (c) 2014, 2015, the respective contributors +All rights reserved. + +Caffe uses a shared copyright model: each contributor holds copyright +over their contributions to Caffe. The project versioning records all +such contribution and copyright details. If a contributor wants to +further mark their specific copyright on a particular contribution, +they should indicate their copyright solely in the commit message of +the change when it is committed. + +The BSD 2-Clause License + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions +are met: + +1. Redistributions of source code must retain the above copyright notice, +this list of conditions and the following disclaimer. + +2. Redistributions in binary form must reproduce the above copyright +notice, this list of conditions and the following disclaimer in the +documentation and/or other materials provided with the distribution. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED +TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +************END OF THIRD-PARTY SOFTWARE NOTICES AND INFORMATION********** + +MIT License + +Copyright (c) 2018 WANG Chenxi + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/src/cython-bbox/MANIFEST.in b/src/cython-bbox/MANIFEST.in new file mode 100644 index 0000000000000000000000000000000000000000..ac4672546aa5941a312d9b62a4174197c76c20e9 --- /dev/null +++ b/src/cython-bbox/MANIFEST.in @@ -0,0 +1,2 @@ +include src/*.pyx +include README.md diff --git a/src/cython-bbox/README.md b/src/cython-bbox/README.md new file mode 100644 index 0000000000000000000000000000000000000000..5bc95c22a028c9f53830c624013b3b5ba1bf25fe --- /dev/null +++ b/src/cython-bbox/README.md @@ -0,0 +1,23 @@ +# cython_bbox + +cython_bbox is widely used in object detection tasks. To my best knowledge, it was first implemented in [Faster-RCNN](https://github.com/rbgirshick/py-faster-rcnn). Since then, almost all object detection projects use the source code directly. + +In order to use it in standalone code snippets or small projects, I make it a pypi module. The `cython_bbox.pyx` is totally borrowed from [Faster-RCNN](https://github.com/rbgirshick/py-faster-rcnn). Thanks [RBG](http://www.rossgirshick.info/)! + +## install + +``` +pip install cython_bbox +``` + +## usage + + +``` +from cython_bbox import bbox_overlaps +overlaps = bbox_overlaps( + np.ascontiguousarray(dt, dtype=np.float32), + np.ascontiguousarray(gt, dtype=np.float32) + ) + +``` diff --git a/src/cython-bbox/build/lib.win-amd64-3.9/cython_bbox.cp39-win_amd64.pyd b/src/cython-bbox/build/lib.win-amd64-3.9/cython_bbox.cp39-win_amd64.pyd new file mode 100644 index 0000000000000000000000000000000000000000..88e733376a5f17a501f19d1d7a37986d5bfee119 Binary files /dev/null and b/src/cython-bbox/build/lib.win-amd64-3.9/cython_bbox.cp39-win_amd64.pyd differ diff --git a/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.cp39-win_amd64.exp b/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.cp39-win_amd64.exp new file mode 100644 index 0000000000000000000000000000000000000000..752fca780afdc808ba8de9e27018003ab3e841b1 Binary files /dev/null and b/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.cp39-win_amd64.exp differ diff --git a/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.cp39-win_amd64.lib b/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.cp39-win_amd64.lib new file mode 100644 index 0000000000000000000000000000000000000000..6355ef7cf37912d8a2b2e548da576780f06d8f6b Binary files /dev/null and b/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.cp39-win_amd64.lib differ diff --git a/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.obj b/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.obj new file mode 100644 index 0000000000000000000000000000000000000000..4fb6490bc23bd7370190ac1449eec42b2ed06b8f Binary files /dev/null and b/src/cython-bbox/build/temp.win-amd64-3.9/Release/src/cython_bbox.obj differ diff --git a/src/cython-bbox/cython_bbox.cp39-win_amd64.pyd b/src/cython-bbox/cython_bbox.cp39-win_amd64.pyd new file mode 100644 index 0000000000000000000000000000000000000000..88e733376a5f17a501f19d1d7a37986d5bfee119 Binary files /dev/null and b/src/cython-bbox/cython_bbox.cp39-win_amd64.pyd differ diff --git a/src/cython-bbox/cython_bbox.egg-info/PKG-INFO b/src/cython-bbox/cython_bbox.egg-info/PKG-INFO new file mode 100644 index 0000000000000000000000000000000000000000..2e0749ae34d4066d28ea8c6f6ab10e949ecbd4bd --- /dev/null +++ b/src/cython-bbox/cython_bbox.egg-info/PKG-INFO @@ -0,0 +1,38 @@ +Metadata-Version: 2.1 +Name: cython-bbox +Version: 0.1.3 +Summary: Standalone cython_bbox +Home-page: https://github.com/samson-wang/cython_bbox.git +Author: Samson Wang +Author-email: samson.c.wang@gmail.com +License: UNKNOWN +Keywords: cython_bbox +Platform: UNKNOWN +Description-Content-Type: text/markdown +License-File: LICENSE + +# cython_bbox + +cython_bbox is widely used in object detection tasks. To my best knowledge, it was first implemented in [Faster-RCNN](https://github.com/rbgirshick/py-faster-rcnn). Since then, almost all object detection projects use the source code directly. + +In order to use it in standalone code snippets or small projects, I make it a pypi module. The `cython_bbox.pyx` is totally borrowed from [Faster-RCNN](https://github.com/rbgirshick/py-faster-rcnn). Thanks [RBG](http://www.rossgirshick.info/)! + +## install + +``` +pip install cython_bbox +``` + +## usage + + +``` +from cython_bbox import bbox_overlaps +overlaps = bbox_overlaps( + np.ascontiguousarray(dt, dtype=np.float32), + np.ascontiguousarray(gt, dtype=np.float32) + ) + +``` + + diff --git a/src/cython-bbox/cython_bbox.egg-info/SOURCES.txt b/src/cython-bbox/cython_bbox.egg-info/SOURCES.txt new file mode 100644 index 0000000000000000000000000000000000000000..159d9efea0f745de292372129ed43256a5b635ff --- /dev/null +++ b/src/cython-bbox/cython_bbox.egg-info/SOURCES.txt @@ -0,0 +1,10 @@ +LICENSE +MANIFEST.in +README.md +setup.py +cython_bbox.egg-info/PKG-INFO +cython_bbox.egg-info/SOURCES.txt +cython_bbox.egg-info/dependency_links.txt +cython_bbox.egg-info/requires.txt +cython_bbox.egg-info/top_level.txt +src/cython_bbox.pyx \ No newline at end of file diff --git a/src/cython-bbox/cython_bbox.egg-info/dependency_links.txt b/src/cython-bbox/cython_bbox.egg-info/dependency_links.txt new file mode 100644 index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc --- /dev/null +++ b/src/cython-bbox/cython_bbox.egg-info/dependency_links.txt @@ -0,0 +1 @@ + diff --git a/src/cython-bbox/cython_bbox.egg-info/requires.txt b/src/cython-bbox/cython_bbox.egg-info/requires.txt new file mode 100644 index 0000000000000000000000000000000000000000..29726b00a6ad5accbb71c0ac4ab9491bcf07d2f6 --- /dev/null +++ b/src/cython-bbox/cython_bbox.egg-info/requires.txt @@ -0,0 +1,2 @@ +Cython +numpy diff --git a/src/cython-bbox/cython_bbox.egg-info/top_level.txt b/src/cython-bbox/cython_bbox.egg-info/top_level.txt new file mode 100644 index 0000000000000000000000000000000000000000..900222a67197c51f77793399a69f8bebf8ee0c22 --- /dev/null +++ b/src/cython-bbox/cython_bbox.egg-info/top_level.txt @@ -0,0 +1 @@ +cython_bbox diff --git a/src/cython-bbox/setup.py b/src/cython-bbox/setup.py new file mode 100644 index 0000000000000000000000000000000000000000..ab19ea98546707fff1cbd127b28515025601cd71 --- /dev/null +++ b/src/cython-bbox/setup.py @@ -0,0 +1,60 @@ +# -------------------------------------------------------- +# Fast R-CNN +# Copyright (c) 2015 Microsoft +# Licensed under The MIT License [see LICENSE for details] +# Written by Samson Wang +# -------------------------------------------------------- + +from __future__ import print_function + +from setuptools import Extension +from setuptools import setup +from distutils.command.build import build as _build +import os + +# ref from https://stackoverflow.com/questions/54117786/add-numpy-get-include-argument-to-setuptools-without-preinstalled-numpy +class build(_build): + def finalize_options(self): + super().finalize_options() + import builtins + builtins.__NUMPY_SETUP__ = False + import numpy as np + # Obtain the numpy include directory. This logic works across numpy versions. + extension = next(m for m in self.distribution.ext_modules if m.name=='cython_bbox') + try: + extension.include_dirs.append(np.get_include()) + except AttributeError: + extension.include_dirs.append(np.get_numpy_include()) + +with open("README.md", "r") as fh: + long_description = fh.read() + +if os.name == 'nt': + compile_args = {'gcc': ['/Qstd=c99']} +else: + compile_args = ['-Wno-cpp'] + +ext_modules = [ + Extension( + name='cython_bbox', + sources=['src/cython_bbox.pyx'], + extra_compile_args = compile_args, + ) +] + +setup( + name='cython_bbox', + setup_requires=["setuptools>=18.0","Cython","numpy"], + install_requires=["Cython","numpy"], + ext_modules=ext_modules, + cmdclass={'build': build}, + version = '0.1.3', + description = 'Standalone cython_bbox', + long_description=long_description, + long_description_content_type="text/markdown", + author = 'Samson Wang', + author_email = 'samson.c.wang@gmail.com', + url = 'https://github.com/samson-wang/cython_bbox.git', + keywords = ['cython_bbox'] +) + diff --git a/src/cython-bbox/src/cython_bbox.c b/src/cython-bbox/src/cython_bbox.c new file mode 100644 index 0000000000000000000000000000000000000000..5885afd9afed7341f4be2bd9258c38b810b39b73 --- /dev/null +++ b/src/cython-bbox/src/cython_bbox.c @@ -0,0 +1,6962 @@ +/* Generated by Cython 0.29.28 */ + +#ifndef PY_SSIZE_T_CLEAN +#define PY_SSIZE_T_CLEAN +#endif /* PY_SSIZE_T_CLEAN */ +#include "Python.h" +#ifndef Py_PYTHON_H + #error Python headers needed to compile C extensions, please install development version of Python. +#elif PY_VERSION_HEX < 0x02060000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03030000) + #error Cython requires Python 2.6+ or Python 3.3+. +#else +#define CYTHON_ABI "0_29_28" +#define CYTHON_HEX_VERSION 0x001D1CF0 +#define CYTHON_FUTURE_DIVISION 0 +#include +#ifndef offsetof + #define offsetof(type, member) ( (size_t) & ((type*)0) -> member ) +#endif +#if !defined(WIN32) && !defined(MS_WINDOWS) + #ifndef __stdcall + #define __stdcall + #endif + #ifndef __cdecl + #define __cdecl + #endif + #ifndef __fastcall + #define __fastcall + #endif +#endif +#ifndef DL_IMPORT + #define DL_IMPORT(t) t +#endif +#ifndef DL_EXPORT + #define DL_EXPORT(t) t +#endif +#define __PYX_COMMA , +#ifndef HAVE_LONG_LONG + #if PY_VERSION_HEX >= 0x02070000 + #define HAVE_LONG_LONG + #endif +#endif +#ifndef PY_LONG_LONG + #define PY_LONG_LONG LONG_LONG +#endif +#ifndef Py_HUGE_VAL + #define Py_HUGE_VAL HUGE_VAL +#endif +#ifdef PYPY_VERSION + #define CYTHON_COMPILING_IN_PYPY 1 + #define CYTHON_COMPILING_IN_PYSTON 0 + #define CYTHON_COMPILING_IN_CPYTHON 0 + #undef CYTHON_USE_TYPE_SLOTS + #define CYTHON_USE_TYPE_SLOTS 0 + #undef CYTHON_USE_PYTYPE_LOOKUP + #define CYTHON_USE_PYTYPE_LOOKUP 0 + #if PY_VERSION_HEX < 0x03050000 + #undef CYTHON_USE_ASYNC_SLOTS + #define CYTHON_USE_ASYNC_SLOTS 0 + #elif !defined(CYTHON_USE_ASYNC_SLOTS) + #define CYTHON_USE_ASYNC_SLOTS 1 + #endif + #undef CYTHON_USE_PYLIST_INTERNALS + #define CYTHON_USE_PYLIST_INTERNALS 0 + #undef CYTHON_USE_UNICODE_INTERNALS + #define CYTHON_USE_UNICODE_INTERNALS 0 + #undef CYTHON_USE_UNICODE_WRITER + #define CYTHON_USE_UNICODE_WRITER 0 + #undef CYTHON_USE_PYLONG_INTERNALS + #define CYTHON_USE_PYLONG_INTERNALS 0 + #undef CYTHON_AVOID_BORROWED_REFS + #define CYTHON_AVOID_BORROWED_REFS 1 + #undef CYTHON_ASSUME_SAFE_MACROS + #define CYTHON_ASSUME_SAFE_MACROS 0 + #undef CYTHON_UNPACK_METHODS + #define CYTHON_UNPACK_METHODS 0 + #undef CYTHON_FAST_THREAD_STATE + #define CYTHON_FAST_THREAD_STATE 0 + #undef CYTHON_FAST_PYCALL + #define CYTHON_FAST_PYCALL 0 + #undef CYTHON_PEP489_MULTI_PHASE_INIT + #define CYTHON_PEP489_MULTI_PHASE_INIT 0 + #undef CYTHON_USE_TP_FINALIZE + #define CYTHON_USE_TP_FINALIZE 0 + #undef CYTHON_USE_DICT_VERSIONS + #define CYTHON_USE_DICT_VERSIONS 0 + #undef CYTHON_USE_EXC_INFO_STACK + #define CYTHON_USE_EXC_INFO_STACK 0 +#elif defined(PYSTON_VERSION) + #define CYTHON_COMPILING_IN_PYPY 0 + #define CYTHON_COMPILING_IN_PYSTON 1 + #define CYTHON_COMPILING_IN_CPYTHON 0 + #ifndef CYTHON_USE_TYPE_SLOTS + #define CYTHON_USE_TYPE_SLOTS 1 + #endif + #undef CYTHON_USE_PYTYPE_LOOKUP + #define CYTHON_USE_PYTYPE_LOOKUP 0 + #undef CYTHON_USE_ASYNC_SLOTS + #define CYTHON_USE_ASYNC_SLOTS 0 + #undef CYTHON_USE_PYLIST_INTERNALS + #define CYTHON_USE_PYLIST_INTERNALS 0 + #ifndef CYTHON_USE_UNICODE_INTERNALS + #define CYTHON_USE_UNICODE_INTERNALS 1 + #endif + #undef CYTHON_USE_UNICODE_WRITER + #define CYTHON_USE_UNICODE_WRITER 0 + #undef CYTHON_USE_PYLONG_INTERNALS + #define CYTHON_USE_PYLONG_INTERNALS 0 + #ifndef CYTHON_AVOID_BORROWED_REFS + #define CYTHON_AVOID_BORROWED_REFS 0 + #endif + #ifndef CYTHON_ASSUME_SAFE_MACROS + #define CYTHON_ASSUME_SAFE_MACROS 1 + #endif + #ifndef CYTHON_UNPACK_METHODS + #define CYTHON_UNPACK_METHODS 1 + #endif + #undef CYTHON_FAST_THREAD_STATE + #define CYTHON_FAST_THREAD_STATE 0 + #undef CYTHON_FAST_PYCALL + #define CYTHON_FAST_PYCALL 0 + #undef CYTHON_PEP489_MULTI_PHASE_INIT + #define CYTHON_PEP489_MULTI_PHASE_INIT 0 + #undef CYTHON_USE_TP_FINALIZE + #define CYTHON_USE_TP_FINALIZE 0 + #undef CYTHON_USE_DICT_VERSIONS + #define CYTHON_USE_DICT_VERSIONS 0 + #undef CYTHON_USE_EXC_INFO_STACK + #define CYTHON_USE_EXC_INFO_STACK 0 +#else + #define CYTHON_COMPILING_IN_PYPY 0 + #define CYTHON_COMPILING_IN_PYSTON 0 + #define CYTHON_COMPILING_IN_CPYTHON 1 + #ifndef CYTHON_USE_TYPE_SLOTS + #define CYTHON_USE_TYPE_SLOTS 1 + #endif + #if PY_VERSION_HEX < 0x02070000 + #undef CYTHON_USE_PYTYPE_LOOKUP + #define CYTHON_USE_PYTYPE_LOOKUP 0 + #elif !defined(CYTHON_USE_PYTYPE_LOOKUP) + #define CYTHON_USE_PYTYPE_LOOKUP 1 + #endif + #if PY_MAJOR_VERSION < 3 + #undef CYTHON_USE_ASYNC_SLOTS + #define CYTHON_USE_ASYNC_SLOTS 0 + #elif !defined(CYTHON_USE_ASYNC_SLOTS) + #define CYTHON_USE_ASYNC_SLOTS 1 + #endif + #if PY_VERSION_HEX < 0x02070000 + #undef CYTHON_USE_PYLONG_INTERNALS + #define CYTHON_USE_PYLONG_INTERNALS 0 + #elif !defined(CYTHON_USE_PYLONG_INTERNALS) + #define CYTHON_USE_PYLONG_INTERNALS 1 + #endif + #ifndef CYTHON_USE_PYLIST_INTERNALS + #define CYTHON_USE_PYLIST_INTERNALS 1 + #endif + #ifndef CYTHON_USE_UNICODE_INTERNALS + #define CYTHON_USE_UNICODE_INTERNALS 1 + #endif + #if PY_VERSION_HEX < 0x030300F0 || PY_VERSION_HEX >= 0x030B00A2 + #undef CYTHON_USE_UNICODE_WRITER + #define CYTHON_USE_UNICODE_WRITER 0 + #elif !defined(CYTHON_USE_UNICODE_WRITER) + #define CYTHON_USE_UNICODE_WRITER 1 + #endif + #ifndef CYTHON_AVOID_BORROWED_REFS + #define CYTHON_AVOID_BORROWED_REFS 0 + #endif + #ifndef CYTHON_ASSUME_SAFE_MACROS + #define CYTHON_ASSUME_SAFE_MACROS 1 + #endif + #ifndef CYTHON_UNPACK_METHODS + #define CYTHON_UNPACK_METHODS 1 + #endif + #if PY_VERSION_HEX >= 0x030B00A4 + #undef CYTHON_FAST_THREAD_STATE + #define CYTHON_FAST_THREAD_STATE 0 + #elif !defined(CYTHON_FAST_THREAD_STATE) + #define CYTHON_FAST_THREAD_STATE 1 + #endif + #ifndef CYTHON_FAST_PYCALL + #define CYTHON_FAST_PYCALL (PY_VERSION_HEX < 0x030B00A1) + #endif + #ifndef CYTHON_PEP489_MULTI_PHASE_INIT + #define CYTHON_PEP489_MULTI_PHASE_INIT (PY_VERSION_HEX >= 0x03050000) + #endif + #ifndef CYTHON_USE_TP_FINALIZE + #define CYTHON_USE_TP_FINALIZE (PY_VERSION_HEX >= 0x030400a1) + #endif + #ifndef CYTHON_USE_DICT_VERSIONS + #define CYTHON_USE_DICT_VERSIONS (PY_VERSION_HEX >= 0x030600B1) + #endif + #if PY_VERSION_HEX >= 0x030B00A4 + #undef CYTHON_USE_EXC_INFO_STACK + #define CYTHON_USE_EXC_INFO_STACK 0 + #elif !defined(CYTHON_USE_EXC_INFO_STACK) + #define CYTHON_USE_EXC_INFO_STACK (PY_VERSION_HEX >= 0x030700A3) + #endif +#endif +#if !defined(CYTHON_FAST_PYCCALL) +#define CYTHON_FAST_PYCCALL (CYTHON_FAST_PYCALL && PY_VERSION_HEX >= 0x030600B1) +#endif +#if CYTHON_USE_PYLONG_INTERNALS + #if PY_MAJOR_VERSION < 3 + #include "longintrepr.h" + #endif + #undef SHIFT + #undef BASE + #undef MASK + #ifdef SIZEOF_VOID_P + enum { __pyx_check_sizeof_voidp = 1 / (int)(SIZEOF_VOID_P == sizeof(void*)) }; + #endif +#endif +#ifndef __has_attribute + #define __has_attribute(x) 0 +#endif +#ifndef __has_cpp_attribute + #define __has_cpp_attribute(x) 0 +#endif +#ifndef CYTHON_RESTRICT + #if defined(__GNUC__) + #define CYTHON_RESTRICT __restrict__ + #elif defined(_MSC_VER) && _MSC_VER >= 1400 + #define CYTHON_RESTRICT __restrict + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_RESTRICT restrict + #else + #define CYTHON_RESTRICT + #endif +#endif +#ifndef CYTHON_UNUSED +# if defined(__GNUC__) +# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +#endif +#ifndef CYTHON_MAYBE_UNUSED_VAR +# if defined(__cplusplus) + template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } +# else +# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) +# endif +#endif +#ifndef CYTHON_NCP_UNUSED +# if CYTHON_COMPILING_IN_CPYTHON +# define CYTHON_NCP_UNUSED +# else +# define CYTHON_NCP_UNUSED CYTHON_UNUSED +# endif +#endif +#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) +#ifdef _MSC_VER + #ifndef _MSC_STDINT_H_ + #if _MSC_VER < 1300 + typedef unsigned char uint8_t; + typedef unsigned int uint32_t; + #else + typedef unsigned __int8 uint8_t; + typedef unsigned __int32 uint32_t; + #endif + #endif +#else + #include +#endif +#ifndef CYTHON_FALLTHROUGH + #if defined(__cplusplus) && __cplusplus >= 201103L + #if __has_cpp_attribute(fallthrough) + #define CYTHON_FALLTHROUGH [[fallthrough]] + #elif __has_cpp_attribute(clang::fallthrough) + #define CYTHON_FALLTHROUGH [[clang::fallthrough]] + #elif __has_cpp_attribute(gnu::fallthrough) + #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] + #endif + #endif + #ifndef CYTHON_FALLTHROUGH + #if __has_attribute(fallthrough) + #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) + #else + #define CYTHON_FALLTHROUGH + #endif + #endif + #if defined(__clang__ ) && defined(__apple_build_version__) + #if __apple_build_version__ < 7000000 + #undef CYTHON_FALLTHROUGH + #define CYTHON_FALLTHROUGH + #endif + #endif +#endif + +#ifndef CYTHON_INLINE + #if defined(__clang__) + #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) + #elif defined(__GNUC__) + #define CYTHON_INLINE __inline__ + #elif defined(_MSC_VER) + #define CYTHON_INLINE __inline + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_INLINE inline + #else + #define CYTHON_INLINE + #endif +#endif + +#if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX < 0x02070600 && !defined(Py_OptimizeFlag) + #define Py_OptimizeFlag 0 +#endif +#define __PYX_BUILD_PY_SSIZE_T "n" +#define CYTHON_FORMAT_SSIZE_T "z" +#if PY_MAJOR_VERSION < 3 + #define __Pyx_BUILTIN_MODULE_NAME "__builtin__" + #define __Pyx_PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)\ + PyCode_New(a+k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos) + #define __Pyx_DefaultClassType PyClass_Type +#else + #define __Pyx_BUILTIN_MODULE_NAME "builtins" + #define __Pyx_DefaultClassType PyType_Type +#if PY_VERSION_HEX >= 0x030B00A1 + static CYTHON_INLINE PyCodeObject* __Pyx_PyCode_New(int a, int k, int l, int s, int f, + PyObject *code, PyObject *c, PyObject* n, PyObject *v, + PyObject *fv, PyObject *cell, PyObject* fn, + PyObject *name, int fline, PyObject *lnos) { + PyObject *kwds=NULL, *argcount=NULL, *posonlyargcount=NULL, *kwonlyargcount=NULL; + PyObject *nlocals=NULL, *stacksize=NULL, *flags=NULL, *replace=NULL, *call_result=NULL, *empty=NULL; + const char *fn_cstr=NULL; + const char *name_cstr=NULL; + PyCodeObject* co=NULL; + PyObject *type, *value, *traceback; + PyErr_Fetch(&type, &value, &traceback); + if (!(kwds=PyDict_New())) goto end; + if (!(argcount=PyLong_FromLong(a))) goto end; + if (PyDict_SetItemString(kwds, "co_argcount", argcount) != 0) goto end; + if (!(posonlyargcount=PyLong_FromLong(0))) goto end; + if (PyDict_SetItemString(kwds, "co_posonlyargcount", posonlyargcount) != 0) goto end; + if (!(kwonlyargcount=PyLong_FromLong(k))) goto end; + if (PyDict_SetItemString(kwds, "co_kwonlyargcount", kwonlyargcount) != 0) goto end; + if (!(nlocals=PyLong_FromLong(l))) goto end; + if (PyDict_SetItemString(kwds, "co_nlocals", nlocals) != 0) goto end; + if (!(stacksize=PyLong_FromLong(s))) goto end; + if (PyDict_SetItemString(kwds, "co_stacksize", stacksize) != 0) goto end; + if (!(flags=PyLong_FromLong(f))) goto end; + if (PyDict_SetItemString(kwds, "co_flags", flags) != 0) goto end; + if (PyDict_SetItemString(kwds, "co_code", code) != 0) goto end; + if (PyDict_SetItemString(kwds, "co_consts", c) != 0) goto end; + if (PyDict_SetItemString(kwds, "co_names", n) != 0) goto end; + if (PyDict_SetItemString(kwds, "co_varnames", v) != 0) goto end; + if (PyDict_SetItemString(kwds, "co_freevars", fv) != 0) goto end; + if (PyDict_SetItemString(kwds, "co_cellvars", cell) != 0) goto end; + if (PyDict_SetItemString(kwds, "co_linetable", lnos) != 0) goto end; + if (!(fn_cstr=PyUnicode_AsUTF8AndSize(fn, NULL))) goto end; + if (!(name_cstr=PyUnicode_AsUTF8AndSize(name, NULL))) goto end; + if (!(co = PyCode_NewEmpty(fn_cstr, name_cstr, fline))) goto end; + if (!(replace = PyObject_GetAttrString((PyObject*)co, "replace"))) goto cleanup_code_too; + if (!(empty = PyTuple_New(0))) goto cleanup_code_too; // unfortunately __pyx_empty_tuple isn't available here + if (!(call_result = PyObject_Call(replace, empty, kwds))) goto cleanup_code_too; + Py_XDECREF((PyObject*)co); + co = (PyCodeObject*)call_result; + call_result = NULL; + if (0) { + cleanup_code_too: + Py_XDECREF((PyObject*)co); + co = NULL; + } + end: + Py_XDECREF(kwds); + Py_XDECREF(argcount); + Py_XDECREF(posonlyargcount); + Py_XDECREF(kwonlyargcount); + Py_XDECREF(nlocals); + Py_XDECREF(stacksize); + Py_XDECREF(replace); + Py_XDECREF(call_result); + Py_XDECREF(empty); + if (type) { + PyErr_Restore(type, value, traceback); + } + return co; + } +#else + #define __Pyx_PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)\ + PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos) +#endif + #define __Pyx_DefaultClassType PyType_Type +#endif +#ifndef Py_TPFLAGS_CHECKTYPES + #define Py_TPFLAGS_CHECKTYPES 0 +#endif +#ifndef Py_TPFLAGS_HAVE_INDEX + #define Py_TPFLAGS_HAVE_INDEX 0 +#endif +#ifndef Py_TPFLAGS_HAVE_NEWBUFFER + #define Py_TPFLAGS_HAVE_NEWBUFFER 0 +#endif +#ifndef Py_TPFLAGS_HAVE_FINALIZE + #define Py_TPFLAGS_HAVE_FINALIZE 0 +#endif +#ifndef METH_STACKLESS + #define METH_STACKLESS 0 +#endif +#if PY_VERSION_HEX <= 0x030700A3 || !defined(METH_FASTCALL) + #ifndef METH_FASTCALL + #define METH_FASTCALL 0x80 + #endif + typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject *const *args, Py_ssize_t nargs); + typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject *const *args, + Py_ssize_t nargs, PyObject *kwnames); +#else + #define __Pyx_PyCFunctionFast _PyCFunctionFast + #define __Pyx_PyCFunctionFastWithKeywords _PyCFunctionFastWithKeywords +#endif +#if CYTHON_FAST_PYCCALL +#define __Pyx_PyFastCFunction_Check(func)\ + ((PyCFunction_Check(func) && (METH_FASTCALL == (PyCFunction_GET_FLAGS(func) & ~(METH_CLASS | METH_STATIC | METH_COEXIST | METH_KEYWORDS | METH_STACKLESS))))) +#else +#define __Pyx_PyFastCFunction_Check(func) 0 +#endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) + #define PyObject_Malloc(s) PyMem_Malloc(s) + #define PyObject_Free(p) PyMem_Free(p) + #define PyObject_Realloc(p) PyMem_Realloc(p) +#endif +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX < 0x030400A1 + #define PyMem_RawMalloc(n) PyMem_Malloc(n) + #define PyMem_RawRealloc(p, n) PyMem_Realloc(p, n) + #define PyMem_RawFree(p) PyMem_Free(p) +#endif +#if CYTHON_COMPILING_IN_PYSTON + #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) +#else + #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) +#endif +#if !CYTHON_FAST_THREAD_STATE || PY_VERSION_HEX < 0x02070000 + #define __Pyx_PyThreadState_Current PyThreadState_GET() +#elif PY_VERSION_HEX >= 0x03060000 + #define __Pyx_PyThreadState_Current _PyThreadState_UncheckedGet() +#elif PY_VERSION_HEX >= 0x03000000 + #define __Pyx_PyThreadState_Current PyThreadState_GET() +#else + #define __Pyx_PyThreadState_Current _PyThreadState_Current +#endif +#if PY_VERSION_HEX < 0x030700A2 && !defined(PyThread_tss_create) && !defined(Py_tss_NEEDS_INIT) +#include "pythread.h" +#define Py_tss_NEEDS_INIT 0 +typedef int Py_tss_t; +static CYTHON_INLINE int PyThread_tss_create(Py_tss_t *key) { + *key = PyThread_create_key(); + return 0; +} +static CYTHON_INLINE Py_tss_t * PyThread_tss_alloc(void) { + Py_tss_t *key = (Py_tss_t *)PyObject_Malloc(sizeof(Py_tss_t)); + *key = Py_tss_NEEDS_INIT; + return key; +} +static CYTHON_INLINE void PyThread_tss_free(Py_tss_t *key) { + PyObject_Free(key); +} +static CYTHON_INLINE int PyThread_tss_is_created(Py_tss_t *key) { + return *key != Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE void PyThread_tss_delete(Py_tss_t *key) { + PyThread_delete_key(*key); + *key = Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE int PyThread_tss_set(Py_tss_t *key, void *value) { + return PyThread_set_key_value(*key, value); +} +static CYTHON_INLINE void * PyThread_tss_get(Py_tss_t *key) { + return PyThread_get_key_value(*key); +} +#endif +#if CYTHON_COMPILING_IN_CPYTHON || defined(_PyDict_NewPresized) +#define __Pyx_PyDict_NewPresized(n) ((n <= 8) ? PyDict_New() : _PyDict_NewPresized(n)) +#else +#define __Pyx_PyDict_NewPresized(n) PyDict_New() +#endif +#if PY_MAJOR_VERSION >= 3 || CYTHON_FUTURE_DIVISION + #define __Pyx_PyNumber_Divide(x,y) PyNumber_TrueDivide(x,y) + #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceTrueDivide(x,y) +#else + #define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y) + #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y) +#endif +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 && CYTHON_USE_UNICODE_INTERNALS +#define __Pyx_PyDict_GetItemStr(dict, name) _PyDict_GetItem_KnownHash(dict, name, ((PyASCIIObject *) name)->hash) +#else +#define __Pyx_PyDict_GetItemStr(dict, name) PyDict_GetItem(dict, name) +#endif +#if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND) + #define CYTHON_PEP393_ENABLED 1 + #if defined(PyUnicode_IS_READY) + #define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ?\ + 0 : _PyUnicode_Ready((PyObject *)(op))) + #else + #define __Pyx_PyUnicode_READY(op) (0) + #endif + #define __Pyx_PyUnicode_GET_LENGTH(u) PyUnicode_GET_LENGTH(u) + #define __Pyx_PyUnicode_READ_CHAR(u, i) PyUnicode_READ_CHAR(u, i) + #define __Pyx_PyUnicode_MAX_CHAR_VALUE(u) PyUnicode_MAX_CHAR_VALUE(u) + #define __Pyx_PyUnicode_KIND(u) PyUnicode_KIND(u) + #define __Pyx_PyUnicode_DATA(u) PyUnicode_DATA(u) + #define __Pyx_PyUnicode_READ(k, d, i) PyUnicode_READ(k, d, i) + #define __Pyx_PyUnicode_WRITE(k, d, i, ch) PyUnicode_WRITE(k, d, i, ch) + #if defined(PyUnicode_IS_READY) && defined(PyUnicode_GET_SIZE) + #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x03090000 + #define __Pyx_PyUnicode_IS_TRUE(u) (0 != (likely(PyUnicode_IS_READY(u)) ? PyUnicode_GET_LENGTH(u) : ((PyCompactUnicodeObject *)(u))->wstr_length)) + #else + #define __Pyx_PyUnicode_IS_TRUE(u) (0 != (likely(PyUnicode_IS_READY(u)) ? PyUnicode_GET_LENGTH(u) : PyUnicode_GET_SIZE(u))) + #endif + #else + #define __Pyx_PyUnicode_IS_TRUE(u) (0 != PyUnicode_GET_LENGTH(u)) + #endif +#else + #define CYTHON_PEP393_ENABLED 0 + #define PyUnicode_1BYTE_KIND 1 + #define PyUnicode_2BYTE_KIND 2 + #define PyUnicode_4BYTE_KIND 4 + #define __Pyx_PyUnicode_READY(op) (0) + #define __Pyx_PyUnicode_GET_LENGTH(u) PyUnicode_GET_SIZE(u) + #define __Pyx_PyUnicode_READ_CHAR(u, i) ((Py_UCS4)(PyUnicode_AS_UNICODE(u)[i])) + #define __Pyx_PyUnicode_MAX_CHAR_VALUE(u) ((sizeof(Py_UNICODE) == 2) ? 65535 : 1114111) + #define __Pyx_PyUnicode_KIND(u) (sizeof(Py_UNICODE)) + #define __Pyx_PyUnicode_DATA(u) ((void*)PyUnicode_AS_UNICODE(u)) + #define __Pyx_PyUnicode_READ(k, d, i) ((void)(k), (Py_UCS4)(((Py_UNICODE*)d)[i])) + #define __Pyx_PyUnicode_WRITE(k, d, i, ch) (((void)(k)), ((Py_UNICODE*)d)[i] = ch) + #define __Pyx_PyUnicode_IS_TRUE(u) (0 != PyUnicode_GET_SIZE(u)) +#endif +#if CYTHON_COMPILING_IN_PYPY + #define __Pyx_PyUnicode_Concat(a, b) PyNumber_Add(a, b) + #define __Pyx_PyUnicode_ConcatSafe(a, b) PyNumber_Add(a, b) +#else + #define __Pyx_PyUnicode_Concat(a, b) PyUnicode_Concat(a, b) + #define __Pyx_PyUnicode_ConcatSafe(a, b) ((unlikely((a) == Py_None) || unlikely((b) == Py_None)) ?\ + PyNumber_Add(a, b) : __Pyx_PyUnicode_Concat(a, b)) +#endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyUnicode_Contains) + #define PyUnicode_Contains(u, s) PySequence_Contains(u, s) +#endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyByteArray_Check) + #define PyByteArray_Check(obj) PyObject_TypeCheck(obj, &PyByteArray_Type) +#endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Format) + #define PyObject_Format(obj, fmt) PyObject_CallMethod(obj, "__format__", "O", fmt) +#endif +#define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None || (PyString_Check(b) && !PyString_CheckExact(b)))) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b)) +#define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None || (PyUnicode_Check(b) && !PyUnicode_CheckExact(b)))) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b)) +#if PY_MAJOR_VERSION >= 3 + #define __Pyx_PyString_Format(a, b) PyUnicode_Format(a, b) +#else + #define __Pyx_PyString_Format(a, b) PyString_Format(a, b) +#endif +#if PY_MAJOR_VERSION < 3 && !defined(PyObject_ASCII) + #define PyObject_ASCII(o) PyObject_Repr(o) +#endif +#if PY_MAJOR_VERSION >= 3 + #define PyBaseString_Type PyUnicode_Type + #define PyStringObject PyUnicodeObject + #define PyString_Type PyUnicode_Type + #define PyString_Check PyUnicode_Check + #define PyString_CheckExact PyUnicode_CheckExact +#ifndef PyObject_Unicode + #define PyObject_Unicode PyObject_Str +#endif +#endif +#if PY_MAJOR_VERSION >= 3 + #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj) + #define __Pyx_PyBaseString_CheckExact(obj) PyUnicode_CheckExact(obj) +#else + #define __Pyx_PyBaseString_Check(obj) (PyString_Check(obj) || PyUnicode_Check(obj)) + #define __Pyx_PyBaseString_CheckExact(obj) (PyString_CheckExact(obj) || PyUnicode_CheckExact(obj)) +#endif +#ifndef PySet_CheckExact + #define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type) +#endif +#if PY_VERSION_HEX >= 0x030900A4 + #define __Pyx_SET_REFCNT(obj, refcnt) Py_SET_REFCNT(obj, refcnt) + #define __Pyx_SET_SIZE(obj, size) Py_SET_SIZE(obj, size) +#else + #define __Pyx_SET_REFCNT(obj, refcnt) Py_REFCNT(obj) = (refcnt) + #define __Pyx_SET_SIZE(obj, size) Py_SIZE(obj) = (size) +#endif +#if CYTHON_ASSUME_SAFE_MACROS + #define __Pyx_PySequence_SIZE(seq) Py_SIZE(seq) +#else + #define __Pyx_PySequence_SIZE(seq) PySequence_Size(seq) +#endif +#if PY_MAJOR_VERSION >= 3 + #define PyIntObject PyLongObject + #define PyInt_Type PyLong_Type + #define PyInt_Check(op) PyLong_Check(op) + #define PyInt_CheckExact(op) PyLong_CheckExact(op) + #define PyInt_FromString PyLong_FromString + #define PyInt_FromUnicode PyLong_FromUnicode + #define PyInt_FromLong PyLong_FromLong + #define PyInt_FromSize_t PyLong_FromSize_t + #define PyInt_FromSsize_t PyLong_FromSsize_t + #define PyInt_AsLong PyLong_AsLong + #define PyInt_AS_LONG PyLong_AS_LONG + #define PyInt_AsSsize_t PyLong_AsSsize_t + #define PyInt_AsUnsignedLongMask PyLong_AsUnsignedLongMask + #define PyInt_AsUnsignedLongLongMask PyLong_AsUnsignedLongLongMask + #define PyNumber_Int PyNumber_Long +#endif +#if PY_MAJOR_VERSION >= 3 + #define PyBoolObject PyLongObject +#endif +#if PY_MAJOR_VERSION >= 3 && CYTHON_COMPILING_IN_PYPY + #ifndef PyUnicode_InternFromString + #define PyUnicode_InternFromString(s) PyUnicode_FromString(s) + #endif +#endif +#if PY_VERSION_HEX < 0x030200A4 + typedef long Py_hash_t; + #define __Pyx_PyInt_FromHash_t PyInt_FromLong + #define __Pyx_PyInt_AsHash_t __Pyx_PyIndex_AsHash_t +#else + #define __Pyx_PyInt_FromHash_t PyInt_FromSsize_t + #define __Pyx_PyInt_AsHash_t __Pyx_PyIndex_AsSsize_t +#endif +#if PY_MAJOR_VERSION >= 3 + #define __Pyx_PyMethod_New(func, self, klass) ((self) ? ((void)(klass), PyMethod_New(func, self)) : __Pyx_NewRef(func)) +#else + #define __Pyx_PyMethod_New(func, self, klass) PyMethod_New(func, self, klass) +#endif +#if CYTHON_USE_ASYNC_SLOTS + #if PY_VERSION_HEX >= 0x030500B1 + #define __Pyx_PyAsyncMethodsStruct PyAsyncMethods + #define __Pyx_PyType_AsAsync(obj) (Py_TYPE(obj)->tp_as_async) + #else + #define __Pyx_PyType_AsAsync(obj) ((__Pyx_PyAsyncMethodsStruct*) (Py_TYPE(obj)->tp_reserved)) + #endif +#else + #define __Pyx_PyType_AsAsync(obj) NULL +#endif +#ifndef __Pyx_PyAsyncMethodsStruct + typedef struct { + unaryfunc am_await; + unaryfunc am_aiter; + unaryfunc am_anext; + } __Pyx_PyAsyncMethodsStruct; +#endif + +#if defined(WIN32) || defined(MS_WINDOWS) + #define _USE_MATH_DEFINES +#endif +#include +#ifdef NAN +#define __PYX_NAN() ((float) NAN) +#else +static CYTHON_INLINE float __PYX_NAN() { + float value; + memset(&value, 0xFF, sizeof(value)); + return value; +} +#endif +#if defined(__CYGWIN__) && defined(_LDBL_EQ_DBL) +#define __Pyx_truncl trunc +#else +#define __Pyx_truncl truncl +#endif + +#define __PYX_MARK_ERR_POS(f_index, lineno) \ + { __pyx_filename = __pyx_f[f_index]; (void)__pyx_filename; __pyx_lineno = lineno; (void)__pyx_lineno; __pyx_clineno = __LINE__; (void)__pyx_clineno; } +#define __PYX_ERR(f_index, lineno, Ln_error) \ + { __PYX_MARK_ERR_POS(f_index, lineno) goto Ln_error; } + +#ifndef __PYX_EXTERN_C + #ifdef __cplusplus + #define __PYX_EXTERN_C extern "C" + #else + #define __PYX_EXTERN_C extern + #endif +#endif + +#define __PYX_HAVE__cython_bbox +#define __PYX_HAVE_API__cython_bbox +/* Early includes */ +#include +#include +#include "numpy/arrayobject.h" +#include "numpy/ndarrayobject.h" +#include "numpy/ndarraytypes.h" +#include "numpy/arrayscalars.h" +#include "numpy/ufuncobject.h" + + /* NumPy API declarations from "numpy/__init__.pxd" */ + +#ifdef _OPENMP +#include +#endif /* _OPENMP */ + +#if defined(PYREX_WITHOUT_ASSERTIONS) && !defined(CYTHON_WITHOUT_ASSERTIONS) +#define CYTHON_WITHOUT_ASSERTIONS +#endif + +typedef struct {PyObject **p; const char *s; const Py_ssize_t n; const char* encoding; + const char is_unicode; const char is_str; const char intern; } __Pyx_StringTabEntry; + +#define __PYX_DEFAULT_STRING_ENCODING_IS_ASCII 0 +#define __PYX_DEFAULT_STRING_ENCODING_IS_UTF8 0 +#define __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT (PY_MAJOR_VERSION >= 3 && __PYX_DEFAULT_STRING_ENCODING_IS_UTF8) +#define __PYX_DEFAULT_STRING_ENCODING "" +#define __Pyx_PyObject_FromString __Pyx_PyBytes_FromString +#define __Pyx_PyObject_FromStringAndSize __Pyx_PyBytes_FromStringAndSize +#define __Pyx_uchar_cast(c) ((unsigned char)c) +#define __Pyx_long_cast(x) ((long)x) +#define __Pyx_fits_Py_ssize_t(v, type, is_signed) (\ + (sizeof(type) < sizeof(Py_ssize_t)) ||\ + (sizeof(type) > sizeof(Py_ssize_t) &&\ + likely(v < (type)PY_SSIZE_T_MAX ||\ + v == (type)PY_SSIZE_T_MAX) &&\ + (!is_signed || likely(v > (type)PY_SSIZE_T_MIN ||\ + v == (type)PY_SSIZE_T_MIN))) ||\ + (sizeof(type) == sizeof(Py_ssize_t) &&\ + (is_signed || likely(v < (type)PY_SSIZE_T_MAX ||\ + v == (type)PY_SSIZE_T_MAX))) ) +static CYTHON_INLINE int __Pyx_is_valid_index(Py_ssize_t i, Py_ssize_t limit) { + return (size_t) i < (size_t) limit; +} +#if defined (__cplusplus) && __cplusplus >= 201103L + #include + #define __Pyx_sst_abs(value) std::abs(value) +#elif SIZEOF_INT >= SIZEOF_SIZE_T + #define __Pyx_sst_abs(value) abs(value) +#elif SIZEOF_LONG >= SIZEOF_SIZE_T + #define __Pyx_sst_abs(value) labs(value) +#elif defined (_MSC_VER) + #define __Pyx_sst_abs(value) ((Py_ssize_t)_abs64(value)) +#elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define __Pyx_sst_abs(value) llabs(value) +#elif defined (__GNUC__) + #define __Pyx_sst_abs(value) __builtin_llabs(value) +#else + #define __Pyx_sst_abs(value) ((value<0) ? -value : value) +#endif +static CYTHON_INLINE const char* __Pyx_PyObject_AsString(PyObject*); +static CYTHON_INLINE const char* __Pyx_PyObject_AsStringAndSize(PyObject*, Py_ssize_t* length); +#define __Pyx_PyByteArray_FromString(s) PyByteArray_FromStringAndSize((const char*)s, strlen((const char*)s)) +#define __Pyx_PyByteArray_FromStringAndSize(s, l) PyByteArray_FromStringAndSize((const char*)s, l) +#define __Pyx_PyBytes_FromString PyBytes_FromString +#define __Pyx_PyBytes_FromStringAndSize PyBytes_FromStringAndSize +static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(const char*); +#if PY_MAJOR_VERSION < 3 + #define __Pyx_PyStr_FromString __Pyx_PyBytes_FromString + #define __Pyx_PyStr_FromStringAndSize __Pyx_PyBytes_FromStringAndSize +#else + #define __Pyx_PyStr_FromString __Pyx_PyUnicode_FromString + #define __Pyx_PyStr_FromStringAndSize __Pyx_PyUnicode_FromStringAndSize +#endif +#define __Pyx_PyBytes_AsWritableString(s) ((char*) PyBytes_AS_STRING(s)) +#define __Pyx_PyBytes_AsWritableSString(s) ((signed char*) PyBytes_AS_STRING(s)) +#define __Pyx_PyBytes_AsWritableUString(s) ((unsigned char*) PyBytes_AS_STRING(s)) +#define __Pyx_PyBytes_AsString(s) ((const char*) PyBytes_AS_STRING(s)) +#define __Pyx_PyBytes_AsSString(s) ((const signed char*) PyBytes_AS_STRING(s)) +#define __Pyx_PyBytes_AsUString(s) ((const unsigned char*) PyBytes_AS_STRING(s)) +#define __Pyx_PyObject_AsWritableString(s) ((char*) __Pyx_PyObject_AsString(s)) +#define __Pyx_PyObject_AsWritableSString(s) ((signed char*) __Pyx_PyObject_AsString(s)) +#define __Pyx_PyObject_AsWritableUString(s) ((unsigned char*) __Pyx_PyObject_AsString(s)) +#define __Pyx_PyObject_AsSString(s) ((const signed char*) __Pyx_PyObject_AsString(s)) +#define __Pyx_PyObject_AsUString(s) ((const unsigned char*) __Pyx_PyObject_AsString(s)) +#define __Pyx_PyObject_FromCString(s) __Pyx_PyObject_FromString((const char*)s) +#define __Pyx_PyBytes_FromCString(s) __Pyx_PyBytes_FromString((const char*)s) +#define __Pyx_PyByteArray_FromCString(s) __Pyx_PyByteArray_FromString((const char*)s) +#define __Pyx_PyStr_FromCString(s) __Pyx_PyStr_FromString((const char*)s) +#define __Pyx_PyUnicode_FromCString(s) __Pyx_PyUnicode_FromString((const char*)s) +static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u) { + const Py_UNICODE *u_end = u; + while (*u_end++) ; + return (size_t)(u_end - u - 1); +} +#define __Pyx_PyUnicode_FromUnicode(u) PyUnicode_FromUnicode(u, __Pyx_Py_UNICODE_strlen(u)) +#define __Pyx_PyUnicode_FromUnicodeAndLength PyUnicode_FromUnicode +#define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode +#define __Pyx_NewRef(obj) (Py_INCREF(obj), obj) +#define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None) +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b); +static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*); +static CYTHON_INLINE int __Pyx_PyObject_IsTrueAndDecref(PyObject*); +static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x); +#define __Pyx_PySequence_Tuple(obj)\ + (likely(PyTuple_CheckExact(obj)) ? __Pyx_NewRef(obj) : PySequence_Tuple(obj)) +static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject*); +static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t); +static CYTHON_INLINE Py_hash_t __Pyx_PyIndex_AsHash_t(PyObject*); +#if CYTHON_ASSUME_SAFE_MACROS +#define __pyx_PyFloat_AsDouble(x) (PyFloat_CheckExact(x) ? PyFloat_AS_DOUBLE(x) : PyFloat_AsDouble(x)) +#else +#define __pyx_PyFloat_AsDouble(x) PyFloat_AsDouble(x) +#endif +#define __pyx_PyFloat_AsFloat(x) ((float) __pyx_PyFloat_AsDouble(x)) +#if PY_MAJOR_VERSION >= 3 +#define __Pyx_PyNumber_Int(x) (PyLong_CheckExact(x) ? __Pyx_NewRef(x) : PyNumber_Long(x)) +#else +#define __Pyx_PyNumber_Int(x) (PyInt_CheckExact(x) ? __Pyx_NewRef(x) : PyNumber_Int(x)) +#endif +#define __Pyx_PyNumber_Float(x) (PyFloat_CheckExact(x) ? __Pyx_NewRef(x) : PyNumber_Float(x)) +#if PY_MAJOR_VERSION < 3 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII +static int __Pyx_sys_getdefaultencoding_not_ascii; +static int __Pyx_init_sys_getdefaultencoding_params(void) { + PyObject* sys; + PyObject* default_encoding = NULL; + PyObject* ascii_chars_u = NULL; + PyObject* ascii_chars_b = NULL; + const char* default_encoding_c; + sys = PyImport_ImportModule("sys"); + if (!sys) goto bad; + default_encoding = PyObject_CallMethod(sys, (char*) "getdefaultencoding", NULL); + Py_DECREF(sys); + if (!default_encoding) goto bad; + default_encoding_c = PyBytes_AsString(default_encoding); + if (!default_encoding_c) goto bad; + if (strcmp(default_encoding_c, "ascii") == 0) { + __Pyx_sys_getdefaultencoding_not_ascii = 0; + } else { + char ascii_chars[128]; + int c; + for (c = 0; c < 128; c++) { + ascii_chars[c] = c; + } + __Pyx_sys_getdefaultencoding_not_ascii = 1; + ascii_chars_u = PyUnicode_DecodeASCII(ascii_chars, 128, NULL); + if (!ascii_chars_u) goto bad; + ascii_chars_b = PyUnicode_AsEncodedString(ascii_chars_u, default_encoding_c, NULL); + if (!ascii_chars_b || !PyBytes_Check(ascii_chars_b) || memcmp(ascii_chars, PyBytes_AS_STRING(ascii_chars_b), 128) != 0) { + PyErr_Format( + PyExc_ValueError, + "This module compiled with c_string_encoding=ascii, but default encoding '%.200s' is not a superset of ascii.", + default_encoding_c); + goto bad; + } + Py_DECREF(ascii_chars_u); + Py_DECREF(ascii_chars_b); + } + Py_DECREF(default_encoding); + return 0; +bad: + Py_XDECREF(default_encoding); + Py_XDECREF(ascii_chars_u); + Py_XDECREF(ascii_chars_b); + return -1; +} +#endif +#if __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT && PY_MAJOR_VERSION >= 3 +#define __Pyx_PyUnicode_FromStringAndSize(c_str, size) PyUnicode_DecodeUTF8(c_str, size, NULL) +#else +#define __Pyx_PyUnicode_FromStringAndSize(c_str, size) PyUnicode_Decode(c_str, size, __PYX_DEFAULT_STRING_ENCODING, NULL) +#if __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT +static char* __PYX_DEFAULT_STRING_ENCODING; +static int __Pyx_init_sys_getdefaultencoding_params(void) { + PyObject* sys; + PyObject* default_encoding = NULL; + char* default_encoding_c; + sys = PyImport_ImportModule("sys"); + if (!sys) goto bad; + default_encoding = PyObject_CallMethod(sys, (char*) (const char*) "getdefaultencoding", NULL); + Py_DECREF(sys); + if (!default_encoding) goto bad; + default_encoding_c = PyBytes_AsString(default_encoding); + if (!default_encoding_c) goto bad; + __PYX_DEFAULT_STRING_ENCODING = (char*) malloc(strlen(default_encoding_c) + 1); + if (!__PYX_DEFAULT_STRING_ENCODING) goto bad; + strcpy(__PYX_DEFAULT_STRING_ENCODING, default_encoding_c); + Py_DECREF(default_encoding); + return 0; +bad: + Py_XDECREF(default_encoding); + return -1; +} +#endif +#endif + + +/* Test for GCC > 2.95 */ +#if defined(__GNUC__) && (__GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95))) + #define likely(x) __builtin_expect(!!(x), 1) + #define unlikely(x) __builtin_expect(!!(x), 0) +#else /* !__GNUC__ or GCC < 2.95 */ + #define likely(x) (x) + #define unlikely(x) (x) +#endif /* __GNUC__ */ +static CYTHON_INLINE void __Pyx_pretend_to_initialize(void* ptr) { (void)ptr; } + +static PyObject *__pyx_m = NULL; +static PyObject *__pyx_d; +static PyObject *__pyx_b; +static PyObject *__pyx_cython_runtime = NULL; +static PyObject *__pyx_empty_tuple; +static PyObject *__pyx_empty_bytes; +static PyObject *__pyx_empty_unicode; +static int __pyx_lineno; +static int __pyx_clineno = 0; +static const char * __pyx_cfilenm= __FILE__; +static const char *__pyx_filename; + +/* Header.proto */ +#if !defined(CYTHON_CCOMPLEX) + #if defined(__cplusplus) + #define CYTHON_CCOMPLEX 1 + #elif defined(_Complex_I) + #define CYTHON_CCOMPLEX 1 + #else + #define CYTHON_CCOMPLEX 0 + #endif +#endif +#if CYTHON_CCOMPLEX + #ifdef __cplusplus + #include + #else + #include + #endif +#endif +#if CYTHON_CCOMPLEX && !defined(__cplusplus) && defined(__sun__) && defined(__GNUC__) + #undef _Complex_I + #define _Complex_I 1.0fj +#endif + + +static const char *__pyx_f[] = { + "src\\cython_bbox.pyx", + "__init__.pxd", + "type.pxd", +}; +/* BufferFormatStructs.proto */ +#define IS_UNSIGNED(type) (((type) -1) > 0) +struct __Pyx_StructField_; +#define __PYX_BUF_FLAGS_PACKED_STRUCT (1 << 0) +typedef struct { + const char* name; + struct __Pyx_StructField_* fields; + size_t size; + size_t arraysize[8]; + int ndim; + char typegroup; + char is_unsigned; + int flags; +} __Pyx_TypeInfo; +typedef struct __Pyx_StructField_ { + __Pyx_TypeInfo* type; + const char* name; + size_t offset; +} __Pyx_StructField; +typedef struct { + __Pyx_StructField* field; + size_t parent_offset; +} __Pyx_BufFmt_StackElem; +typedef struct { + __Pyx_StructField root; + __Pyx_BufFmt_StackElem* head; + size_t fmt_offset; + size_t new_count, enc_count; + size_t struct_alignment; + int is_complex; + char enc_type; + char new_packmode; + char enc_packmode; + char is_valid_array; +} __Pyx_BufFmt_Context; + + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":690 + * # in Cython to enable them only on the right systems. + * + * ctypedef npy_int8 int8_t # <<<<<<<<<<<<<< + * ctypedef npy_int16 int16_t + * ctypedef npy_int32 int32_t + */ +typedef npy_int8 __pyx_t_5numpy_int8_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":691 + * + * ctypedef npy_int8 int8_t + * ctypedef npy_int16 int16_t # <<<<<<<<<<<<<< + * ctypedef npy_int32 int32_t + * ctypedef npy_int64 int64_t + */ +typedef npy_int16 __pyx_t_5numpy_int16_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":692 + * ctypedef npy_int8 int8_t + * ctypedef npy_int16 int16_t + * ctypedef npy_int32 int32_t # <<<<<<<<<<<<<< + * ctypedef npy_int64 int64_t + * #ctypedef npy_int96 int96_t + */ +typedef npy_int32 __pyx_t_5numpy_int32_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":693 + * ctypedef npy_int16 int16_t + * ctypedef npy_int32 int32_t + * ctypedef npy_int64 int64_t # <<<<<<<<<<<<<< + * #ctypedef npy_int96 int96_t + * #ctypedef npy_int128 int128_t + */ +typedef npy_int64 __pyx_t_5numpy_int64_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":697 + * #ctypedef npy_int128 int128_t + * + * ctypedef npy_uint8 uint8_t # <<<<<<<<<<<<<< + * ctypedef npy_uint16 uint16_t + * ctypedef npy_uint32 uint32_t + */ +typedef npy_uint8 __pyx_t_5numpy_uint8_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":698 + * + * ctypedef npy_uint8 uint8_t + * ctypedef npy_uint16 uint16_t # <<<<<<<<<<<<<< + * ctypedef npy_uint32 uint32_t + * ctypedef npy_uint64 uint64_t + */ +typedef npy_uint16 __pyx_t_5numpy_uint16_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":699 + * ctypedef npy_uint8 uint8_t + * ctypedef npy_uint16 uint16_t + * ctypedef npy_uint32 uint32_t # <<<<<<<<<<<<<< + * ctypedef npy_uint64 uint64_t + * #ctypedef npy_uint96 uint96_t + */ +typedef npy_uint32 __pyx_t_5numpy_uint32_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":700 + * ctypedef npy_uint16 uint16_t + * ctypedef npy_uint32 uint32_t + * ctypedef npy_uint64 uint64_t # <<<<<<<<<<<<<< + * #ctypedef npy_uint96 uint96_t + * #ctypedef npy_uint128 uint128_t + */ +typedef npy_uint64 __pyx_t_5numpy_uint64_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":704 + * #ctypedef npy_uint128 uint128_t + * + * ctypedef npy_float32 float32_t # <<<<<<<<<<<<<< + * ctypedef npy_float64 float64_t + * #ctypedef npy_float80 float80_t + */ +typedef npy_float32 __pyx_t_5numpy_float32_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":705 + * + * ctypedef npy_float32 float32_t + * ctypedef npy_float64 float64_t # <<<<<<<<<<<<<< + * #ctypedef npy_float80 float80_t + * #ctypedef npy_float128 float128_t + */ +typedef npy_float64 __pyx_t_5numpy_float64_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":714 + * # The int types are mapped a bit surprising -- + * # numpy.int corresponds to 'l' and numpy.long to 'q' + * ctypedef npy_long int_t # <<<<<<<<<<<<<< + * ctypedef npy_longlong long_t + * ctypedef npy_longlong longlong_t + */ +typedef npy_long __pyx_t_5numpy_int_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":715 + * # numpy.int corresponds to 'l' and numpy.long to 'q' + * ctypedef npy_long int_t + * ctypedef npy_longlong long_t # <<<<<<<<<<<<<< + * ctypedef npy_longlong longlong_t + * + */ +typedef npy_longlong __pyx_t_5numpy_long_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":716 + * ctypedef npy_long int_t + * ctypedef npy_longlong long_t + * ctypedef npy_longlong longlong_t # <<<<<<<<<<<<<< + * + * ctypedef npy_ulong uint_t + */ +typedef npy_longlong __pyx_t_5numpy_longlong_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":718 + * ctypedef npy_longlong longlong_t + * + * ctypedef npy_ulong uint_t # <<<<<<<<<<<<<< + * ctypedef npy_ulonglong ulong_t + * ctypedef npy_ulonglong ulonglong_t + */ +typedef npy_ulong __pyx_t_5numpy_uint_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":719 + * + * ctypedef npy_ulong uint_t + * ctypedef npy_ulonglong ulong_t # <<<<<<<<<<<<<< + * ctypedef npy_ulonglong ulonglong_t + * + */ +typedef npy_ulonglong __pyx_t_5numpy_ulong_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":720 + * ctypedef npy_ulong uint_t + * ctypedef npy_ulonglong ulong_t + * ctypedef npy_ulonglong ulonglong_t # <<<<<<<<<<<<<< + * + * ctypedef npy_intp intp_t + */ +typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":722 + * ctypedef npy_ulonglong ulonglong_t + * + * ctypedef npy_intp intp_t # <<<<<<<<<<<<<< + * ctypedef npy_uintp uintp_t + * + */ +typedef npy_intp __pyx_t_5numpy_intp_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":723 + * + * ctypedef npy_intp intp_t + * ctypedef npy_uintp uintp_t # <<<<<<<<<<<<<< + * + * ctypedef npy_double float_t + */ +typedef npy_uintp __pyx_t_5numpy_uintp_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":725 + * ctypedef npy_uintp uintp_t + * + * ctypedef npy_double float_t # <<<<<<<<<<<<<< + * ctypedef npy_double double_t + * ctypedef npy_longdouble longdouble_t + */ +typedef npy_double __pyx_t_5numpy_float_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":726 + * + * ctypedef npy_double float_t + * ctypedef npy_double double_t # <<<<<<<<<<<<<< + * ctypedef npy_longdouble longdouble_t + * + */ +typedef npy_double __pyx_t_5numpy_double_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":727 + * ctypedef npy_double float_t + * ctypedef npy_double double_t + * ctypedef npy_longdouble longdouble_t # <<<<<<<<<<<<<< + * + * ctypedef npy_cfloat cfloat_t + */ +typedef npy_longdouble __pyx_t_5numpy_longdouble_t; + +/* "cython_bbox.pyx":13 + * + * DTYPE = np.float + * ctypedef np.float_t DTYPE_t # <<<<<<<<<<<<<< + * + * def bbox_overlaps( + */ +typedef __pyx_t_5numpy_float_t __pyx_t_11cython_bbox_DTYPE_t; +/* Declarations.proto */ +#if CYTHON_CCOMPLEX + #ifdef __cplusplus + typedef ::std::complex< float > __pyx_t_float_complex; + #else + typedef float _Complex __pyx_t_float_complex; + #endif +#else + typedef struct { float real, imag; } __pyx_t_float_complex; +#endif +static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float, float); + +/* Declarations.proto */ +#if CYTHON_CCOMPLEX + #ifdef __cplusplus + typedef ::std::complex< double > __pyx_t_double_complex; + #else + typedef double _Complex __pyx_t_double_complex; + #endif +#else + typedef struct { double real, imag; } __pyx_t_double_complex; +#endif +static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double, double); + + +/*--- Type declarations ---*/ + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":729 + * ctypedef npy_longdouble longdouble_t + * + * ctypedef npy_cfloat cfloat_t # <<<<<<<<<<<<<< + * ctypedef npy_cdouble cdouble_t + * ctypedef npy_clongdouble clongdouble_t + */ +typedef npy_cfloat __pyx_t_5numpy_cfloat_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":730 + * + * ctypedef npy_cfloat cfloat_t + * ctypedef npy_cdouble cdouble_t # <<<<<<<<<<<<<< + * ctypedef npy_clongdouble clongdouble_t + * + */ +typedef npy_cdouble __pyx_t_5numpy_cdouble_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":731 + * ctypedef npy_cfloat cfloat_t + * ctypedef npy_cdouble cdouble_t + * ctypedef npy_clongdouble clongdouble_t # <<<<<<<<<<<<<< + * + * ctypedef npy_cdouble complex_t + */ +typedef npy_clongdouble __pyx_t_5numpy_clongdouble_t; + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":733 + * ctypedef npy_clongdouble clongdouble_t + * + * ctypedef npy_cdouble complex_t # <<<<<<<<<<<<<< + * + * cdef inline object PyArray_MultiIterNew1(a): + */ +typedef npy_cdouble __pyx_t_5numpy_complex_t; + +/* --- Runtime support code (head) --- */ +/* Refnanny.proto */ +#ifndef CYTHON_REFNANNY + #define CYTHON_REFNANNY 0 +#endif +#if CYTHON_REFNANNY + typedef struct { + void (*INCREF)(void*, PyObject*, int); + void (*DECREF)(void*, PyObject*, int); + void (*GOTREF)(void*, PyObject*, int); + void (*GIVEREF)(void*, PyObject*, int); + void* (*SetupContext)(const char*, int, const char*); + void (*FinishContext)(void**); + } __Pyx_RefNannyAPIStruct; + static __Pyx_RefNannyAPIStruct *__Pyx_RefNanny = NULL; + static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname); + #define __Pyx_RefNannyDeclarations void *__pyx_refnanny = NULL; +#ifdef WITH_THREAD + #define __Pyx_RefNannySetupContext(name, acquire_gil)\ + if (acquire_gil) {\ + PyGILState_STATE __pyx_gilstate_save = PyGILState_Ensure();\ + __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__);\ + PyGILState_Release(__pyx_gilstate_save);\ + } else {\ + __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__);\ + } +#else + #define __Pyx_RefNannySetupContext(name, acquire_gil)\ + __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__) +#endif + #define __Pyx_RefNannyFinishContext()\ + __Pyx_RefNanny->FinishContext(&__pyx_refnanny) + #define __Pyx_INCREF(r) __Pyx_RefNanny->INCREF(__pyx_refnanny, (PyObject *)(r), __LINE__) + #define __Pyx_DECREF(r) __Pyx_RefNanny->DECREF(__pyx_refnanny, (PyObject *)(r), __LINE__) + #define __Pyx_GOTREF(r) __Pyx_RefNanny->GOTREF(__pyx_refnanny, (PyObject *)(r), __LINE__) + #define __Pyx_GIVEREF(r) __Pyx_RefNanny->GIVEREF(__pyx_refnanny, (PyObject *)(r), __LINE__) + #define __Pyx_XINCREF(r) do { if((r) != NULL) {__Pyx_INCREF(r); }} while(0) + #define __Pyx_XDECREF(r) do { if((r) != NULL) {__Pyx_DECREF(r); }} while(0) + #define __Pyx_XGOTREF(r) do { if((r) != NULL) {__Pyx_GOTREF(r); }} while(0) + #define __Pyx_XGIVEREF(r) do { if((r) != NULL) {__Pyx_GIVEREF(r);}} while(0) +#else + #define __Pyx_RefNannyDeclarations + #define __Pyx_RefNannySetupContext(name, acquire_gil) + #define __Pyx_RefNannyFinishContext() + #define __Pyx_INCREF(r) Py_INCREF(r) + #define __Pyx_DECREF(r) Py_DECREF(r) + #define __Pyx_GOTREF(r) + #define __Pyx_GIVEREF(r) + #define __Pyx_XINCREF(r) Py_XINCREF(r) + #define __Pyx_XDECREF(r) Py_XDECREF(r) + #define __Pyx_XGOTREF(r) + #define __Pyx_XGIVEREF(r) +#endif +#define __Pyx_XDECREF_SET(r, v) do {\ + PyObject *tmp = (PyObject *) r;\ + r = v; __Pyx_XDECREF(tmp);\ + } while (0) +#define __Pyx_DECREF_SET(r, v) do {\ + PyObject *tmp = (PyObject *) r;\ + r = v; __Pyx_DECREF(tmp);\ + } while (0) +#define __Pyx_CLEAR(r) do { PyObject* tmp = ((PyObject*)(r)); r = NULL; __Pyx_DECREF(tmp);} while(0) +#define __Pyx_XCLEAR(r) do { if((r) != NULL) {PyObject* tmp = ((PyObject*)(r)); r = NULL; __Pyx_DECREF(tmp);}} while(0) + +/* PyObjectGetAttrStr.proto */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name); +#else +#define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n) +#endif + +/* GetBuiltinName.proto */ +static PyObject *__Pyx_GetBuiltinName(PyObject *name); + +/* RaiseArgTupleInvalid.proto */ +static void __Pyx_RaiseArgtupleInvalid(const char* func_name, int exact, + Py_ssize_t num_min, Py_ssize_t num_max, Py_ssize_t num_found); + +/* RaiseDoubleKeywords.proto */ +static void __Pyx_RaiseDoubleKeywordsError(const char* func_name, PyObject* kw_name); + +/* ParseKeywords.proto */ +static int __Pyx_ParseOptionalKeywords(PyObject *kwds, PyObject **argnames[],\ + PyObject *kwds2, PyObject *values[], Py_ssize_t num_pos_args,\ + const char* function_name); + +/* ArgTypeTest.proto */ +#define __Pyx_ArgTypeTest(obj, type, none_allowed, name, exact)\ + ((likely((Py_TYPE(obj) == type) | (none_allowed && (obj == Py_None)))) ? 1 :\ + __Pyx__ArgTypeTest(obj, type, name, exact)) +static int __Pyx__ArgTypeTest(PyObject *obj, PyTypeObject *type, const char *name, int exact); + +/* IsLittleEndian.proto */ +static CYTHON_INLINE int __Pyx_Is_Little_Endian(void); + +/* BufferFormatCheck.proto */ +static const char* __Pyx_BufFmt_CheckString(__Pyx_BufFmt_Context* ctx, const char* ts); +static void __Pyx_BufFmt_Init(__Pyx_BufFmt_Context* ctx, + __Pyx_BufFmt_StackElem* stack, + __Pyx_TypeInfo* type); + +/* BufferGetAndValidate.proto */ +#define __Pyx_GetBufferAndValidate(buf, obj, dtype, flags, nd, cast, stack)\ + ((obj == Py_None || obj == NULL) ?\ + (__Pyx_ZeroBuffer(buf), 0) :\ + __Pyx__GetBufferAndValidate(buf, obj, dtype, flags, nd, cast, stack)) +static int __Pyx__GetBufferAndValidate(Py_buffer* buf, PyObject* obj, + __Pyx_TypeInfo* dtype, int flags, int nd, int cast, __Pyx_BufFmt_StackElem* stack); +static void __Pyx_ZeroBuffer(Py_buffer* buf); +static CYTHON_INLINE void __Pyx_SafeReleaseBuffer(Py_buffer* info); +static Py_ssize_t __Pyx_minusones[] = { -1, -1, -1, -1, -1, -1, -1, -1 }; +static Py_ssize_t __Pyx_zeros[] = { 0, 0, 0, 0, 0, 0, 0, 0 }; + +/* PyDictVersioning.proto */ +#if CYTHON_USE_DICT_VERSIONS && CYTHON_USE_TYPE_SLOTS +#define __PYX_DICT_VERSION_INIT ((PY_UINT64_T) -1) +#define __PYX_GET_DICT_VERSION(dict) (((PyDictObject*)(dict))->ma_version_tag) +#define __PYX_UPDATE_DICT_CACHE(dict, value, cache_var, version_var)\ + (version_var) = __PYX_GET_DICT_VERSION(dict);\ + (cache_var) = (value); +#define __PYX_PY_DICT_LOOKUP_IF_MODIFIED(VAR, DICT, LOOKUP) {\ + static PY_UINT64_T __pyx_dict_version = 0;\ + static PyObject *__pyx_dict_cached_value = NULL;\ + if (likely(__PYX_GET_DICT_VERSION(DICT) == __pyx_dict_version)) {\ + (VAR) = __pyx_dict_cached_value;\ + } else {\ + (VAR) = __pyx_dict_cached_value = (LOOKUP);\ + __pyx_dict_version = __PYX_GET_DICT_VERSION(DICT);\ + }\ +} +static CYTHON_INLINE PY_UINT64_T __Pyx_get_tp_dict_version(PyObject *obj); +static CYTHON_INLINE PY_UINT64_T __Pyx_get_object_dict_version(PyObject *obj); +static CYTHON_INLINE int __Pyx_object_dict_version_matches(PyObject* obj, PY_UINT64_T tp_dict_version, PY_UINT64_T obj_dict_version); +#else +#define __PYX_GET_DICT_VERSION(dict) (0) +#define __PYX_UPDATE_DICT_CACHE(dict, value, cache_var, version_var) +#define __PYX_PY_DICT_LOOKUP_IF_MODIFIED(VAR, DICT, LOOKUP) (VAR) = (LOOKUP); +#endif + +/* GetModuleGlobalName.proto */ +#if CYTHON_USE_DICT_VERSIONS +#define __Pyx_GetModuleGlobalName(var, name) {\ + static PY_UINT64_T __pyx_dict_version = 0;\ + static PyObject *__pyx_dict_cached_value = NULL;\ + (var) = (likely(__pyx_dict_version == __PYX_GET_DICT_VERSION(__pyx_d))) ?\ + (likely(__pyx_dict_cached_value) ? __Pyx_NewRef(__pyx_dict_cached_value) : __Pyx_GetBuiltinName(name)) :\ + __Pyx__GetModuleGlobalName(name, &__pyx_dict_version, &__pyx_dict_cached_value);\ +} +#define __Pyx_GetModuleGlobalNameUncached(var, name) {\ + PY_UINT64_T __pyx_dict_version;\ + PyObject *__pyx_dict_cached_value;\ + (var) = __Pyx__GetModuleGlobalName(name, &__pyx_dict_version, &__pyx_dict_cached_value);\ +} +static PyObject *__Pyx__GetModuleGlobalName(PyObject *name, PY_UINT64_T *dict_version, PyObject **dict_cached_value); +#else +#define __Pyx_GetModuleGlobalName(var, name) (var) = __Pyx__GetModuleGlobalName(name) +#define __Pyx_GetModuleGlobalNameUncached(var, name) (var) = __Pyx__GetModuleGlobalName(name) +static CYTHON_INLINE PyObject *__Pyx__GetModuleGlobalName(PyObject *name); +#endif + +/* PyObjectCall.proto */ +#if CYTHON_COMPILING_IN_CPYTHON +static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg, PyObject *kw); +#else +#define __Pyx_PyObject_Call(func, arg, kw) PyObject_Call(func, arg, kw) +#endif + +/* ExtTypeTest.proto */ +static CYTHON_INLINE int __Pyx_TypeTest(PyObject *obj, PyTypeObject *type); + +/* BufferIndexError.proto */ +static void __Pyx_RaiseBufferIndexError(int axis); + +#define __Pyx_BufPtrStrided2d(type, buf, i0, s0, i1, s1) (type)((char*)buf + i0 * s0 + i1 * s1) +/* PyThreadStateGet.proto */ +#if CYTHON_FAST_THREAD_STATE +#define __Pyx_PyThreadState_declare PyThreadState *__pyx_tstate; +#define __Pyx_PyThreadState_assign __pyx_tstate = __Pyx_PyThreadState_Current; +#define __Pyx_PyErr_Occurred() __pyx_tstate->curexc_type +#else +#define __Pyx_PyThreadState_declare +#define __Pyx_PyThreadState_assign +#define __Pyx_PyErr_Occurred() PyErr_Occurred() +#endif + +/* PyErrFetchRestore.proto */ +#if CYTHON_FAST_THREAD_STATE +#define __Pyx_PyErr_Clear() __Pyx_ErrRestore(NULL, NULL, NULL) +#define __Pyx_ErrRestoreWithState(type, value, tb) __Pyx_ErrRestoreInState(PyThreadState_GET(), type, value, tb) +#define __Pyx_ErrFetchWithState(type, value, tb) __Pyx_ErrFetchInState(PyThreadState_GET(), type, value, tb) +#define __Pyx_ErrRestore(type, value, tb) __Pyx_ErrRestoreInState(__pyx_tstate, type, value, tb) +#define __Pyx_ErrFetch(type, value, tb) __Pyx_ErrFetchInState(__pyx_tstate, type, value, tb) +static CYTHON_INLINE void __Pyx_ErrRestoreInState(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb); +static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb); +#if CYTHON_COMPILING_IN_CPYTHON +#define __Pyx_PyErr_SetNone(exc) (Py_INCREF(exc), __Pyx_ErrRestore((exc), NULL, NULL)) +#else +#define __Pyx_PyErr_SetNone(exc) PyErr_SetNone(exc) +#endif +#else +#define __Pyx_PyErr_Clear() PyErr_Clear() +#define __Pyx_PyErr_SetNone(exc) PyErr_SetNone(exc) +#define __Pyx_ErrRestoreWithState(type, value, tb) PyErr_Restore(type, value, tb) +#define __Pyx_ErrFetchWithState(type, value, tb) PyErr_Fetch(type, value, tb) +#define __Pyx_ErrRestoreInState(tstate, type, value, tb) PyErr_Restore(type, value, tb) +#define __Pyx_ErrFetchInState(tstate, type, value, tb) PyErr_Fetch(type, value, tb) +#define __Pyx_ErrRestore(type, value, tb) PyErr_Restore(type, value, tb) +#define __Pyx_ErrFetch(type, value, tb) PyErr_Fetch(type, value, tb) +#endif + +/* GetTopmostException.proto */ +#if CYTHON_USE_EXC_INFO_STACK +static _PyErr_StackItem * __Pyx_PyErr_GetTopmostException(PyThreadState *tstate); +#endif + +/* SaveResetException.proto */ +#if CYTHON_FAST_THREAD_STATE +#define __Pyx_ExceptionSave(type, value, tb) __Pyx__ExceptionSave(__pyx_tstate, type, value, tb) +static CYTHON_INLINE void __Pyx__ExceptionSave(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb); +#define __Pyx_ExceptionReset(type, value, tb) __Pyx__ExceptionReset(__pyx_tstate, type, value, tb) +static CYTHON_INLINE void __Pyx__ExceptionReset(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb); +#else +#define __Pyx_ExceptionSave(type, value, tb) PyErr_GetExcInfo(type, value, tb) +#define __Pyx_ExceptionReset(type, value, tb) PyErr_SetExcInfo(type, value, tb) +#endif + +/* PyErrExceptionMatches.proto */ +#if CYTHON_FAST_THREAD_STATE +#define __Pyx_PyErr_ExceptionMatches(err) __Pyx_PyErr_ExceptionMatchesInState(__pyx_tstate, err) +static CYTHON_INLINE int __Pyx_PyErr_ExceptionMatchesInState(PyThreadState* tstate, PyObject* err); +#else +#define __Pyx_PyErr_ExceptionMatches(err) PyErr_ExceptionMatches(err) +#endif + +/* GetException.proto */ +#if CYTHON_FAST_THREAD_STATE +#define __Pyx_GetException(type, value, tb) __Pyx__GetException(__pyx_tstate, type, value, tb) +static int __Pyx__GetException(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb); +#else +static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb); +#endif + +/* RaiseException.proto */ +static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause); + +/* TypeImport.proto */ +#ifndef __PYX_HAVE_RT_ImportType_proto +#define __PYX_HAVE_RT_ImportType_proto +enum __Pyx_ImportType_CheckSize { + __Pyx_ImportType_CheckSize_Error = 0, + __Pyx_ImportType_CheckSize_Warn = 1, + __Pyx_ImportType_CheckSize_Ignore = 2 +}; +static PyTypeObject *__Pyx_ImportType(PyObject* module, const char *module_name, const char *class_name, size_t size, enum __Pyx_ImportType_CheckSize check_size); +#endif + +/* Import.proto */ +static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level); + +/* CLineInTraceback.proto */ +#ifdef CYTHON_CLINE_IN_TRACEBACK +#define __Pyx_CLineForTraceback(tstate, c_line) (((CYTHON_CLINE_IN_TRACEBACK)) ? c_line : 0) +#else +static int __Pyx_CLineForTraceback(PyThreadState *tstate, int c_line); +#endif + +/* CodeObjectCache.proto */ +typedef struct { + PyCodeObject* code_object; + int code_line; +} __Pyx_CodeObjectCacheEntry; +struct __Pyx_CodeObjectCache { + int count; + int max_count; + __Pyx_CodeObjectCacheEntry* entries; +}; +static struct __Pyx_CodeObjectCache __pyx_code_cache = {0,0,NULL}; +static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line); +static PyCodeObject *__pyx_find_code_object(int code_line); +static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object); + +/* AddTraceback.proto */ +static void __Pyx_AddTraceback(const char *funcname, int c_line, + int py_line, const char *filename); + +/* BufferStructDeclare.proto */ +typedef struct { + Py_ssize_t shape, strides, suboffsets; +} __Pyx_Buf_DimInfo; +typedef struct { + size_t refcount; + Py_buffer pybuffer; +} __Pyx_Buffer; +typedef struct { + __Pyx_Buffer *rcbuffer; + char *data; + __Pyx_Buf_DimInfo diminfo[8]; +} __Pyx_LocalBuf_ND; + +#if PY_MAJOR_VERSION < 3 + static int __Pyx_GetBuffer(PyObject *obj, Py_buffer *view, int flags); + static void __Pyx_ReleaseBuffer(Py_buffer *view); +#else + #define __Pyx_GetBuffer PyObject_GetBuffer + #define __Pyx_ReleaseBuffer PyBuffer_Release +#endif + + +/* GCCDiagnostics.proto */ +#if defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)) +#define __Pyx_HAS_GCC_DIAGNOSTIC +#endif + +/* RealImag.proto */ +#if CYTHON_CCOMPLEX + #ifdef __cplusplus + #define __Pyx_CREAL(z) ((z).real()) + #define __Pyx_CIMAG(z) ((z).imag()) + #else + #define __Pyx_CREAL(z) (__real__(z)) + #define __Pyx_CIMAG(z) (__imag__(z)) + #endif +#else + #define __Pyx_CREAL(z) ((z).real) + #define __Pyx_CIMAG(z) ((z).imag) +#endif +#if defined(__cplusplus) && CYTHON_CCOMPLEX\ + && (defined(_WIN32) || defined(__clang__) || (defined(__GNUC__) && (__GNUC__ >= 5 || __GNUC__ == 4 && __GNUC_MINOR__ >= 4 )) || __cplusplus >= 201103) + #define __Pyx_SET_CREAL(z,x) ((z).real(x)) + #define __Pyx_SET_CIMAG(z,y) ((z).imag(y)) +#else + #define __Pyx_SET_CREAL(z,x) __Pyx_CREAL(z) = (x) + #define __Pyx_SET_CIMAG(z,y) __Pyx_CIMAG(z) = (y) +#endif + +/* Arithmetic.proto */ +#if CYTHON_CCOMPLEX + #define __Pyx_c_eq_float(a, b) ((a)==(b)) + #define __Pyx_c_sum_float(a, b) ((a)+(b)) + #define __Pyx_c_diff_float(a, b) ((a)-(b)) + #define __Pyx_c_prod_float(a, b) ((a)*(b)) + #define __Pyx_c_quot_float(a, b) ((a)/(b)) + #define __Pyx_c_neg_float(a) (-(a)) + #ifdef __cplusplus + #define __Pyx_c_is_zero_float(z) ((z)==(float)0) + #define __Pyx_c_conj_float(z) (::std::conj(z)) + #if 1 + #define __Pyx_c_abs_float(z) (::std::abs(z)) + #define __Pyx_c_pow_float(a, b) (::std::pow(a, b)) + #endif + #else + #define __Pyx_c_is_zero_float(z) ((z)==0) + #define __Pyx_c_conj_float(z) (conjf(z)) + #if 1 + #define __Pyx_c_abs_float(z) (cabsf(z)) + #define __Pyx_c_pow_float(a, b) (cpowf(a, b)) + #endif + #endif +#else + static CYTHON_INLINE int __Pyx_c_eq_float(__pyx_t_float_complex, __pyx_t_float_complex); + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_sum_float(__pyx_t_float_complex, __pyx_t_float_complex); + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_diff_float(__pyx_t_float_complex, __pyx_t_float_complex); + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_prod_float(__pyx_t_float_complex, __pyx_t_float_complex); + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_quot_float(__pyx_t_float_complex, __pyx_t_float_complex); + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_neg_float(__pyx_t_float_complex); + static CYTHON_INLINE int __Pyx_c_is_zero_float(__pyx_t_float_complex); + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_conj_float(__pyx_t_float_complex); + #if 1 + static CYTHON_INLINE float __Pyx_c_abs_float(__pyx_t_float_complex); + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_pow_float(__pyx_t_float_complex, __pyx_t_float_complex); + #endif +#endif + +/* Arithmetic.proto */ +#if CYTHON_CCOMPLEX + #define __Pyx_c_eq_double(a, b) ((a)==(b)) + #define __Pyx_c_sum_double(a, b) ((a)+(b)) + #define __Pyx_c_diff_double(a, b) ((a)-(b)) + #define __Pyx_c_prod_double(a, b) ((a)*(b)) + #define __Pyx_c_quot_double(a, b) ((a)/(b)) + #define __Pyx_c_neg_double(a) (-(a)) + #ifdef __cplusplus + #define __Pyx_c_is_zero_double(z) ((z)==(double)0) + #define __Pyx_c_conj_double(z) (::std::conj(z)) + #if 1 + #define __Pyx_c_abs_double(z) (::std::abs(z)) + #define __Pyx_c_pow_double(a, b) (::std::pow(a, b)) + #endif + #else + #define __Pyx_c_is_zero_double(z) ((z)==0) + #define __Pyx_c_conj_double(z) (conj(z)) + #if 1 + #define __Pyx_c_abs_double(z) (cabs(z)) + #define __Pyx_c_pow_double(a, b) (cpow(a, b)) + #endif + #endif +#else + static CYTHON_INLINE int __Pyx_c_eq_double(__pyx_t_double_complex, __pyx_t_double_complex); + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_sum_double(__pyx_t_double_complex, __pyx_t_double_complex); + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_diff_double(__pyx_t_double_complex, __pyx_t_double_complex); + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_prod_double(__pyx_t_double_complex, __pyx_t_double_complex); + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_quot_double(__pyx_t_double_complex, __pyx_t_double_complex); + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_neg_double(__pyx_t_double_complex); + static CYTHON_INLINE int __Pyx_c_is_zero_double(__pyx_t_double_complex); + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_conj_double(__pyx_t_double_complex); + #if 1 + static CYTHON_INLINE double __Pyx_c_abs_double(__pyx_t_double_complex); + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_pow_double(__pyx_t_double_complex, __pyx_t_double_complex); + #endif +#endif + +/* CIntToPy.proto */ +static CYTHON_INLINE PyObject* __Pyx_PyInt_From_unsigned_int(unsigned int value); + +/* CIntFromPy.proto */ +static CYTHON_INLINE unsigned int __Pyx_PyInt_As_unsigned_int(PyObject *); + +/* CIntToPy.proto */ +static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value); + +/* CIntFromPy.proto */ +static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *); + +/* CIntFromPy.proto */ +static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *); + +/* FastTypeChecks.proto */ +#if CYTHON_COMPILING_IN_CPYTHON +#define __Pyx_TypeCheck(obj, type) __Pyx_IsSubtype(Py_TYPE(obj), (PyTypeObject *)type) +static CYTHON_INLINE int __Pyx_IsSubtype(PyTypeObject *a, PyTypeObject *b); +static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches(PyObject *err, PyObject *type); +static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObject *type1, PyObject *type2); +#else +#define __Pyx_TypeCheck(obj, type) PyObject_TypeCheck(obj, (PyTypeObject *)type) +#define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) +#define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) +#endif +#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) + +/* CheckBinaryVersion.proto */ +static int __Pyx_check_binary_version(void); + +/* InitStrings.proto */ +static int __Pyx_InitStrings(__Pyx_StringTabEntry *t); + + +/* Module declarations from 'cython' */ + +/* Module declarations from 'cpython.buffer' */ + +/* Module declarations from 'libc.string' */ + +/* Module declarations from 'libc.stdio' */ + +/* Module declarations from '__builtin__' */ + +/* Module declarations from 'cpython.type' */ +static PyTypeObject *__pyx_ptype_7cpython_4type_type = 0; + +/* Module declarations from 'cpython' */ + +/* Module declarations from 'cpython.object' */ + +/* Module declarations from 'cpython.ref' */ + +/* Module declarations from 'cpython.mem' */ + +/* Module declarations from 'numpy' */ + +/* Module declarations from 'numpy' */ +static PyTypeObject *__pyx_ptype_5numpy_dtype = 0; +static PyTypeObject *__pyx_ptype_5numpy_flatiter = 0; +static PyTypeObject *__pyx_ptype_5numpy_broadcast = 0; +static PyTypeObject *__pyx_ptype_5numpy_ndarray = 0; +static PyTypeObject *__pyx_ptype_5numpy_generic = 0; +static PyTypeObject *__pyx_ptype_5numpy_number = 0; +static PyTypeObject *__pyx_ptype_5numpy_integer = 0; +static PyTypeObject *__pyx_ptype_5numpy_signedinteger = 0; +static PyTypeObject *__pyx_ptype_5numpy_unsignedinteger = 0; +static PyTypeObject *__pyx_ptype_5numpy_inexact = 0; +static PyTypeObject *__pyx_ptype_5numpy_floating = 0; +static PyTypeObject *__pyx_ptype_5numpy_complexfloating = 0; +static PyTypeObject *__pyx_ptype_5numpy_flexible = 0; +static PyTypeObject *__pyx_ptype_5numpy_character = 0; +static PyTypeObject *__pyx_ptype_5numpy_ufunc = 0; + +/* Module declarations from 'cython_bbox' */ +static __Pyx_TypeInfo __Pyx_TypeInfo_nn___pyx_t_11cython_bbox_DTYPE_t = { "DTYPE_t", NULL, sizeof(__pyx_t_11cython_bbox_DTYPE_t), { 0 }, 0, 'R', 0, 0 }; +#define __Pyx_MODULE_NAME "cython_bbox" +extern int __pyx_module_is_main_cython_bbox; +int __pyx_module_is_main_cython_bbox = 0; + +/* Implementation of 'cython_bbox' */ +static PyObject *__pyx_builtin_range; +static PyObject *__pyx_builtin_ImportError; +static const char __pyx_k_K[] = "K"; +static const char __pyx_k_N[] = "N"; +static const char __pyx_k_k[] = "k"; +static const char __pyx_k_n[] = "n"; +static const char __pyx_k_ih[] = "ih"; +static const char __pyx_k_iw[] = "iw"; +static const char __pyx_k_np[] = "np"; +static const char __pyx_k_ua[] = "ua"; +static const char __pyx_k_main[] = "__main__"; +static const char __pyx_k_name[] = "__name__"; +static const char __pyx_k_test[] = "__test__"; +static const char __pyx_k_DTYPE[] = "DTYPE"; +static const char __pyx_k_boxes[] = "boxes"; +static const char __pyx_k_dtype[] = "dtype"; +static const char __pyx_k_float[] = "float"; +static const char __pyx_k_numpy[] = "numpy"; +static const char __pyx_k_range[] = "range"; +static const char __pyx_k_zeros[] = "zeros"; +static const char __pyx_k_import[] = "__import__"; +static const char __pyx_k_box_area[] = "box_area"; +static const char __pyx_k_overlaps[] = "overlaps"; +static const char __pyx_k_ImportError[] = "ImportError"; +static const char __pyx_k_cython_bbox[] = "cython_bbox"; +static const char __pyx_k_query_boxes[] = "query_boxes"; +static const char __pyx_k_bbox_overlaps[] = "bbox_overlaps"; +static const char __pyx_k_cline_in_traceback[] = "cline_in_traceback"; +static const char __pyx_k_src_cython_bbox_pyx[] = "src\\cython_bbox.pyx"; +static const char __pyx_k_numpy_core_multiarray_failed_to[] = "numpy.core.multiarray failed to import"; +static const char __pyx_k_numpy_core_umath_failed_to_impor[] = "numpy.core.umath failed to import"; +static PyObject *__pyx_n_s_DTYPE; +static PyObject *__pyx_n_s_ImportError; +static PyObject *__pyx_n_s_K; +static PyObject *__pyx_n_s_N; +static PyObject *__pyx_n_s_bbox_overlaps; +static PyObject *__pyx_n_s_box_area; +static PyObject *__pyx_n_s_boxes; +static PyObject *__pyx_n_s_cline_in_traceback; +static PyObject *__pyx_n_s_cython_bbox; +static PyObject *__pyx_n_s_dtype; +static PyObject *__pyx_n_s_float; +static PyObject *__pyx_n_s_ih; +static PyObject *__pyx_n_s_import; +static PyObject *__pyx_n_s_iw; +static PyObject *__pyx_n_s_k; +static PyObject *__pyx_n_s_main; +static PyObject *__pyx_n_s_n; +static PyObject *__pyx_n_s_name; +static PyObject *__pyx_n_s_np; +static PyObject *__pyx_n_s_numpy; +static PyObject *__pyx_kp_s_numpy_core_multiarray_failed_to; +static PyObject *__pyx_kp_s_numpy_core_umath_failed_to_impor; +static PyObject *__pyx_n_s_overlaps; +static PyObject *__pyx_n_s_query_boxes; +static PyObject *__pyx_n_s_range; +static PyObject *__pyx_kp_s_src_cython_bbox_pyx; +static PyObject *__pyx_n_s_test; +static PyObject *__pyx_n_s_ua; +static PyObject *__pyx_n_s_zeros; +static PyObject *__pyx_pf_11cython_bbox_bbox_overlaps(CYTHON_UNUSED PyObject *__pyx_self, PyArrayObject *__pyx_v_boxes, PyArrayObject *__pyx_v_query_boxes); /* proto */ +static PyObject *__pyx_tuple_; +static PyObject *__pyx_tuple__2; +static PyObject *__pyx_tuple__3; +static PyObject *__pyx_codeobj__4; +/* Late includes */ + +/* "cython_bbox.pyx":15 + * ctypedef np.float_t DTYPE_t + * + * def bbox_overlaps( # <<<<<<<<<<<<<< + * np.ndarray[DTYPE_t, ndim=2] boxes, + * np.ndarray[DTYPE_t, ndim=2] query_boxes): + */ + +/* Python wrapper */ +static PyObject *__pyx_pw_11cython_bbox_1bbox_overlaps(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ +static char __pyx_doc_11cython_bbox_bbox_overlaps[] = "\n Parameters\n ----------\n boxes: (N, 4) ndarray of float\n query_boxes: (K, 4) ndarray of float\n Returns\n -------\n overlaps: (N, K) ndarray of overlap between boxes and query_boxes\n "; +static PyMethodDef __pyx_mdef_11cython_bbox_1bbox_overlaps = {"bbox_overlaps", (PyCFunction)(void*)(PyCFunctionWithKeywords)__pyx_pw_11cython_bbox_1bbox_overlaps, METH_VARARGS|METH_KEYWORDS, __pyx_doc_11cython_bbox_bbox_overlaps}; +static PyObject *__pyx_pw_11cython_bbox_1bbox_overlaps(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { + PyArrayObject *__pyx_v_boxes = 0; + PyArrayObject *__pyx_v_query_boxes = 0; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + PyObject *__pyx_r = 0; + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("bbox_overlaps (wrapper)", 0); + { + static PyObject **__pyx_pyargnames[] = {&__pyx_n_s_boxes,&__pyx_n_s_query_boxes,0}; + PyObject* values[2] = {0,0}; + if (unlikely(__pyx_kwds)) { + Py_ssize_t kw_args; + const Py_ssize_t pos_args = PyTuple_GET_SIZE(__pyx_args); + switch (pos_args) { + case 2: values[1] = PyTuple_GET_ITEM(__pyx_args, 1); + CYTHON_FALLTHROUGH; + case 1: values[0] = PyTuple_GET_ITEM(__pyx_args, 0); + CYTHON_FALLTHROUGH; + case 0: break; + default: goto __pyx_L5_argtuple_error; + } + kw_args = PyDict_Size(__pyx_kwds); + switch (pos_args) { + case 0: + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_boxes)) != 0)) kw_args--; + else goto __pyx_L5_argtuple_error; + CYTHON_FALLTHROUGH; + case 1: + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_query_boxes)) != 0)) kw_args--; + else { + __Pyx_RaiseArgtupleInvalid("bbox_overlaps", 1, 2, 2, 1); __PYX_ERR(0, 15, __pyx_L3_error) + } + } + if (unlikely(kw_args > 0)) { + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "bbox_overlaps") < 0)) __PYX_ERR(0, 15, __pyx_L3_error) + } + } else if (PyTuple_GET_SIZE(__pyx_args) != 2) { + goto __pyx_L5_argtuple_error; + } else { + values[0] = PyTuple_GET_ITEM(__pyx_args, 0); + values[1] = PyTuple_GET_ITEM(__pyx_args, 1); + } + __pyx_v_boxes = ((PyArrayObject *)values[0]); + __pyx_v_query_boxes = ((PyArrayObject *)values[1]); + } + goto __pyx_L4_argument_unpacking_done; + __pyx_L5_argtuple_error:; + __Pyx_RaiseArgtupleInvalid("bbox_overlaps", 1, 2, 2, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 15, __pyx_L3_error) + __pyx_L3_error:; + __Pyx_AddTraceback("cython_bbox.bbox_overlaps", __pyx_clineno, __pyx_lineno, __pyx_filename); + __Pyx_RefNannyFinishContext(); + return NULL; + __pyx_L4_argument_unpacking_done:; + if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_boxes), __pyx_ptype_5numpy_ndarray, 1, "boxes", 0))) __PYX_ERR(0, 16, __pyx_L1_error) + if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_query_boxes), __pyx_ptype_5numpy_ndarray, 1, "query_boxes", 0))) __PYX_ERR(0, 17, __pyx_L1_error) + __pyx_r = __pyx_pf_11cython_bbox_bbox_overlaps(__pyx_self, __pyx_v_boxes, __pyx_v_query_boxes); + + /* function exit code */ + goto __pyx_L0; + __pyx_L1_error:; + __pyx_r = NULL; + __pyx_L0:; + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +static PyObject *__pyx_pf_11cython_bbox_bbox_overlaps(CYTHON_UNUSED PyObject *__pyx_self, PyArrayObject *__pyx_v_boxes, PyArrayObject *__pyx_v_query_boxes) { + unsigned int __pyx_v_N; + unsigned int __pyx_v_K; + PyArrayObject *__pyx_v_overlaps = 0; + __pyx_t_11cython_bbox_DTYPE_t __pyx_v_iw; + __pyx_t_11cython_bbox_DTYPE_t __pyx_v_ih; + __pyx_t_11cython_bbox_DTYPE_t __pyx_v_box_area; + __pyx_t_11cython_bbox_DTYPE_t __pyx_v_ua; + unsigned int __pyx_v_k; + unsigned int __pyx_v_n; + __Pyx_LocalBuf_ND __pyx_pybuffernd_boxes; + __Pyx_Buffer __pyx_pybuffer_boxes; + __Pyx_LocalBuf_ND __pyx_pybuffernd_overlaps; + __Pyx_Buffer __pyx_pybuffer_overlaps; + __Pyx_LocalBuf_ND __pyx_pybuffernd_query_boxes; + __Pyx_Buffer __pyx_pybuffer_query_boxes; + PyObject *__pyx_r = NULL; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + PyObject *__pyx_t_2 = NULL; + PyObject *__pyx_t_3 = NULL; + PyObject *__pyx_t_4 = NULL; + PyArrayObject *__pyx_t_5 = NULL; + unsigned int __pyx_t_6; + unsigned int __pyx_t_7; + unsigned int __pyx_t_8; + size_t __pyx_t_9; + Py_ssize_t __pyx_t_10; + int __pyx_t_11; + size_t __pyx_t_12; + Py_ssize_t __pyx_t_13; + size_t __pyx_t_14; + Py_ssize_t __pyx_t_15; + size_t __pyx_t_16; + Py_ssize_t __pyx_t_17; + unsigned int __pyx_t_18; + unsigned int __pyx_t_19; + unsigned int __pyx_t_20; + __pyx_t_11cython_bbox_DTYPE_t __pyx_t_21; + __pyx_t_11cython_bbox_DTYPE_t __pyx_t_22; + __pyx_t_11cython_bbox_DTYPE_t __pyx_t_23; + __pyx_t_11cython_bbox_DTYPE_t __pyx_t_24; + int __pyx_t_25; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("bbox_overlaps", 0); + __pyx_pybuffer_overlaps.pybuffer.buf = NULL; + __pyx_pybuffer_overlaps.refcount = 0; + __pyx_pybuffernd_overlaps.data = NULL; + __pyx_pybuffernd_overlaps.rcbuffer = &__pyx_pybuffer_overlaps; + __pyx_pybuffer_boxes.pybuffer.buf = NULL; + __pyx_pybuffer_boxes.refcount = 0; + __pyx_pybuffernd_boxes.data = NULL; + __pyx_pybuffernd_boxes.rcbuffer = &__pyx_pybuffer_boxes; + __pyx_pybuffer_query_boxes.pybuffer.buf = NULL; + __pyx_pybuffer_query_boxes.refcount = 0; + __pyx_pybuffernd_query_boxes.data = NULL; + __pyx_pybuffernd_query_boxes.rcbuffer = &__pyx_pybuffer_query_boxes; + { + __Pyx_BufFmt_StackElem __pyx_stack[1]; + if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_boxes.rcbuffer->pybuffer, (PyObject*)__pyx_v_boxes, &__Pyx_TypeInfo_nn___pyx_t_11cython_bbox_DTYPE_t, PyBUF_FORMAT| PyBUF_STRIDES, 2, 0, __pyx_stack) == -1)) __PYX_ERR(0, 15, __pyx_L1_error) + } + __pyx_pybuffernd_boxes.diminfo[0].strides = __pyx_pybuffernd_boxes.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_boxes.diminfo[0].shape = __pyx_pybuffernd_boxes.rcbuffer->pybuffer.shape[0]; __pyx_pybuffernd_boxes.diminfo[1].strides = __pyx_pybuffernd_boxes.rcbuffer->pybuffer.strides[1]; __pyx_pybuffernd_boxes.diminfo[1].shape = __pyx_pybuffernd_boxes.rcbuffer->pybuffer.shape[1]; + { + __Pyx_BufFmt_StackElem __pyx_stack[1]; + if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_query_boxes.rcbuffer->pybuffer, (PyObject*)__pyx_v_query_boxes, &__Pyx_TypeInfo_nn___pyx_t_11cython_bbox_DTYPE_t, PyBUF_FORMAT| PyBUF_STRIDES, 2, 0, __pyx_stack) == -1)) __PYX_ERR(0, 15, __pyx_L1_error) + } + __pyx_pybuffernd_query_boxes.diminfo[0].strides = __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_query_boxes.diminfo[0].shape = __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.shape[0]; __pyx_pybuffernd_query_boxes.diminfo[1].strides = __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.strides[1]; __pyx_pybuffernd_query_boxes.diminfo[1].shape = __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.shape[1]; + + /* "cython_bbox.pyx":27 + * overlaps: (N, K) ndarray of overlap between boxes and query_boxes + * """ + * cdef unsigned int N = boxes.shape[0] # <<<<<<<<<<<<<< + * cdef unsigned int K = query_boxes.shape[0] + * cdef np.ndarray[DTYPE_t, ndim=2] overlaps = np.zeros((N, K), dtype=DTYPE) + */ + __pyx_v_N = (__pyx_v_boxes->dimensions[0]); + + /* "cython_bbox.pyx":28 + * """ + * cdef unsigned int N = boxes.shape[0] + * cdef unsigned int K = query_boxes.shape[0] # <<<<<<<<<<<<<< + * cdef np.ndarray[DTYPE_t, ndim=2] overlaps = np.zeros((N, K), dtype=DTYPE) + * cdef DTYPE_t iw, ih, box_area + */ + __pyx_v_K = (__pyx_v_query_boxes->dimensions[0]); + + /* "cython_bbox.pyx":29 + * cdef unsigned int N = boxes.shape[0] + * cdef unsigned int K = query_boxes.shape[0] + * cdef np.ndarray[DTYPE_t, ndim=2] overlaps = np.zeros((N, K), dtype=DTYPE) # <<<<<<<<<<<<<< + * cdef DTYPE_t iw, ih, box_area + * cdef DTYPE_t ua + */ + __Pyx_GetModuleGlobalName(__pyx_t_1, __pyx_n_s_np); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_zeros); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_1 = __Pyx_PyInt_From_unsigned_int(__pyx_v_N); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_t_3 = __Pyx_PyInt_From_unsigned_int(__pyx_v_K); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_3); + __pyx_t_4 = PyTuple_New(2); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_4); + __Pyx_GIVEREF(__pyx_t_1); + PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_1); + __Pyx_GIVEREF(__pyx_t_3); + PyTuple_SET_ITEM(__pyx_t_4, 1, __pyx_t_3); + __pyx_t_1 = 0; + __pyx_t_3 = 0; + __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_3); + __Pyx_GIVEREF(__pyx_t_4); + PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_4); + __pyx_t_4 = 0; + __pyx_t_4 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_4); + __Pyx_GetModuleGlobalName(__pyx_t_1, __pyx_n_s_DTYPE); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_t_4, __pyx_n_s_dtype, __pyx_t_1) < 0) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_3, __pyx_t_4); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 29, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 29, __pyx_L1_error) + __pyx_t_5 = ((PyArrayObject *)__pyx_t_1); + { + __Pyx_BufFmt_StackElem __pyx_stack[1]; + if (unlikely(__Pyx_GetBufferAndValidate(&__pyx_pybuffernd_overlaps.rcbuffer->pybuffer, (PyObject*)__pyx_t_5, &__Pyx_TypeInfo_nn___pyx_t_11cython_bbox_DTYPE_t, PyBUF_FORMAT| PyBUF_STRIDES| PyBUF_WRITABLE, 2, 0, __pyx_stack) == -1)) { + __pyx_v_overlaps = ((PyArrayObject *)Py_None); __Pyx_INCREF(Py_None); __pyx_pybuffernd_overlaps.rcbuffer->pybuffer.buf = NULL; + __PYX_ERR(0, 29, __pyx_L1_error) + } else {__pyx_pybuffernd_overlaps.diminfo[0].strides = __pyx_pybuffernd_overlaps.rcbuffer->pybuffer.strides[0]; __pyx_pybuffernd_overlaps.diminfo[0].shape = __pyx_pybuffernd_overlaps.rcbuffer->pybuffer.shape[0]; __pyx_pybuffernd_overlaps.diminfo[1].strides = __pyx_pybuffernd_overlaps.rcbuffer->pybuffer.strides[1]; __pyx_pybuffernd_overlaps.diminfo[1].shape = __pyx_pybuffernd_overlaps.rcbuffer->pybuffer.shape[1]; + } + } + __pyx_t_5 = 0; + __pyx_v_overlaps = ((PyArrayObject *)__pyx_t_1); + __pyx_t_1 = 0; + + /* "cython_bbox.pyx":33 + * cdef DTYPE_t ua + * cdef unsigned int k, n + * for k in range(K): # <<<<<<<<<<<<<< + * box_area = ( + * (query_boxes[k, 2] - query_boxes[k, 0] + 1) * + */ + __pyx_t_6 = __pyx_v_K; + __pyx_t_7 = __pyx_t_6; + for (__pyx_t_8 = 0; __pyx_t_8 < __pyx_t_7; __pyx_t_8+=1) { + __pyx_v_k = __pyx_t_8; + + /* "cython_bbox.pyx":35 + * for k in range(K): + * box_area = ( + * (query_boxes[k, 2] - query_boxes[k, 0] + 1) * # <<<<<<<<<<<<<< + * (query_boxes[k, 3] - query_boxes[k, 1] + 1) + * ) + */ + __pyx_t_9 = __pyx_v_k; + __pyx_t_10 = 2; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_9 >= (size_t)__pyx_pybuffernd_query_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_10 < 0) { + __pyx_t_10 += __pyx_pybuffernd_query_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_10 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_10 >= __pyx_pybuffernd_query_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 35, __pyx_L1_error) + } + __pyx_t_12 = __pyx_v_k; + __pyx_t_13 = 0; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_12 >= (size_t)__pyx_pybuffernd_query_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_13 < 0) { + __pyx_t_13 += __pyx_pybuffernd_query_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_13 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_13 >= __pyx_pybuffernd_query_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 35, __pyx_L1_error) + } + + /* "cython_bbox.pyx":36 + * box_area = ( + * (query_boxes[k, 2] - query_boxes[k, 0] + 1) * + * (query_boxes[k, 3] - query_boxes[k, 1] + 1) # <<<<<<<<<<<<<< + * ) + * for n in range(N): + */ + __pyx_t_14 = __pyx_v_k; + __pyx_t_15 = 3; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_14 >= (size_t)__pyx_pybuffernd_query_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_15 < 0) { + __pyx_t_15 += __pyx_pybuffernd_query_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_15 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_15 >= __pyx_pybuffernd_query_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 36, __pyx_L1_error) + } + __pyx_t_16 = __pyx_v_k; + __pyx_t_17 = 1; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_query_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_query_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_query_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 36, __pyx_L1_error) + } + + /* "cython_bbox.pyx":35 + * for k in range(K): + * box_area = ( + * (query_boxes[k, 2] - query_boxes[k, 0] + 1) * # <<<<<<<<<<<<<< + * (query_boxes[k, 3] - query_boxes[k, 1] + 1) + * ) + */ + __pyx_v_box_area = ((((*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.buf, __pyx_t_9, __pyx_pybuffernd_query_boxes.diminfo[0].strides, __pyx_t_10, __pyx_pybuffernd_query_boxes.diminfo[1].strides)) - (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.buf, __pyx_t_12, __pyx_pybuffernd_query_boxes.diminfo[0].strides, __pyx_t_13, __pyx_pybuffernd_query_boxes.diminfo[1].strides))) + 1.0) * (((*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.buf, __pyx_t_14, __pyx_pybuffernd_query_boxes.diminfo[0].strides, __pyx_t_15, __pyx_pybuffernd_query_boxes.diminfo[1].strides)) - (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_query_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_query_boxes.diminfo[1].strides))) + 1.0)); + + /* "cython_bbox.pyx":38 + * (query_boxes[k, 3] - query_boxes[k, 1] + 1) + * ) + * for n in range(N): # <<<<<<<<<<<<<< + * iw = ( + * min(boxes[n, 2], query_boxes[k, 2]) - + */ + __pyx_t_18 = __pyx_v_N; + __pyx_t_19 = __pyx_t_18; + for (__pyx_t_20 = 0; __pyx_t_20 < __pyx_t_19; __pyx_t_20+=1) { + __pyx_v_n = __pyx_t_20; + + /* "cython_bbox.pyx":40 + * for n in range(N): + * iw = ( + * min(boxes[n, 2], query_boxes[k, 2]) - # <<<<<<<<<<<<<< + * max(boxes[n, 0], query_boxes[k, 0]) + 1 + * ) + */ + __pyx_t_16 = __pyx_v_k; + __pyx_t_17 = 2; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_query_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_query_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_query_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 40, __pyx_L1_error) + } + __pyx_t_21 = (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_query_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_query_boxes.diminfo[1].strides)); + __pyx_t_16 = __pyx_v_n; + __pyx_t_17 = 2; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 40, __pyx_L1_error) + } + __pyx_t_22 = (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_boxes.diminfo[1].strides)); + if (((__pyx_t_21 < __pyx_t_22) != 0)) { + __pyx_t_23 = __pyx_t_21; + } else { + __pyx_t_23 = __pyx_t_22; + } + + /* "cython_bbox.pyx":41 + * iw = ( + * min(boxes[n, 2], query_boxes[k, 2]) - + * max(boxes[n, 0], query_boxes[k, 0]) + 1 # <<<<<<<<<<<<<< + * ) + * if iw > 0: + */ + __pyx_t_16 = __pyx_v_k; + __pyx_t_17 = 0; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_query_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_query_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_query_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 41, __pyx_L1_error) + } + __pyx_t_21 = (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_query_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_query_boxes.diminfo[1].strides)); + __pyx_t_16 = __pyx_v_n; + __pyx_t_17 = 0; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 41, __pyx_L1_error) + } + __pyx_t_22 = (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_boxes.diminfo[1].strides)); + if (((__pyx_t_21 > __pyx_t_22) != 0)) { + __pyx_t_24 = __pyx_t_21; + } else { + __pyx_t_24 = __pyx_t_22; + } + + /* "cython_bbox.pyx":40 + * for n in range(N): + * iw = ( + * min(boxes[n, 2], query_boxes[k, 2]) - # <<<<<<<<<<<<<< + * max(boxes[n, 0], query_boxes[k, 0]) + 1 + * ) + */ + __pyx_v_iw = ((__pyx_t_23 - __pyx_t_24) + 1.0); + + /* "cython_bbox.pyx":43 + * max(boxes[n, 0], query_boxes[k, 0]) + 1 + * ) + * if iw > 0: # <<<<<<<<<<<<<< + * ih = ( + * min(boxes[n, 3], query_boxes[k, 3]) - + */ + __pyx_t_25 = ((__pyx_v_iw > 0.0) != 0); + if (__pyx_t_25) { + + /* "cython_bbox.pyx":45 + * if iw > 0: + * ih = ( + * min(boxes[n, 3], query_boxes[k, 3]) - # <<<<<<<<<<<<<< + * max(boxes[n, 1], query_boxes[k, 1]) + 1 + * ) + */ + __pyx_t_16 = __pyx_v_k; + __pyx_t_17 = 3; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_query_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_query_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_query_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 45, __pyx_L1_error) + } + __pyx_t_24 = (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_query_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_query_boxes.diminfo[1].strides)); + __pyx_t_16 = __pyx_v_n; + __pyx_t_17 = 3; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 45, __pyx_L1_error) + } + __pyx_t_23 = (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_boxes.diminfo[1].strides)); + if (((__pyx_t_24 < __pyx_t_23) != 0)) { + __pyx_t_21 = __pyx_t_24; + } else { + __pyx_t_21 = __pyx_t_23; + } + + /* "cython_bbox.pyx":46 + * ih = ( + * min(boxes[n, 3], query_boxes[k, 3]) - + * max(boxes[n, 1], query_boxes[k, 1]) + 1 # <<<<<<<<<<<<<< + * ) + * if ih > 0: + */ + __pyx_t_16 = __pyx_v_k; + __pyx_t_17 = 1; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_query_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_query_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_query_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 46, __pyx_L1_error) + } + __pyx_t_24 = (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_query_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_query_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_query_boxes.diminfo[1].strides)); + __pyx_t_16 = __pyx_v_n; + __pyx_t_17 = 1; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 46, __pyx_L1_error) + } + __pyx_t_23 = (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_boxes.diminfo[1].strides)); + if (((__pyx_t_24 > __pyx_t_23) != 0)) { + __pyx_t_22 = __pyx_t_24; + } else { + __pyx_t_22 = __pyx_t_23; + } + + /* "cython_bbox.pyx":45 + * if iw > 0: + * ih = ( + * min(boxes[n, 3], query_boxes[k, 3]) - # <<<<<<<<<<<<<< + * max(boxes[n, 1], query_boxes[k, 1]) + 1 + * ) + */ + __pyx_v_ih = ((__pyx_t_21 - __pyx_t_22) + 1.0); + + /* "cython_bbox.pyx":48 + * max(boxes[n, 1], query_boxes[k, 1]) + 1 + * ) + * if ih > 0: # <<<<<<<<<<<<<< + * ua = float( + * (boxes[n, 2] - boxes[n, 0] + 1) * + */ + __pyx_t_25 = ((__pyx_v_ih > 0.0) != 0); + if (__pyx_t_25) { + + /* "cython_bbox.pyx":50 + * if ih > 0: + * ua = float( + * (boxes[n, 2] - boxes[n, 0] + 1) * # <<<<<<<<<<<<<< + * (boxes[n, 3] - boxes[n, 1] + 1) + + * box_area - iw * ih + */ + __pyx_t_16 = __pyx_v_n; + __pyx_t_17 = 2; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_16 >= (size_t)__pyx_pybuffernd_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_17 < 0) { + __pyx_t_17 += __pyx_pybuffernd_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_17 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_17 >= __pyx_pybuffernd_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 50, __pyx_L1_error) + } + __pyx_t_14 = __pyx_v_n; + __pyx_t_15 = 0; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_14 >= (size_t)__pyx_pybuffernd_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_15 < 0) { + __pyx_t_15 += __pyx_pybuffernd_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_15 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_15 >= __pyx_pybuffernd_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 50, __pyx_L1_error) + } + + /* "cython_bbox.pyx":51 + * ua = float( + * (boxes[n, 2] - boxes[n, 0] + 1) * + * (boxes[n, 3] - boxes[n, 1] + 1) + # <<<<<<<<<<<<<< + * box_area - iw * ih + * ) + */ + __pyx_t_12 = __pyx_v_n; + __pyx_t_13 = 3; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_12 >= (size_t)__pyx_pybuffernd_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_13 < 0) { + __pyx_t_13 += __pyx_pybuffernd_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_13 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_13 >= __pyx_pybuffernd_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 51, __pyx_L1_error) + } + __pyx_t_9 = __pyx_v_n; + __pyx_t_10 = 1; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_9 >= (size_t)__pyx_pybuffernd_boxes.diminfo[0].shape)) __pyx_t_11 = 0; + if (__pyx_t_10 < 0) { + __pyx_t_10 += __pyx_pybuffernd_boxes.diminfo[1].shape; + if (unlikely(__pyx_t_10 < 0)) __pyx_t_11 = 1; + } else if (unlikely(__pyx_t_10 >= __pyx_pybuffernd_boxes.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 51, __pyx_L1_error) + } + + /* "cython_bbox.pyx":49 + * ) + * if ih > 0: + * ua = float( # <<<<<<<<<<<<<< + * (boxes[n, 2] - boxes[n, 0] + 1) * + * (boxes[n, 3] - boxes[n, 1] + 1) + + */ + __pyx_v_ua = ((double)((((((*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_boxes.rcbuffer->pybuffer.buf, __pyx_t_16, __pyx_pybuffernd_boxes.diminfo[0].strides, __pyx_t_17, __pyx_pybuffernd_boxes.diminfo[1].strides)) - (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_boxes.rcbuffer->pybuffer.buf, __pyx_t_14, __pyx_pybuffernd_boxes.diminfo[0].strides, __pyx_t_15, __pyx_pybuffernd_boxes.diminfo[1].strides))) + 1.0) * (((*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_boxes.rcbuffer->pybuffer.buf, __pyx_t_12, __pyx_pybuffernd_boxes.diminfo[0].strides, __pyx_t_13, __pyx_pybuffernd_boxes.diminfo[1].strides)) - (*__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_boxes.rcbuffer->pybuffer.buf, __pyx_t_9, __pyx_pybuffernd_boxes.diminfo[0].strides, __pyx_t_10, __pyx_pybuffernd_boxes.diminfo[1].strides))) + 1.0)) + __pyx_v_box_area) - (__pyx_v_iw * __pyx_v_ih))); + + /* "cython_bbox.pyx":54 + * box_area - iw * ih + * ) + * overlaps[n, k] = iw * ih / ua # <<<<<<<<<<<<<< + * return overlaps + */ + __pyx_t_22 = (__pyx_v_iw * __pyx_v_ih); + if (unlikely(__pyx_v_ua == 0)) { + PyErr_SetString(PyExc_ZeroDivisionError, "float division"); + __PYX_ERR(0, 54, __pyx_L1_error) + } + __pyx_t_9 = __pyx_v_n; + __pyx_t_12 = __pyx_v_k; + __pyx_t_11 = -1; + if (unlikely(__pyx_t_9 >= (size_t)__pyx_pybuffernd_overlaps.diminfo[0].shape)) __pyx_t_11 = 0; + if (unlikely(__pyx_t_12 >= (size_t)__pyx_pybuffernd_overlaps.diminfo[1].shape)) __pyx_t_11 = 1; + if (unlikely(__pyx_t_11 != -1)) { + __Pyx_RaiseBufferIndexError(__pyx_t_11); + __PYX_ERR(0, 54, __pyx_L1_error) + } + *__Pyx_BufPtrStrided2d(__pyx_t_11cython_bbox_DTYPE_t *, __pyx_pybuffernd_overlaps.rcbuffer->pybuffer.buf, __pyx_t_9, __pyx_pybuffernd_overlaps.diminfo[0].strides, __pyx_t_12, __pyx_pybuffernd_overlaps.diminfo[1].strides) = (__pyx_t_22 / __pyx_v_ua); + + /* "cython_bbox.pyx":48 + * max(boxes[n, 1], query_boxes[k, 1]) + 1 + * ) + * if ih > 0: # <<<<<<<<<<<<<< + * ua = float( + * (boxes[n, 2] - boxes[n, 0] + 1) * + */ + } + + /* "cython_bbox.pyx":43 + * max(boxes[n, 0], query_boxes[k, 0]) + 1 + * ) + * if iw > 0: # <<<<<<<<<<<<<< + * ih = ( + * min(boxes[n, 3], query_boxes[k, 3]) - + */ + } + } + } + + /* "cython_bbox.pyx":55 + * ) + * overlaps[n, k] = iw * ih / ua + * return overlaps # <<<<<<<<<<<<<< + */ + __Pyx_XDECREF(__pyx_r); + __Pyx_INCREF(((PyObject *)__pyx_v_overlaps)); + __pyx_r = ((PyObject *)__pyx_v_overlaps); + goto __pyx_L0; + + /* "cython_bbox.pyx":15 + * ctypedef np.float_t DTYPE_t + * + * def bbox_overlaps( # <<<<<<<<<<<<<< + * np.ndarray[DTYPE_t, ndim=2] boxes, + * np.ndarray[DTYPE_t, ndim=2] query_boxes): + */ + + /* function exit code */ + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_XDECREF(__pyx_t_2); + __Pyx_XDECREF(__pyx_t_3); + __Pyx_XDECREF(__pyx_t_4); + { PyObject *__pyx_type, *__pyx_value, *__pyx_tb; + __Pyx_PyThreadState_declare + __Pyx_PyThreadState_assign + __Pyx_ErrFetch(&__pyx_type, &__pyx_value, &__pyx_tb); + __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_boxes.rcbuffer->pybuffer); + __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_overlaps.rcbuffer->pybuffer); + __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_query_boxes.rcbuffer->pybuffer); + __Pyx_ErrRestore(__pyx_type, __pyx_value, __pyx_tb);} + __Pyx_AddTraceback("cython_bbox.bbox_overlaps", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = NULL; + goto __pyx_L2; + __pyx_L0:; + __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_boxes.rcbuffer->pybuffer); + __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_overlaps.rcbuffer->pybuffer); + __Pyx_SafeReleaseBuffer(&__pyx_pybuffernd_query_boxes.rcbuffer->pybuffer); + __pyx_L2:; + __Pyx_XDECREF((PyObject *)__pyx_v_overlaps); + __Pyx_XGIVEREF(__pyx_r); + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":735 + * ctypedef npy_cdouble complex_t + * + * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(1, a) + * + */ + +static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__pyx_v_a) { + PyObject *__pyx_r = NULL; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("PyArray_MultiIterNew1", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":736 + * + * cdef inline object PyArray_MultiIterNew1(a): + * return PyArray_MultiIterNew(1, a) # <<<<<<<<<<<<<< + * + * cdef inline object PyArray_MultiIterNew2(a, b): + */ + __Pyx_XDECREF(__pyx_r); + __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 736, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_r = __pyx_t_1; + __pyx_t_1 = 0; + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":735 + * ctypedef npy_cdouble complex_t + * + * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(1, a) + * + */ + + /* function exit code */ + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_AddTraceback("numpy.PyArray_MultiIterNew1", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = 0; + __pyx_L0:; + __Pyx_XGIVEREF(__pyx_r); + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":738 + * return PyArray_MultiIterNew(1, a) + * + * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(2, a, b) + * + */ + +static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__pyx_v_a, PyObject *__pyx_v_b) { + PyObject *__pyx_r = NULL; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("PyArray_MultiIterNew2", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":739 + * + * cdef inline object PyArray_MultiIterNew2(a, b): + * return PyArray_MultiIterNew(2, a, b) # <<<<<<<<<<<<<< + * + * cdef inline object PyArray_MultiIterNew3(a, b, c): + */ + __Pyx_XDECREF(__pyx_r); + __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 739, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_r = __pyx_t_1; + __pyx_t_1 = 0; + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":738 + * return PyArray_MultiIterNew(1, a) + * + * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(2, a, b) + * + */ + + /* function exit code */ + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_AddTraceback("numpy.PyArray_MultiIterNew2", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = 0; + __pyx_L0:; + __Pyx_XGIVEREF(__pyx_r); + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":741 + * return PyArray_MultiIterNew(2, a, b) + * + * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(3, a, b, c) + * + */ + +static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__pyx_v_a, PyObject *__pyx_v_b, PyObject *__pyx_v_c) { + PyObject *__pyx_r = NULL; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("PyArray_MultiIterNew3", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":742 + * + * cdef inline object PyArray_MultiIterNew3(a, b, c): + * return PyArray_MultiIterNew(3, a, b, c) # <<<<<<<<<<<<<< + * + * cdef inline object PyArray_MultiIterNew4(a, b, c, d): + */ + __Pyx_XDECREF(__pyx_r); + __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 742, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_r = __pyx_t_1; + __pyx_t_1 = 0; + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":741 + * return PyArray_MultiIterNew(2, a, b) + * + * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(3, a, b, c) + * + */ + + /* function exit code */ + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_AddTraceback("numpy.PyArray_MultiIterNew3", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = 0; + __pyx_L0:; + __Pyx_XGIVEREF(__pyx_r); + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":744 + * return PyArray_MultiIterNew(3, a, b, c) + * + * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(4, a, b, c, d) + * + */ + +static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__pyx_v_a, PyObject *__pyx_v_b, PyObject *__pyx_v_c, PyObject *__pyx_v_d) { + PyObject *__pyx_r = NULL; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("PyArray_MultiIterNew4", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":745 + * + * cdef inline object PyArray_MultiIterNew4(a, b, c, d): + * return PyArray_MultiIterNew(4, a, b, c, d) # <<<<<<<<<<<<<< + * + * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): + */ + __Pyx_XDECREF(__pyx_r); + __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 745, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_r = __pyx_t_1; + __pyx_t_1 = 0; + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":744 + * return PyArray_MultiIterNew(3, a, b, c) + * + * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(4, a, b, c, d) + * + */ + + /* function exit code */ + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_AddTraceback("numpy.PyArray_MultiIterNew4", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = 0; + __pyx_L0:; + __Pyx_XGIVEREF(__pyx_r); + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":747 + * return PyArray_MultiIterNew(4, a, b, c, d) + * + * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(5, a, b, c, d, e) + * + */ + +static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__pyx_v_a, PyObject *__pyx_v_b, PyObject *__pyx_v_c, PyObject *__pyx_v_d, PyObject *__pyx_v_e) { + PyObject *__pyx_r = NULL; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("PyArray_MultiIterNew5", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":748 + * + * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): + * return PyArray_MultiIterNew(5, a, b, c, d, e) # <<<<<<<<<<<<<< + * + * cdef inline tuple PyDataType_SHAPE(dtype d): + */ + __Pyx_XDECREF(__pyx_r); + __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 748, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_r = __pyx_t_1; + __pyx_t_1 = 0; + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":747 + * return PyArray_MultiIterNew(4, a, b, c, d) + * + * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< + * return PyArray_MultiIterNew(5, a, b, c, d, e) + * + */ + + /* function exit code */ + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_AddTraceback("numpy.PyArray_MultiIterNew5", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = 0; + __pyx_L0:; + __Pyx_XGIVEREF(__pyx_r); + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":750 + * return PyArray_MultiIterNew(5, a, b, c, d, e) + * + * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< + * if PyDataType_HASSUBARRAY(d): + * return d.subarray.shape + */ + +static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__pyx_v_d) { + PyObject *__pyx_r = NULL; + __Pyx_RefNannyDeclarations + int __pyx_t_1; + __Pyx_RefNannySetupContext("PyDataType_SHAPE", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":751 + * + * cdef inline tuple PyDataType_SHAPE(dtype d): + * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< + * return d.subarray.shape + * else: + */ + __pyx_t_1 = (PyDataType_HASSUBARRAY(__pyx_v_d) != 0); + if (__pyx_t_1) { + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":752 + * cdef inline tuple PyDataType_SHAPE(dtype d): + * if PyDataType_HASSUBARRAY(d): + * return d.subarray.shape # <<<<<<<<<<<<<< + * else: + * return () + */ + __Pyx_XDECREF(__pyx_r); + __Pyx_INCREF(((PyObject*)__pyx_v_d->subarray->shape)); + __pyx_r = ((PyObject*)__pyx_v_d->subarray->shape); + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":751 + * + * cdef inline tuple PyDataType_SHAPE(dtype d): + * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< + * return d.subarray.shape + * else: + */ + } + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":754 + * return d.subarray.shape + * else: + * return () # <<<<<<<<<<<<<< + * + * + */ + /*else*/ { + __Pyx_XDECREF(__pyx_r); + __Pyx_INCREF(__pyx_empty_tuple); + __pyx_r = __pyx_empty_tuple; + goto __pyx_L0; + } + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":750 + * return PyArray_MultiIterNew(5, a, b, c, d, e) + * + * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< + * if PyDataType_HASSUBARRAY(d): + * return d.subarray.shape + */ + + /* function exit code */ + __pyx_L0:; + __Pyx_XGIVEREF(__pyx_r); + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":929 + * int _import_umath() except -1 + * + * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< + * Py_INCREF(base) # important to do this before stealing the reference below! + * PyArray_SetBaseObject(arr, base) + */ + +static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_arr, PyObject *__pyx_v_base) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("set_array_base", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":930 + * + * cdef inline void set_array_base(ndarray arr, object base): + * Py_INCREF(base) # important to do this before stealing the reference below! # <<<<<<<<<<<<<< + * PyArray_SetBaseObject(arr, base) + * + */ + Py_INCREF(__pyx_v_base); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":931 + * cdef inline void set_array_base(ndarray arr, object base): + * Py_INCREF(base) # important to do this before stealing the reference below! + * PyArray_SetBaseObject(arr, base) # <<<<<<<<<<<<<< + * + * cdef inline object get_array_base(ndarray arr): + */ + (void)(PyArray_SetBaseObject(__pyx_v_arr, __pyx_v_base)); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":929 + * int _import_umath() except -1 + * + * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< + * Py_INCREF(base) # important to do this before stealing the reference below! + * PyArray_SetBaseObject(arr, base) + */ + + /* function exit code */ + __Pyx_RefNannyFinishContext(); +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":933 + * PyArray_SetBaseObject(arr, base) + * + * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< + * base = PyArray_BASE(arr) + * if base is NULL: + */ + +static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__pyx_v_arr) { + PyObject *__pyx_v_base; + PyObject *__pyx_r = NULL; + __Pyx_RefNannyDeclarations + int __pyx_t_1; + __Pyx_RefNannySetupContext("get_array_base", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":934 + * + * cdef inline object get_array_base(ndarray arr): + * base = PyArray_BASE(arr) # <<<<<<<<<<<<<< + * if base is NULL: + * return None + */ + __pyx_v_base = PyArray_BASE(__pyx_v_arr); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":935 + * cdef inline object get_array_base(ndarray arr): + * base = PyArray_BASE(arr) + * if base is NULL: # <<<<<<<<<<<<<< + * return None + * return base + */ + __pyx_t_1 = ((__pyx_v_base == NULL) != 0); + if (__pyx_t_1) { + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":936 + * base = PyArray_BASE(arr) + * if base is NULL: + * return None # <<<<<<<<<<<<<< + * return base + * + */ + __Pyx_XDECREF(__pyx_r); + __pyx_r = Py_None; __Pyx_INCREF(Py_None); + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":935 + * cdef inline object get_array_base(ndarray arr): + * base = PyArray_BASE(arr) + * if base is NULL: # <<<<<<<<<<<<<< + * return None + * return base + */ + } + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":937 + * if base is NULL: + * return None + * return base # <<<<<<<<<<<<<< + * + * # Versions of the import_* functions which are more suitable for + */ + __Pyx_XDECREF(__pyx_r); + __Pyx_INCREF(((PyObject *)__pyx_v_base)); + __pyx_r = ((PyObject *)__pyx_v_base); + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":933 + * PyArray_SetBaseObject(arr, base) + * + * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< + * base = PyArray_BASE(arr) + * if base is NULL: + */ + + /* function exit code */ + __pyx_L0:; + __Pyx_XGIVEREF(__pyx_r); + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":941 + * # Versions of the import_* functions which are more suitable for + * # Cython code. + * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< + * try: + * __pyx_import_array() + */ + +static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { + int __pyx_r; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + PyObject *__pyx_t_2 = NULL; + PyObject *__pyx_t_3 = NULL; + int __pyx_t_4; + PyObject *__pyx_t_5 = NULL; + PyObject *__pyx_t_6 = NULL; + PyObject *__pyx_t_7 = NULL; + PyObject *__pyx_t_8 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("import_array", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":942 + * # Cython code. + * cdef inline int import_array() except -1: + * try: # <<<<<<<<<<<<<< + * __pyx_import_array() + * except Exception: + */ + { + __Pyx_PyThreadState_declare + __Pyx_PyThreadState_assign + __Pyx_ExceptionSave(&__pyx_t_1, &__pyx_t_2, &__pyx_t_3); + __Pyx_XGOTREF(__pyx_t_1); + __Pyx_XGOTREF(__pyx_t_2); + __Pyx_XGOTREF(__pyx_t_3); + /*try:*/ { + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":943 + * cdef inline int import_array() except -1: + * try: + * __pyx_import_array() # <<<<<<<<<<<<<< + * except Exception: + * raise ImportError("numpy.core.multiarray failed to import") + */ + __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 943, __pyx_L3_error) + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":942 + * # Cython code. + * cdef inline int import_array() except -1: + * try: # <<<<<<<<<<<<<< + * __pyx_import_array() + * except Exception: + */ + } + __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; + goto __pyx_L8_try_end; + __pyx_L3_error:; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":944 + * try: + * __pyx_import_array() + * except Exception: # <<<<<<<<<<<<<< + * raise ImportError("numpy.core.multiarray failed to import") + * + */ + __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); + if (__pyx_t_4) { + __Pyx_AddTraceback("numpy.import_array", __pyx_clineno, __pyx_lineno, __pyx_filename); + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 944, __pyx_L5_except_error) + __Pyx_GOTREF(__pyx_t_5); + __Pyx_GOTREF(__pyx_t_6); + __Pyx_GOTREF(__pyx_t_7); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":945 + * __pyx_import_array() + * except Exception: + * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< + * + * cdef inline int import_umath() except -1: + */ + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 945, __pyx_L5_except_error) + __Pyx_GOTREF(__pyx_t_8); + __Pyx_Raise(__pyx_t_8, 0, 0, 0); + __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; + __PYX_ERR(1, 945, __pyx_L5_except_error) + } + goto __pyx_L5_except_error; + __pyx_L5_except_error:; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":942 + * # Cython code. + * cdef inline int import_array() except -1: + * try: # <<<<<<<<<<<<<< + * __pyx_import_array() + * except Exception: + */ + __Pyx_XGIVEREF(__pyx_t_1); + __Pyx_XGIVEREF(__pyx_t_2); + __Pyx_XGIVEREF(__pyx_t_3); + __Pyx_ExceptionReset(__pyx_t_1, __pyx_t_2, __pyx_t_3); + goto __pyx_L1_error; + __pyx_L8_try_end:; + } + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":941 + * # Versions of the import_* functions which are more suitable for + * # Cython code. + * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< + * try: + * __pyx_import_array() + */ + + /* function exit code */ + __pyx_r = 0; + goto __pyx_L0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_5); + __Pyx_XDECREF(__pyx_t_6); + __Pyx_XDECREF(__pyx_t_7); + __Pyx_XDECREF(__pyx_t_8); + __Pyx_AddTraceback("numpy.import_array", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = -1; + __pyx_L0:; + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":947 + * raise ImportError("numpy.core.multiarray failed to import") + * + * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< + * try: + * _import_umath() + */ + +static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { + int __pyx_r; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + PyObject *__pyx_t_2 = NULL; + PyObject *__pyx_t_3 = NULL; + int __pyx_t_4; + PyObject *__pyx_t_5 = NULL; + PyObject *__pyx_t_6 = NULL; + PyObject *__pyx_t_7 = NULL; + PyObject *__pyx_t_8 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("import_umath", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":948 + * + * cdef inline int import_umath() except -1: + * try: # <<<<<<<<<<<<<< + * _import_umath() + * except Exception: + */ + { + __Pyx_PyThreadState_declare + __Pyx_PyThreadState_assign + __Pyx_ExceptionSave(&__pyx_t_1, &__pyx_t_2, &__pyx_t_3); + __Pyx_XGOTREF(__pyx_t_1); + __Pyx_XGOTREF(__pyx_t_2); + __Pyx_XGOTREF(__pyx_t_3); + /*try:*/ { + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":949 + * cdef inline int import_umath() except -1: + * try: + * _import_umath() # <<<<<<<<<<<<<< + * except Exception: + * raise ImportError("numpy.core.umath failed to import") + */ + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 949, __pyx_L3_error) + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":948 + * + * cdef inline int import_umath() except -1: + * try: # <<<<<<<<<<<<<< + * _import_umath() + * except Exception: + */ + } + __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; + goto __pyx_L8_try_end; + __pyx_L3_error:; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":950 + * try: + * _import_umath() + * except Exception: # <<<<<<<<<<<<<< + * raise ImportError("numpy.core.umath failed to import") + * + */ + __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); + if (__pyx_t_4) { + __Pyx_AddTraceback("numpy.import_umath", __pyx_clineno, __pyx_lineno, __pyx_filename); + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 950, __pyx_L5_except_error) + __Pyx_GOTREF(__pyx_t_5); + __Pyx_GOTREF(__pyx_t_6); + __Pyx_GOTREF(__pyx_t_7); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":951 + * _import_umath() + * except Exception: + * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< + * + * cdef inline int import_ufunc() except -1: + */ + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 951, __pyx_L5_except_error) + __Pyx_GOTREF(__pyx_t_8); + __Pyx_Raise(__pyx_t_8, 0, 0, 0); + __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; + __PYX_ERR(1, 951, __pyx_L5_except_error) + } + goto __pyx_L5_except_error; + __pyx_L5_except_error:; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":948 + * + * cdef inline int import_umath() except -1: + * try: # <<<<<<<<<<<<<< + * _import_umath() + * except Exception: + */ + __Pyx_XGIVEREF(__pyx_t_1); + __Pyx_XGIVEREF(__pyx_t_2); + __Pyx_XGIVEREF(__pyx_t_3); + __Pyx_ExceptionReset(__pyx_t_1, __pyx_t_2, __pyx_t_3); + goto __pyx_L1_error; + __pyx_L8_try_end:; + } + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":947 + * raise ImportError("numpy.core.multiarray failed to import") + * + * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< + * try: + * _import_umath() + */ + + /* function exit code */ + __pyx_r = 0; + goto __pyx_L0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_5); + __Pyx_XDECREF(__pyx_t_6); + __Pyx_XDECREF(__pyx_t_7); + __Pyx_XDECREF(__pyx_t_8); + __Pyx_AddTraceback("numpy.import_umath", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = -1; + __pyx_L0:; + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":953 + * raise ImportError("numpy.core.umath failed to import") + * + * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< + * try: + * _import_umath() + */ + +static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { + int __pyx_r; + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + PyObject *__pyx_t_2 = NULL; + PyObject *__pyx_t_3 = NULL; + int __pyx_t_4; + PyObject *__pyx_t_5 = NULL; + PyObject *__pyx_t_6 = NULL; + PyObject *__pyx_t_7 = NULL; + PyObject *__pyx_t_8 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("import_ufunc", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":954 + * + * cdef inline int import_ufunc() except -1: + * try: # <<<<<<<<<<<<<< + * _import_umath() + * except Exception: + */ + { + __Pyx_PyThreadState_declare + __Pyx_PyThreadState_assign + __Pyx_ExceptionSave(&__pyx_t_1, &__pyx_t_2, &__pyx_t_3); + __Pyx_XGOTREF(__pyx_t_1); + __Pyx_XGOTREF(__pyx_t_2); + __Pyx_XGOTREF(__pyx_t_3); + /*try:*/ { + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":955 + * cdef inline int import_ufunc() except -1: + * try: + * _import_umath() # <<<<<<<<<<<<<< + * except Exception: + * raise ImportError("numpy.core.umath failed to import") + */ + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 955, __pyx_L3_error) + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":954 + * + * cdef inline int import_ufunc() except -1: + * try: # <<<<<<<<<<<<<< + * _import_umath() + * except Exception: + */ + } + __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; + goto __pyx_L8_try_end; + __pyx_L3_error:; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":956 + * try: + * _import_umath() + * except Exception: # <<<<<<<<<<<<<< + * raise ImportError("numpy.core.umath failed to import") + * + */ + __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); + if (__pyx_t_4) { + __Pyx_AddTraceback("numpy.import_ufunc", __pyx_clineno, __pyx_lineno, __pyx_filename); + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 956, __pyx_L5_except_error) + __Pyx_GOTREF(__pyx_t_5); + __Pyx_GOTREF(__pyx_t_6); + __Pyx_GOTREF(__pyx_t_7); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":957 + * _import_umath() + * except Exception: + * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< + * + * cdef extern from *: + */ + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 957, __pyx_L5_except_error) + __Pyx_GOTREF(__pyx_t_8); + __Pyx_Raise(__pyx_t_8, 0, 0, 0); + __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; + __PYX_ERR(1, 957, __pyx_L5_except_error) + } + goto __pyx_L5_except_error; + __pyx_L5_except_error:; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":954 + * + * cdef inline int import_ufunc() except -1: + * try: # <<<<<<<<<<<<<< + * _import_umath() + * except Exception: + */ + __Pyx_XGIVEREF(__pyx_t_1); + __Pyx_XGIVEREF(__pyx_t_2); + __Pyx_XGIVEREF(__pyx_t_3); + __Pyx_ExceptionReset(__pyx_t_1, __pyx_t_2, __pyx_t_3); + goto __pyx_L1_error; + __pyx_L8_try_end:; + } + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":953 + * raise ImportError("numpy.core.umath failed to import") + * + * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< + * try: + * _import_umath() + */ + + /* function exit code */ + __pyx_r = 0; + goto __pyx_L0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_5); + __Pyx_XDECREF(__pyx_t_6); + __Pyx_XDECREF(__pyx_t_7); + __Pyx_XDECREF(__pyx_t_8); + __Pyx_AddTraceback("numpy.import_ufunc", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = -1; + __pyx_L0:; + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":967 + * + * + * cdef inline bint is_timedelta64_object(object obj): # <<<<<<<<<<<<<< + * """ + * Cython equivalent of `isinstance(obj, np.timedelta64)` + */ + +static CYTHON_INLINE int __pyx_f_5numpy_is_timedelta64_object(PyObject *__pyx_v_obj) { + int __pyx_r; + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("is_timedelta64_object", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":979 + * bool + * """ + * return PyObject_TypeCheck(obj, &PyTimedeltaArrType_Type) # <<<<<<<<<<<<<< + * + * + */ + __pyx_r = PyObject_TypeCheck(__pyx_v_obj, (&PyTimedeltaArrType_Type)); + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":967 + * + * + * cdef inline bint is_timedelta64_object(object obj): # <<<<<<<<<<<<<< + * """ + * Cython equivalent of `isinstance(obj, np.timedelta64)` + */ + + /* function exit code */ + __pyx_L0:; + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":982 + * + * + * cdef inline bint is_datetime64_object(object obj): # <<<<<<<<<<<<<< + * """ + * Cython equivalent of `isinstance(obj, np.datetime64)` + */ + +static CYTHON_INLINE int __pyx_f_5numpy_is_datetime64_object(PyObject *__pyx_v_obj) { + int __pyx_r; + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("is_datetime64_object", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":994 + * bool + * """ + * return PyObject_TypeCheck(obj, &PyDatetimeArrType_Type) # <<<<<<<<<<<<<< + * + * + */ + __pyx_r = PyObject_TypeCheck(__pyx_v_obj, (&PyDatetimeArrType_Type)); + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":982 + * + * + * cdef inline bint is_datetime64_object(object obj): # <<<<<<<<<<<<<< + * """ + * Cython equivalent of `isinstance(obj, np.datetime64)` + */ + + /* function exit code */ + __pyx_L0:; + __Pyx_RefNannyFinishContext(); + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":997 + * + * + * cdef inline npy_datetime get_datetime64_value(object obj) nogil: # <<<<<<<<<<<<<< + * """ + * returns the int64 value underlying scalar numpy datetime64 object + */ + +static CYTHON_INLINE npy_datetime __pyx_f_5numpy_get_datetime64_value(PyObject *__pyx_v_obj) { + npy_datetime __pyx_r; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":1004 + * also needed. That can be found using `get_datetime64_unit`. + * """ + * return (obj).obval # <<<<<<<<<<<<<< + * + * + */ + __pyx_r = ((PyDatetimeScalarObject *)__pyx_v_obj)->obval; + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":997 + * + * + * cdef inline npy_datetime get_datetime64_value(object obj) nogil: # <<<<<<<<<<<<<< + * """ + * returns the int64 value underlying scalar numpy datetime64 object + */ + + /* function exit code */ + __pyx_L0:; + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":1007 + * + * + * cdef inline npy_timedelta get_timedelta64_value(object obj) nogil: # <<<<<<<<<<<<<< + * """ + * returns the int64 value underlying scalar numpy timedelta64 object + */ + +static CYTHON_INLINE npy_timedelta __pyx_f_5numpy_get_timedelta64_value(PyObject *__pyx_v_obj) { + npy_timedelta __pyx_r; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":1011 + * returns the int64 value underlying scalar numpy timedelta64 object + * """ + * return (obj).obval # <<<<<<<<<<<<<< + * + * + */ + __pyx_r = ((PyTimedeltaScalarObject *)__pyx_v_obj)->obval; + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":1007 + * + * + * cdef inline npy_timedelta get_timedelta64_value(object obj) nogil: # <<<<<<<<<<<<<< + * """ + * returns the int64 value underlying scalar numpy timedelta64 object + */ + + /* function exit code */ + __pyx_L0:; + return __pyx_r; +} + +/* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":1014 + * + * + * cdef inline NPY_DATETIMEUNIT get_datetime64_unit(object obj) nogil: # <<<<<<<<<<<<<< + * """ + * returns the unit part of the dtype for a numpy datetime64 object. + */ + +static CYTHON_INLINE NPY_DATETIMEUNIT __pyx_f_5numpy_get_datetime64_unit(PyObject *__pyx_v_obj) { + NPY_DATETIMEUNIT __pyx_r; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":1018 + * returns the unit part of the dtype for a numpy datetime64 object. + * """ + * return (obj).obmeta.base # <<<<<<<<<<<<<< + */ + __pyx_r = ((NPY_DATETIMEUNIT)((PyDatetimeScalarObject *)__pyx_v_obj)->obmeta.base); + goto __pyx_L0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":1014 + * + * + * cdef inline NPY_DATETIMEUNIT get_datetime64_unit(object obj) nogil: # <<<<<<<<<<<<<< + * """ + * returns the unit part of the dtype for a numpy datetime64 object. + */ + + /* function exit code */ + __pyx_L0:; + return __pyx_r; +} + +static PyMethodDef __pyx_methods[] = { + {0, 0, 0, 0} +}; + +#if PY_MAJOR_VERSION >= 3 +#if CYTHON_PEP489_MULTI_PHASE_INIT +static PyObject* __pyx_pymod_create(PyObject *spec, PyModuleDef *def); /*proto*/ +static int __pyx_pymod_exec_cython_bbox(PyObject* module); /*proto*/ +static PyModuleDef_Slot __pyx_moduledef_slots[] = { + {Py_mod_create, (void*)__pyx_pymod_create}, + {Py_mod_exec, (void*)__pyx_pymod_exec_cython_bbox}, + {0, NULL} +}; +#endif + +static struct PyModuleDef __pyx_moduledef = { + PyModuleDef_HEAD_INIT, + "cython_bbox", + 0, /* m_doc */ + #if CYTHON_PEP489_MULTI_PHASE_INIT + 0, /* m_size */ + #else + -1, /* m_size */ + #endif + __pyx_methods /* m_methods */, + #if CYTHON_PEP489_MULTI_PHASE_INIT + __pyx_moduledef_slots, /* m_slots */ + #else + NULL, /* m_reload */ + #endif + NULL, /* m_traverse */ + NULL, /* m_clear */ + NULL /* m_free */ +}; +#endif +#ifndef CYTHON_SMALL_CODE +#if defined(__clang__) + #define CYTHON_SMALL_CODE +#elif defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3)) + #define CYTHON_SMALL_CODE __attribute__((cold)) +#else + #define CYTHON_SMALL_CODE +#endif +#endif + +static __Pyx_StringTabEntry __pyx_string_tab[] = { + {&__pyx_n_s_DTYPE, __pyx_k_DTYPE, sizeof(__pyx_k_DTYPE), 0, 0, 1, 1}, + {&__pyx_n_s_ImportError, __pyx_k_ImportError, sizeof(__pyx_k_ImportError), 0, 0, 1, 1}, + {&__pyx_n_s_K, __pyx_k_K, sizeof(__pyx_k_K), 0, 0, 1, 1}, + {&__pyx_n_s_N, __pyx_k_N, sizeof(__pyx_k_N), 0, 0, 1, 1}, + {&__pyx_n_s_bbox_overlaps, __pyx_k_bbox_overlaps, sizeof(__pyx_k_bbox_overlaps), 0, 0, 1, 1}, + {&__pyx_n_s_box_area, __pyx_k_box_area, sizeof(__pyx_k_box_area), 0, 0, 1, 1}, + {&__pyx_n_s_boxes, __pyx_k_boxes, sizeof(__pyx_k_boxes), 0, 0, 1, 1}, + {&__pyx_n_s_cline_in_traceback, __pyx_k_cline_in_traceback, sizeof(__pyx_k_cline_in_traceback), 0, 0, 1, 1}, + {&__pyx_n_s_cython_bbox, __pyx_k_cython_bbox, sizeof(__pyx_k_cython_bbox), 0, 0, 1, 1}, + {&__pyx_n_s_dtype, __pyx_k_dtype, sizeof(__pyx_k_dtype), 0, 0, 1, 1}, + {&__pyx_n_s_float, __pyx_k_float, sizeof(__pyx_k_float), 0, 0, 1, 1}, + {&__pyx_n_s_ih, __pyx_k_ih, sizeof(__pyx_k_ih), 0, 0, 1, 1}, + {&__pyx_n_s_import, __pyx_k_import, sizeof(__pyx_k_import), 0, 0, 1, 1}, + {&__pyx_n_s_iw, __pyx_k_iw, sizeof(__pyx_k_iw), 0, 0, 1, 1}, + {&__pyx_n_s_k, __pyx_k_k, sizeof(__pyx_k_k), 0, 0, 1, 1}, + {&__pyx_n_s_main, __pyx_k_main, sizeof(__pyx_k_main), 0, 0, 1, 1}, + {&__pyx_n_s_n, __pyx_k_n, sizeof(__pyx_k_n), 0, 0, 1, 1}, + {&__pyx_n_s_name, __pyx_k_name, sizeof(__pyx_k_name), 0, 0, 1, 1}, + {&__pyx_n_s_np, __pyx_k_np, sizeof(__pyx_k_np), 0, 0, 1, 1}, + {&__pyx_n_s_numpy, __pyx_k_numpy, sizeof(__pyx_k_numpy), 0, 0, 1, 1}, + {&__pyx_kp_s_numpy_core_multiarray_failed_to, __pyx_k_numpy_core_multiarray_failed_to, sizeof(__pyx_k_numpy_core_multiarray_failed_to), 0, 0, 1, 0}, + {&__pyx_kp_s_numpy_core_umath_failed_to_impor, __pyx_k_numpy_core_umath_failed_to_impor, sizeof(__pyx_k_numpy_core_umath_failed_to_impor), 0, 0, 1, 0}, + {&__pyx_n_s_overlaps, __pyx_k_overlaps, sizeof(__pyx_k_overlaps), 0, 0, 1, 1}, + {&__pyx_n_s_query_boxes, __pyx_k_query_boxes, sizeof(__pyx_k_query_boxes), 0, 0, 1, 1}, + {&__pyx_n_s_range, __pyx_k_range, sizeof(__pyx_k_range), 0, 0, 1, 1}, + {&__pyx_kp_s_src_cython_bbox_pyx, __pyx_k_src_cython_bbox_pyx, sizeof(__pyx_k_src_cython_bbox_pyx), 0, 0, 1, 0}, + {&__pyx_n_s_test, __pyx_k_test, sizeof(__pyx_k_test), 0, 0, 1, 1}, + {&__pyx_n_s_ua, __pyx_k_ua, sizeof(__pyx_k_ua), 0, 0, 1, 1}, + {&__pyx_n_s_zeros, __pyx_k_zeros, sizeof(__pyx_k_zeros), 0, 0, 1, 1}, + {0, 0, 0, 0, 0, 0, 0} +}; +static CYTHON_SMALL_CODE int __Pyx_InitCachedBuiltins(void) { + __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) __PYX_ERR(0, 33, __pyx_L1_error) + __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(1, 945, __pyx_L1_error) + return 0; + __pyx_L1_error:; + return -1; +} + +static CYTHON_SMALL_CODE int __Pyx_InitCachedConstants(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":945 + * __pyx_import_array() + * except Exception: + * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< + * + * cdef inline int import_umath() except -1: + */ + __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple_)) __PYX_ERR(1, 945, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple_); + __Pyx_GIVEREF(__pyx_tuple_); + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":951 + * _import_umath() + * except Exception: + * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< + * + * cdef inline int import_ufunc() except -1: + */ + __pyx_tuple__2 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__2)) __PYX_ERR(1, 951, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__2); + __Pyx_GIVEREF(__pyx_tuple__2); + + /* "cython_bbox.pyx":15 + * ctypedef np.float_t DTYPE_t + * + * def bbox_overlaps( # <<<<<<<<<<<<<< + * np.ndarray[DTYPE_t, ndim=2] boxes, + * np.ndarray[DTYPE_t, ndim=2] query_boxes): + */ + __pyx_tuple__3 = PyTuple_Pack(11, __pyx_n_s_boxes, __pyx_n_s_query_boxes, __pyx_n_s_N, __pyx_n_s_K, __pyx_n_s_overlaps, __pyx_n_s_iw, __pyx_n_s_ih, __pyx_n_s_box_area, __pyx_n_s_ua, __pyx_n_s_k, __pyx_n_s_n); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__3); + __Pyx_GIVEREF(__pyx_tuple__3); + __pyx_codeobj__4 = (PyObject*)__Pyx_PyCode_New(2, 0, 11, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__3, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_src_cython_bbox_pyx, __pyx_n_s_bbox_overlaps, 15, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__4)) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static CYTHON_SMALL_CODE int __Pyx_InitGlobals(void) { + if (__Pyx_InitStrings(__pyx_string_tab) < 0) __PYX_ERR(0, 1, __pyx_L1_error); + return 0; + __pyx_L1_error:; + return -1; +} + +static CYTHON_SMALL_CODE int __Pyx_modinit_global_init_code(void); /*proto*/ +static CYTHON_SMALL_CODE int __Pyx_modinit_variable_export_code(void); /*proto*/ +static CYTHON_SMALL_CODE int __Pyx_modinit_function_export_code(void); /*proto*/ +static CYTHON_SMALL_CODE int __Pyx_modinit_type_init_code(void); /*proto*/ +static CYTHON_SMALL_CODE int __Pyx_modinit_type_import_code(void); /*proto*/ +static CYTHON_SMALL_CODE int __Pyx_modinit_variable_import_code(void); /*proto*/ +static CYTHON_SMALL_CODE int __Pyx_modinit_function_import_code(void); /*proto*/ + +static int __Pyx_modinit_global_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_global_init_code", 0); + /*--- Global init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_export_code", 0); + /*--- Variable export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_export_code", 0); + /*--- Function export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_init_code", 0); + /*--- Type init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_import_code(void) { + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannySetupContext("__Pyx_modinit_type_import_code", 0); + /*--- Type import code ---*/ + __pyx_t_1 = PyImport_ImportModule(__Pyx_BUILTIN_MODULE_NAME); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 9, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__pyx_t_1, __Pyx_BUILTIN_MODULE_NAME, "type", + #if defined(PYPY_VERSION_NUM) && PYPY_VERSION_NUM < 0x050B0000 + sizeof(PyTypeObject), + #else + sizeof(PyHeapTypeObject), + #endif + __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_7cpython_4type_type) __PYX_ERR(2, 9, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_1 = PyImport_ImportModule("numpy"); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 200, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_ptype_5numpy_dtype = __Pyx_ImportType(__pyx_t_1, "numpy", "dtype", sizeof(PyArray_Descr), __Pyx_ImportType_CheckSize_Ignore); + if (!__pyx_ptype_5numpy_dtype) __PYX_ERR(1, 200, __pyx_L1_error) + __pyx_ptype_5numpy_flatiter = __Pyx_ImportType(__pyx_t_1, "numpy", "flatiter", sizeof(PyArrayIterObject), __Pyx_ImportType_CheckSize_Ignore); + if (!__pyx_ptype_5numpy_flatiter) __PYX_ERR(1, 223, __pyx_L1_error) + __pyx_ptype_5numpy_broadcast = __Pyx_ImportType(__pyx_t_1, "numpy", "broadcast", sizeof(PyArrayMultiIterObject), __Pyx_ImportType_CheckSize_Ignore); + if (!__pyx_ptype_5numpy_broadcast) __PYX_ERR(1, 227, __pyx_L1_error) + __pyx_ptype_5numpy_ndarray = __Pyx_ImportType(__pyx_t_1, "numpy", "ndarray", sizeof(PyArrayObject), __Pyx_ImportType_CheckSize_Ignore); + if (!__pyx_ptype_5numpy_ndarray) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_ptype_5numpy_generic = __Pyx_ImportType(__pyx_t_1, "numpy", "generic", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_generic) __PYX_ERR(1, 771, __pyx_L1_error) + __pyx_ptype_5numpy_number = __Pyx_ImportType(__pyx_t_1, "numpy", "number", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_number) __PYX_ERR(1, 773, __pyx_L1_error) + __pyx_ptype_5numpy_integer = __Pyx_ImportType(__pyx_t_1, "numpy", "integer", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_integer) __PYX_ERR(1, 775, __pyx_L1_error) + __pyx_ptype_5numpy_signedinteger = __Pyx_ImportType(__pyx_t_1, "numpy", "signedinteger", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_signedinteger) __PYX_ERR(1, 777, __pyx_L1_error) + __pyx_ptype_5numpy_unsignedinteger = __Pyx_ImportType(__pyx_t_1, "numpy", "unsignedinteger", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_unsignedinteger) __PYX_ERR(1, 779, __pyx_L1_error) + __pyx_ptype_5numpy_inexact = __Pyx_ImportType(__pyx_t_1, "numpy", "inexact", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_inexact) __PYX_ERR(1, 781, __pyx_L1_error) + __pyx_ptype_5numpy_floating = __Pyx_ImportType(__pyx_t_1, "numpy", "floating", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_floating) __PYX_ERR(1, 783, __pyx_L1_error) + __pyx_ptype_5numpy_complexfloating = __Pyx_ImportType(__pyx_t_1, "numpy", "complexfloating", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_complexfloating) __PYX_ERR(1, 785, __pyx_L1_error) + __pyx_ptype_5numpy_flexible = __Pyx_ImportType(__pyx_t_1, "numpy", "flexible", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_flexible) __PYX_ERR(1, 787, __pyx_L1_error) + __pyx_ptype_5numpy_character = __Pyx_ImportType(__pyx_t_1, "numpy", "character", sizeof(PyObject), __Pyx_ImportType_CheckSize_Warn); + if (!__pyx_ptype_5numpy_character) __PYX_ERR(1, 789, __pyx_L1_error) + __pyx_ptype_5numpy_ufunc = __Pyx_ImportType(__pyx_t_1, "numpy", "ufunc", sizeof(PyUFuncObject), __Pyx_ImportType_CheckSize_Ignore); + if (!__pyx_ptype_5numpy_ufunc) __PYX_ERR(1, 827, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_variable_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_import_code", 0); + /*--- Variable import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_import_code", 0); + /*--- Function import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + + +#ifndef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#elif PY_MAJOR_VERSION < 3 +#ifdef __cplusplus +#define __Pyx_PyMODINIT_FUNC extern "C" void +#else +#define __Pyx_PyMODINIT_FUNC void +#endif +#else +#ifdef __cplusplus +#define __Pyx_PyMODINIT_FUNC extern "C" PyObject * +#else +#define __Pyx_PyMODINIT_FUNC PyObject * +#endif +#endif + + +#if PY_MAJOR_VERSION < 3 +__Pyx_PyMODINIT_FUNC initcython_bbox(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC initcython_bbox(void) +#else +__Pyx_PyMODINIT_FUNC PyInit_cython_bbox(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC PyInit_cython_bbox(void) +#if CYTHON_PEP489_MULTI_PHASE_INIT +{ + return PyModuleDef_Init(&__pyx_moduledef); +} +static CYTHON_SMALL_CODE int __Pyx_check_single_interpreter(void) { + #if PY_VERSION_HEX >= 0x030700A1 + static PY_INT64_T main_interpreter_id = -1; + PY_INT64_T current_id = PyInterpreterState_GetID(PyThreadState_Get()->interp); + if (main_interpreter_id == -1) { + main_interpreter_id = current_id; + return (unlikely(current_id == -1)) ? -1 : 0; + } else if (unlikely(main_interpreter_id != current_id)) + #else + static PyInterpreterState *main_interpreter = NULL; + PyInterpreterState *current_interpreter = PyThreadState_Get()->interp; + if (!main_interpreter) { + main_interpreter = current_interpreter; + } else if (unlikely(main_interpreter != current_interpreter)) + #endif + { + PyErr_SetString( + PyExc_ImportError, + "Interpreter change detected - this module can only be loaded into one interpreter per process."); + return -1; + } + return 0; +} +static CYTHON_SMALL_CODE int __Pyx_copy_spec_to_module(PyObject *spec, PyObject *moddict, const char* from_name, const char* to_name, int allow_none) { + PyObject *value = PyObject_GetAttrString(spec, from_name); + int result = 0; + if (likely(value)) { + if (allow_none || value != Py_None) { + result = PyDict_SetItemString(moddict, to_name, value); + } + Py_DECREF(value); + } else if (PyErr_ExceptionMatches(PyExc_AttributeError)) { + PyErr_Clear(); + } else { + result = -1; + } + return result; +} +static CYTHON_SMALL_CODE PyObject* __pyx_pymod_create(PyObject *spec, CYTHON_UNUSED PyModuleDef *def) { + PyObject *module = NULL, *moddict, *modname; + if (__Pyx_check_single_interpreter()) + return NULL; + if (__pyx_m) + return __Pyx_NewRef(__pyx_m); + modname = PyObject_GetAttrString(spec, "name"); + if (unlikely(!modname)) goto bad; + module = PyModule_NewObject(modname); + Py_DECREF(modname); + if (unlikely(!module)) goto bad; + moddict = PyModule_GetDict(module); + if (unlikely(!moddict)) goto bad; + if (unlikely(__Pyx_copy_spec_to_module(spec, moddict, "loader", "__loader__", 1) < 0)) goto bad; + if (unlikely(__Pyx_copy_spec_to_module(spec, moddict, "origin", "__file__", 1) < 0)) goto bad; + if (unlikely(__Pyx_copy_spec_to_module(spec, moddict, "parent", "__package__", 1) < 0)) goto bad; + if (unlikely(__Pyx_copy_spec_to_module(spec, moddict, "submodule_search_locations", "__path__", 0) < 0)) goto bad; + return module; +bad: + Py_XDECREF(module); + return NULL; +} + + +static CYTHON_SMALL_CODE int __pyx_pymod_exec_cython_bbox(PyObject *__pyx_pyinit_module) +#endif +#endif +{ + PyObject *__pyx_t_1 = NULL; + PyObject *__pyx_t_2 = NULL; + int __pyx_lineno = 0; + const char *__pyx_filename = NULL; + int __pyx_clineno = 0; + __Pyx_RefNannyDeclarations + #if CYTHON_PEP489_MULTI_PHASE_INIT + if (__pyx_m) { + if (__pyx_m == __pyx_pyinit_module) return 0; + PyErr_SetString(PyExc_RuntimeError, "Module 'cython_bbox' has already been imported. Re-initialisation is not supported."); + return -1; + } + #elif PY_MAJOR_VERSION >= 3 + if (__pyx_m) return __Pyx_NewRef(__pyx_m); + #endif + #if CYTHON_REFNANNY +__Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); +if (!__Pyx_RefNanny) { + PyErr_Clear(); + __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); + if (!__Pyx_RefNanny) + Py_FatalError("failed to import 'refnanny' module"); +} +#endif + __Pyx_RefNannySetupContext("__Pyx_PyMODINIT_FUNC PyInit_cython_bbox(void)", 0); + if (__Pyx_check_binary_version() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #ifdef __Pxy_PyFrame_Initialize_Offsets + __Pxy_PyFrame_Initialize_Offsets(); + #endif + __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) __PYX_ERR(0, 1, __pyx_L1_error) + __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) __PYX_ERR(0, 1, __pyx_L1_error) + __pyx_empty_unicode = PyUnicode_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_unicode)) __PYX_ERR(0, 1, __pyx_L1_error) + #ifdef __Pyx_CyFunction_USED + if (__pyx_CyFunction_init() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + #ifdef __Pyx_FusedFunction_USED + if (__pyx_FusedFunction_init() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + #ifdef __Pyx_Coroutine_USED + if (__pyx_Coroutine_init() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + #ifdef __Pyx_Generator_USED + if (__pyx_Generator_init() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + #ifdef __Pyx_AsyncGen_USED + if (__pyx_AsyncGen_init() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + #ifdef __Pyx_StopAsyncIteration_USED + if (__pyx_StopAsyncIteration_init() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + /*--- Library function declarations ---*/ + /*--- Threads initialization code ---*/ + #if defined(WITH_THREAD) && PY_VERSION_HEX < 0x030700F0 && defined(__PYX_FORCE_INIT_THREADS) && __PYX_FORCE_INIT_THREADS + PyEval_InitThreads(); + #endif + /*--- Module creation code ---*/ + #if CYTHON_PEP489_MULTI_PHASE_INIT + __pyx_m = __pyx_pyinit_module; + Py_INCREF(__pyx_m); + #else + #if PY_MAJOR_VERSION < 3 + __pyx_m = Py_InitModule4("cython_bbox", __pyx_methods, 0, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m); + #else + __pyx_m = PyModule_Create(&__pyx_moduledef); + #endif + if (unlikely(!__pyx_m)) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + __pyx_d = PyModule_GetDict(__pyx_m); if (unlikely(!__pyx_d)) __PYX_ERR(0, 1, __pyx_L1_error) + Py_INCREF(__pyx_d); + __pyx_b = PyImport_AddModule(__Pyx_BUILTIN_MODULE_NAME); if (unlikely(!__pyx_b)) __PYX_ERR(0, 1, __pyx_L1_error) + Py_INCREF(__pyx_b); + __pyx_cython_runtime = PyImport_AddModule((char *) "cython_runtime"); if (unlikely(!__pyx_cython_runtime)) __PYX_ERR(0, 1, __pyx_L1_error) + Py_INCREF(__pyx_cython_runtime); + if (PyObject_SetAttrString(__pyx_m, "__builtins__", __pyx_b) < 0) __PYX_ERR(0, 1, __pyx_L1_error); + /*--- Initialize various global constants etc. ---*/ + if (__Pyx_InitGlobals() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #if PY_MAJOR_VERSION < 3 && (__PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT) + if (__Pyx_init_sys_getdefaultencoding_params() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + if (__pyx_module_is_main_cython_bbox) { + if (PyObject_SetAttr(__pyx_m, __pyx_n_s_name, __pyx_n_s_main) < 0) __PYX_ERR(0, 1, __pyx_L1_error) + } + #if PY_MAJOR_VERSION >= 3 + { + PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) __PYX_ERR(0, 1, __pyx_L1_error) + if (!PyDict_GetItemString(modules, "cython_bbox")) { + if (unlikely(PyDict_SetItemString(modules, "cython_bbox", __pyx_m) < 0)) __PYX_ERR(0, 1, __pyx_L1_error) + } + } + #endif + /*--- Builtin init code ---*/ + if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + /*--- Constants init code ---*/ + if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + /*--- Global type/function init code ---*/ + (void)__Pyx_modinit_global_init_code(); + (void)__Pyx_modinit_variable_export_code(); + (void)__Pyx_modinit_function_export_code(); + (void)__Pyx_modinit_type_init_code(); + if (unlikely(__Pyx_modinit_type_import_code() < 0)) __PYX_ERR(0, 1, __pyx_L1_error) + (void)__Pyx_modinit_variable_import_code(); + (void)__Pyx_modinit_function_import_code(); + /*--- Execution code ---*/ + #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) + if (__Pyx_patch_abc() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + #endif + + /* "cython_bbox.pyx":9 + * + * cimport cython + * import numpy as np # <<<<<<<<<<<<<< + * cimport numpy as np + * + */ + __pyx_t_1 = __Pyx_Import(__pyx_n_s_numpy, 0, -1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 9, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_np, __pyx_t_1) < 0) __PYX_ERR(0, 9, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + + /* "cython_bbox.pyx":12 + * cimport numpy as np + * + * DTYPE = np.float # <<<<<<<<<<<<<< + * ctypedef np.float_t DTYPE_t + * + */ + __Pyx_GetModuleGlobalName(__pyx_t_1, __pyx_n_s_np); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 12, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_float); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 12, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + if (PyDict_SetItem(__pyx_d, __pyx_n_s_DTYPE, __pyx_t_2) < 0) __PYX_ERR(0, 12, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + + /* "cython_bbox.pyx":15 + * ctypedef np.float_t DTYPE_t + * + * def bbox_overlaps( # <<<<<<<<<<<<<< + * np.ndarray[DTYPE_t, ndim=2] boxes, + * np.ndarray[DTYPE_t, ndim=2] query_boxes): + */ + __pyx_t_2 = PyCFunction_NewEx(&__pyx_mdef_11cython_bbox_1bbox_overlaps, NULL, __pyx_n_s_cython_bbox); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_bbox_overlaps, __pyx_t_2) < 0) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + + /* "cython_bbox.pyx":1 + * # -------------------------------------------------------- # <<<<<<<<<<<<<< + * # Fast R-CNN + * # Copyright (c) 2015 Microsoft + */ + __pyx_t_2 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_2) < 0) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + + /* "../../../../../Users/s/anaconda3/lib/site-packages/numpy/__init__.pxd":1014 + * + * + * cdef inline NPY_DATETIMEUNIT get_datetime64_unit(object obj) nogil: # <<<<<<<<<<<<<< + * """ + * returns the unit part of the dtype for a numpy datetime64 object. + */ + + /*--- Wrapped vars code ---*/ + + goto __pyx_L0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_XDECREF(__pyx_t_2); + if (__pyx_m) { + if (__pyx_d) { + __Pyx_AddTraceback("init cython_bbox", __pyx_clineno, __pyx_lineno, __pyx_filename); + } + Py_CLEAR(__pyx_m); + } else if (!PyErr_Occurred()) { + PyErr_SetString(PyExc_ImportError, "init cython_bbox"); + } + __pyx_L0:; + __Pyx_RefNannyFinishContext(); + #if CYTHON_PEP489_MULTI_PHASE_INIT + return (__pyx_m != NULL) ? 0 : -1; + #elif PY_MAJOR_VERSION >= 3 + return __pyx_m; + #else + return; + #endif +} + +/* --- Runtime support code --- */ +/* Refnanny */ +#if CYTHON_REFNANNY +static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) { + PyObject *m = NULL, *p = NULL; + void *r = NULL; + m = PyImport_ImportModule(modname); + if (!m) goto end; + p = PyObject_GetAttrString(m, "RefNannyAPI"); + if (!p) goto end; + r = PyLong_AsVoidPtr(p); +end: + Py_XDECREF(p); + Py_XDECREF(m); + return (__Pyx_RefNannyAPIStruct *)r; +} +#endif + +/* PyObjectGetAttrStr */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { + PyTypeObject* tp = Py_TYPE(obj); + if (likely(tp->tp_getattro)) + return tp->tp_getattro(obj, attr_name); +#if PY_MAJOR_VERSION < 3 + if (likely(tp->tp_getattr)) + return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); +#endif + return PyObject_GetAttr(obj, attr_name); +} +#endif + +/* GetBuiltinName */ +static PyObject *__Pyx_GetBuiltinName(PyObject *name) { + PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name); + if (unlikely(!result)) { + PyErr_Format(PyExc_NameError, +#if PY_MAJOR_VERSION >= 3 + "name '%U' is not defined", name); +#else + "name '%.200s' is not defined", PyString_AS_STRING(name)); +#endif + } + return result; +} + +/* RaiseArgTupleInvalid */ +static void __Pyx_RaiseArgtupleInvalid( + const char* func_name, + int exact, + Py_ssize_t num_min, + Py_ssize_t num_max, + Py_ssize_t num_found) +{ + Py_ssize_t num_expected; + const char *more_or_less; + if (num_found < num_min) { + num_expected = num_min; + more_or_less = "at least"; + } else { + num_expected = num_max; + more_or_less = "at most"; + } + if (exact) { + more_or_less = "exactly"; + } + PyErr_Format(PyExc_TypeError, + "%.200s() takes %.8s %" CYTHON_FORMAT_SSIZE_T "d positional argument%.1s (%" CYTHON_FORMAT_SSIZE_T "d given)", + func_name, more_or_less, num_expected, + (num_expected == 1) ? "" : "s", num_found); +} + +/* RaiseDoubleKeywords */ +static void __Pyx_RaiseDoubleKeywordsError( + const char* func_name, + PyObject* kw_name) +{ + PyErr_Format(PyExc_TypeError, + #if PY_MAJOR_VERSION >= 3 + "%s() got multiple values for keyword argument '%U'", func_name, kw_name); + #else + "%s() got multiple values for keyword argument '%s'", func_name, + PyString_AsString(kw_name)); + #endif +} + +/* ParseKeywords */ +static int __Pyx_ParseOptionalKeywords( + PyObject *kwds, + PyObject **argnames[], + PyObject *kwds2, + PyObject *values[], + Py_ssize_t num_pos_args, + const char* function_name) +{ + PyObject *key = 0, *value = 0; + Py_ssize_t pos = 0; + PyObject*** name; + PyObject*** first_kw_arg = argnames + num_pos_args; + while (PyDict_Next(kwds, &pos, &key, &value)) { + name = first_kw_arg; + while (*name && (**name != key)) name++; + if (*name) { + values[name-argnames] = value; + continue; + } + name = first_kw_arg; + #if PY_MAJOR_VERSION < 3 + if (likely(PyString_Check(key))) { + while (*name) { + if ((CYTHON_COMPILING_IN_PYPY || PyString_GET_SIZE(**name) == PyString_GET_SIZE(key)) + && _PyString_Eq(**name, key)) { + values[name-argnames] = value; + break; + } + name++; + } + if (*name) continue; + else { + PyObject*** argname = argnames; + while (argname != first_kw_arg) { + if ((**argname == key) || ( + (CYTHON_COMPILING_IN_PYPY || PyString_GET_SIZE(**argname) == PyString_GET_SIZE(key)) + && _PyString_Eq(**argname, key))) { + goto arg_passed_twice; + } + argname++; + } + } + } else + #endif + if (likely(PyUnicode_Check(key))) { + while (*name) { + int cmp = (**name == key) ? 0 : + #if !CYTHON_COMPILING_IN_PYPY && PY_MAJOR_VERSION >= 3 + (__Pyx_PyUnicode_GET_LENGTH(**name) != __Pyx_PyUnicode_GET_LENGTH(key)) ? 1 : + #endif + PyUnicode_Compare(**name, key); + if (cmp < 0 && unlikely(PyErr_Occurred())) goto bad; + if (cmp == 0) { + values[name-argnames] = value; + break; + } + name++; + } + if (*name) continue; + else { + PyObject*** argname = argnames; + while (argname != first_kw_arg) { + int cmp = (**argname == key) ? 0 : + #if !CYTHON_COMPILING_IN_PYPY && PY_MAJOR_VERSION >= 3 + (__Pyx_PyUnicode_GET_LENGTH(**argname) != __Pyx_PyUnicode_GET_LENGTH(key)) ? 1 : + #endif + PyUnicode_Compare(**argname, key); + if (cmp < 0 && unlikely(PyErr_Occurred())) goto bad; + if (cmp == 0) goto arg_passed_twice; + argname++; + } + } + } else + goto invalid_keyword_type; + if (kwds2) { + if (unlikely(PyDict_SetItem(kwds2, key, value))) goto bad; + } else { + goto invalid_keyword; + } + } + return 0; +arg_passed_twice: + __Pyx_RaiseDoubleKeywordsError(function_name, key); + goto bad; +invalid_keyword_type: + PyErr_Format(PyExc_TypeError, + "%.200s() keywords must be strings", function_name); + goto bad; +invalid_keyword: + PyErr_Format(PyExc_TypeError, + #if PY_MAJOR_VERSION < 3 + "%.200s() got an unexpected keyword argument '%.200s'", + function_name, PyString_AsString(key)); + #else + "%s() got an unexpected keyword argument '%U'", + function_name, key); + #endif +bad: + return -1; +} + +/* ArgTypeTest */ +static int __Pyx__ArgTypeTest(PyObject *obj, PyTypeObject *type, const char *name, int exact) +{ + if (unlikely(!type)) { + PyErr_SetString(PyExc_SystemError, "Missing type object"); + return 0; + } + else if (exact) { + #if PY_MAJOR_VERSION == 2 + if ((type == &PyBaseString_Type) && likely(__Pyx_PyBaseString_CheckExact(obj))) return 1; + #endif + } + else { + if (likely(__Pyx_TypeCheck(obj, type))) return 1; + } + PyErr_Format(PyExc_TypeError, + "Argument '%.200s' has incorrect type (expected %.200s, got %.200s)", + name, type->tp_name, Py_TYPE(obj)->tp_name); + return 0; +} + +/* IsLittleEndian */ +static CYTHON_INLINE int __Pyx_Is_Little_Endian(void) +{ + union { + uint32_t u32; + uint8_t u8[4]; + } S; + S.u32 = 0x01020304; + return S.u8[0] == 4; +} + +/* BufferFormatCheck */ +static void __Pyx_BufFmt_Init(__Pyx_BufFmt_Context* ctx, + __Pyx_BufFmt_StackElem* stack, + __Pyx_TypeInfo* type) { + stack[0].field = &ctx->root; + stack[0].parent_offset = 0; + ctx->root.type = type; + ctx->root.name = "buffer dtype"; + ctx->root.offset = 0; + ctx->head = stack; + ctx->head->field = &ctx->root; + ctx->fmt_offset = 0; + ctx->head->parent_offset = 0; + ctx->new_packmode = '@'; + ctx->enc_packmode = '@'; + ctx->new_count = 1; + ctx->enc_count = 0; + ctx->enc_type = 0; + ctx->is_complex = 0; + ctx->is_valid_array = 0; + ctx->struct_alignment = 0; + while (type->typegroup == 'S') { + ++ctx->head; + ctx->head->field = type->fields; + ctx->head->parent_offset = 0; + type = type->fields->type; + } +} +static int __Pyx_BufFmt_ParseNumber(const char** ts) { + int count; + const char* t = *ts; + if (*t < '0' || *t > '9') { + return -1; + } else { + count = *t++ - '0'; + while (*t >= '0' && *t <= '9') { + count *= 10; + count += *t++ - '0'; + } + } + *ts = t; + return count; +} +static int __Pyx_BufFmt_ExpectNumber(const char **ts) { + int number = __Pyx_BufFmt_ParseNumber(ts); + if (number == -1) + PyErr_Format(PyExc_ValueError,\ + "Does not understand character buffer dtype format string ('%c')", **ts); + return number; +} +static void __Pyx_BufFmt_RaiseUnexpectedChar(char ch) { + PyErr_Format(PyExc_ValueError, + "Unexpected format string character: '%c'", ch); +} +static const char* __Pyx_BufFmt_DescribeTypeChar(char ch, int is_complex) { + switch (ch) { + case '?': return "'bool'"; + case 'c': return "'char'"; + case 'b': return "'signed char'"; + case 'B': return "'unsigned char'"; + case 'h': return "'short'"; + case 'H': return "'unsigned short'"; + case 'i': return "'int'"; + case 'I': return "'unsigned int'"; + case 'l': return "'long'"; + case 'L': return "'unsigned long'"; + case 'q': return "'long long'"; + case 'Q': return "'unsigned long long'"; + case 'f': return (is_complex ? "'complex float'" : "'float'"); + case 'd': return (is_complex ? "'complex double'" : "'double'"); + case 'g': return (is_complex ? "'complex long double'" : "'long double'"); + case 'T': return "a struct"; + case 'O': return "Python object"; + case 'P': return "a pointer"; + case 's': case 'p': return "a string"; + case 0: return "end"; + default: return "unparseable format string"; + } +} +static size_t __Pyx_BufFmt_TypeCharToStandardSize(char ch, int is_complex) { + switch (ch) { + case '?': case 'c': case 'b': case 'B': case 's': case 'p': return 1; + case 'h': case 'H': return 2; + case 'i': case 'I': case 'l': case 'L': return 4; + case 'q': case 'Q': return 8; + case 'f': return (is_complex ? 8 : 4); + case 'd': return (is_complex ? 16 : 8); + case 'g': { + PyErr_SetString(PyExc_ValueError, "Python does not define a standard format string size for long double ('g').."); + return 0; + } + case 'O': case 'P': return sizeof(void*); + default: + __Pyx_BufFmt_RaiseUnexpectedChar(ch); + return 0; + } +} +static size_t __Pyx_BufFmt_TypeCharToNativeSize(char ch, int is_complex) { + switch (ch) { + case '?': case 'c': case 'b': case 'B': case 's': case 'p': return 1; + case 'h': case 'H': return sizeof(short); + case 'i': case 'I': return sizeof(int); + case 'l': case 'L': return sizeof(long); + #ifdef HAVE_LONG_LONG + case 'q': case 'Q': return sizeof(PY_LONG_LONG); + #endif + case 'f': return sizeof(float) * (is_complex ? 2 : 1); + case 'd': return sizeof(double) * (is_complex ? 2 : 1); + case 'g': return sizeof(long double) * (is_complex ? 2 : 1); + case 'O': case 'P': return sizeof(void*); + default: { + __Pyx_BufFmt_RaiseUnexpectedChar(ch); + return 0; + } + } +} +typedef struct { char c; short x; } __Pyx_st_short; +typedef struct { char c; int x; } __Pyx_st_int; +typedef struct { char c; long x; } __Pyx_st_long; +typedef struct { char c; float x; } __Pyx_st_float; +typedef struct { char c; double x; } __Pyx_st_double; +typedef struct { char c; long double x; } __Pyx_st_longdouble; +typedef struct { char c; void *x; } __Pyx_st_void_p; +#ifdef HAVE_LONG_LONG +typedef struct { char c; PY_LONG_LONG x; } __Pyx_st_longlong; +#endif +static size_t __Pyx_BufFmt_TypeCharToAlignment(char ch, CYTHON_UNUSED int is_complex) { + switch (ch) { + case '?': case 'c': case 'b': case 'B': case 's': case 'p': return 1; + case 'h': case 'H': return sizeof(__Pyx_st_short) - sizeof(short); + case 'i': case 'I': return sizeof(__Pyx_st_int) - sizeof(int); + case 'l': case 'L': return sizeof(__Pyx_st_long) - sizeof(long); +#ifdef HAVE_LONG_LONG + case 'q': case 'Q': return sizeof(__Pyx_st_longlong) - sizeof(PY_LONG_LONG); +#endif + case 'f': return sizeof(__Pyx_st_float) - sizeof(float); + case 'd': return sizeof(__Pyx_st_double) - sizeof(double); + case 'g': return sizeof(__Pyx_st_longdouble) - sizeof(long double); + case 'P': case 'O': return sizeof(__Pyx_st_void_p) - sizeof(void*); + default: + __Pyx_BufFmt_RaiseUnexpectedChar(ch); + return 0; + } +} +/* These are for computing the padding at the end of the struct to align + on the first member of the struct. This will probably the same as above, + but we don't have any guarantees. + */ +typedef struct { short x; char c; } __Pyx_pad_short; +typedef struct { int x; char c; } __Pyx_pad_int; +typedef struct { long x; char c; } __Pyx_pad_long; +typedef struct { float x; char c; } __Pyx_pad_float; +typedef struct { double x; char c; } __Pyx_pad_double; +typedef struct { long double x; char c; } __Pyx_pad_longdouble; +typedef struct { void *x; char c; } __Pyx_pad_void_p; +#ifdef HAVE_LONG_LONG +typedef struct { PY_LONG_LONG x; char c; } __Pyx_pad_longlong; +#endif +static size_t __Pyx_BufFmt_TypeCharToPadding(char ch, CYTHON_UNUSED int is_complex) { + switch (ch) { + case '?': case 'c': case 'b': case 'B': case 's': case 'p': return 1; + case 'h': case 'H': return sizeof(__Pyx_pad_short) - sizeof(short); + case 'i': case 'I': return sizeof(__Pyx_pad_int) - sizeof(int); + case 'l': case 'L': return sizeof(__Pyx_pad_long) - sizeof(long); +#ifdef HAVE_LONG_LONG + case 'q': case 'Q': return sizeof(__Pyx_pad_longlong) - sizeof(PY_LONG_LONG); +#endif + case 'f': return sizeof(__Pyx_pad_float) - sizeof(float); + case 'd': return sizeof(__Pyx_pad_double) - sizeof(double); + case 'g': return sizeof(__Pyx_pad_longdouble) - sizeof(long double); + case 'P': case 'O': return sizeof(__Pyx_pad_void_p) - sizeof(void*); + default: + __Pyx_BufFmt_RaiseUnexpectedChar(ch); + return 0; + } +} +static char __Pyx_BufFmt_TypeCharToGroup(char ch, int is_complex) { + switch (ch) { + case 'c': + return 'H'; + case 'b': case 'h': case 'i': + case 'l': case 'q': case 's': case 'p': + return 'I'; + case '?': case 'B': case 'H': case 'I': case 'L': case 'Q': + return 'U'; + case 'f': case 'd': case 'g': + return (is_complex ? 'C' : 'R'); + case 'O': + return 'O'; + case 'P': + return 'P'; + default: { + __Pyx_BufFmt_RaiseUnexpectedChar(ch); + return 0; + } + } +} +static void __Pyx_BufFmt_RaiseExpected(__Pyx_BufFmt_Context* ctx) { + if (ctx->head == NULL || ctx->head->field == &ctx->root) { + const char* expected; + const char* quote; + if (ctx->head == NULL) { + expected = "end"; + quote = ""; + } else { + expected = ctx->head->field->type->name; + quote = "'"; + } + PyErr_Format(PyExc_ValueError, + "Buffer dtype mismatch, expected %s%s%s but got %s", + quote, expected, quote, + __Pyx_BufFmt_DescribeTypeChar(ctx->enc_type, ctx->is_complex)); + } else { + __Pyx_StructField* field = ctx->head->field; + __Pyx_StructField* parent = (ctx->head - 1)->field; + PyErr_Format(PyExc_ValueError, + "Buffer dtype mismatch, expected '%s' but got %s in '%s.%s'", + field->type->name, __Pyx_BufFmt_DescribeTypeChar(ctx->enc_type, ctx->is_complex), + parent->type->name, field->name); + } +} +static int __Pyx_BufFmt_ProcessTypeChunk(__Pyx_BufFmt_Context* ctx) { + char group; + size_t size, offset, arraysize = 1; + if (ctx->enc_type == 0) return 0; + if (ctx->head->field->type->arraysize[0]) { + int i, ndim = 0; + if (ctx->enc_type == 's' || ctx->enc_type == 'p') { + ctx->is_valid_array = ctx->head->field->type->ndim == 1; + ndim = 1; + if (ctx->enc_count != ctx->head->field->type->arraysize[0]) { + PyErr_Format(PyExc_ValueError, + "Expected a dimension of size %zu, got %zu", + ctx->head->field->type->arraysize[0], ctx->enc_count); + return -1; + } + } + if (!ctx->is_valid_array) { + PyErr_Format(PyExc_ValueError, "Expected %d dimensions, got %d", + ctx->head->field->type->ndim, ndim); + return -1; + } + for (i = 0; i < ctx->head->field->type->ndim; i++) { + arraysize *= ctx->head->field->type->arraysize[i]; + } + ctx->is_valid_array = 0; + ctx->enc_count = 1; + } + group = __Pyx_BufFmt_TypeCharToGroup(ctx->enc_type, ctx->is_complex); + do { + __Pyx_StructField* field = ctx->head->field; + __Pyx_TypeInfo* type = field->type; + if (ctx->enc_packmode == '@' || ctx->enc_packmode == '^') { + size = __Pyx_BufFmt_TypeCharToNativeSize(ctx->enc_type, ctx->is_complex); + } else { + size = __Pyx_BufFmt_TypeCharToStandardSize(ctx->enc_type, ctx->is_complex); + } + if (ctx->enc_packmode == '@') { + size_t align_at = __Pyx_BufFmt_TypeCharToAlignment(ctx->enc_type, ctx->is_complex); + size_t align_mod_offset; + if (align_at == 0) return -1; + align_mod_offset = ctx->fmt_offset % align_at; + if (align_mod_offset > 0) ctx->fmt_offset += align_at - align_mod_offset; + if (ctx->struct_alignment == 0) + ctx->struct_alignment = __Pyx_BufFmt_TypeCharToPadding(ctx->enc_type, + ctx->is_complex); + } + if (type->size != size || type->typegroup != group) { + if (type->typegroup == 'C' && type->fields != NULL) { + size_t parent_offset = ctx->head->parent_offset + field->offset; + ++ctx->head; + ctx->head->field = type->fields; + ctx->head->parent_offset = parent_offset; + continue; + } + if ((type->typegroup == 'H' || group == 'H') && type->size == size) { + } else { + __Pyx_BufFmt_RaiseExpected(ctx); + return -1; + } + } + offset = ctx->head->parent_offset + field->offset; + if (ctx->fmt_offset != offset) { + PyErr_Format(PyExc_ValueError, + "Buffer dtype mismatch; next field is at offset %" CYTHON_FORMAT_SSIZE_T "d but %" CYTHON_FORMAT_SSIZE_T "d expected", + (Py_ssize_t)ctx->fmt_offset, (Py_ssize_t)offset); + return -1; + } + ctx->fmt_offset += size; + if (arraysize) + ctx->fmt_offset += (arraysize - 1) * size; + --ctx->enc_count; + while (1) { + if (field == &ctx->root) { + ctx->head = NULL; + if (ctx->enc_count != 0) { + __Pyx_BufFmt_RaiseExpected(ctx); + return -1; + } + break; + } + ctx->head->field = ++field; + if (field->type == NULL) { + --ctx->head; + field = ctx->head->field; + continue; + } else if (field->type->typegroup == 'S') { + size_t parent_offset = ctx->head->parent_offset + field->offset; + if (field->type->fields->type == NULL) continue; + field = field->type->fields; + ++ctx->head; + ctx->head->field = field; + ctx->head->parent_offset = parent_offset; + break; + } else { + break; + } + } + } while (ctx->enc_count); + ctx->enc_type = 0; + ctx->is_complex = 0; + return 0; +} +static PyObject * +__pyx_buffmt_parse_array(__Pyx_BufFmt_Context* ctx, const char** tsp) +{ + const char *ts = *tsp; + int i = 0, number, ndim; + ++ts; + if (ctx->new_count != 1) { + PyErr_SetString(PyExc_ValueError, + "Cannot handle repeated arrays in format string"); + return NULL; + } + if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL; + ndim = ctx->head->field->type->ndim; + while (*ts && *ts != ')') { + switch (*ts) { + case ' ': case '\f': case '\r': case '\n': case '\t': case '\v': continue; + default: break; + } + number = __Pyx_BufFmt_ExpectNumber(&ts); + if (number == -1) return NULL; + if (i < ndim && (size_t) number != ctx->head->field->type->arraysize[i]) + return PyErr_Format(PyExc_ValueError, + "Expected a dimension of size %zu, got %d", + ctx->head->field->type->arraysize[i], number); + if (*ts != ',' && *ts != ')') + return PyErr_Format(PyExc_ValueError, + "Expected a comma in format string, got '%c'", *ts); + if (*ts == ',') ts++; + i++; + } + if (i != ndim) + return PyErr_Format(PyExc_ValueError, "Expected %d dimension(s), got %d", + ctx->head->field->type->ndim, i); + if (!*ts) { + PyErr_SetString(PyExc_ValueError, + "Unexpected end of format string, expected ')'"); + return NULL; + } + ctx->is_valid_array = 1; + ctx->new_count = 1; + *tsp = ++ts; + return Py_None; +} +static const char* __Pyx_BufFmt_CheckString(__Pyx_BufFmt_Context* ctx, const char* ts) { + int got_Z = 0; + while (1) { + switch(*ts) { + case 0: + if (ctx->enc_type != 0 && ctx->head == NULL) { + __Pyx_BufFmt_RaiseExpected(ctx); + return NULL; + } + if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL; + if (ctx->head != NULL) { + __Pyx_BufFmt_RaiseExpected(ctx); + return NULL; + } + return ts; + case ' ': + case '\r': + case '\n': + ++ts; + break; + case '<': + if (!__Pyx_Is_Little_Endian()) { + PyErr_SetString(PyExc_ValueError, "Little-endian buffer not supported on big-endian compiler"); + return NULL; + } + ctx->new_packmode = '='; + ++ts; + break; + case '>': + case '!': + if (__Pyx_Is_Little_Endian()) { + PyErr_SetString(PyExc_ValueError, "Big-endian buffer not supported on little-endian compiler"); + return NULL; + } + ctx->new_packmode = '='; + ++ts; + break; + case '=': + case '@': + case '^': + ctx->new_packmode = *ts++; + break; + case 'T': + { + const char* ts_after_sub; + size_t i, struct_count = ctx->new_count; + size_t struct_alignment = ctx->struct_alignment; + ctx->new_count = 1; + ++ts; + if (*ts != '{') { + PyErr_SetString(PyExc_ValueError, "Buffer acquisition: Expected '{' after 'T'"); + return NULL; + } + if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL; + ctx->enc_type = 0; + ctx->enc_count = 0; + ctx->struct_alignment = 0; + ++ts; + ts_after_sub = ts; + for (i = 0; i != struct_count; ++i) { + ts_after_sub = __Pyx_BufFmt_CheckString(ctx, ts); + if (!ts_after_sub) return NULL; + } + ts = ts_after_sub; + if (struct_alignment) ctx->struct_alignment = struct_alignment; + } + break; + case '}': + { + size_t alignment = ctx->struct_alignment; + ++ts; + if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL; + ctx->enc_type = 0; + if (alignment && ctx->fmt_offset % alignment) { + ctx->fmt_offset += alignment - (ctx->fmt_offset % alignment); + } + } + return ts; + case 'x': + if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL; + ctx->fmt_offset += ctx->new_count; + ctx->new_count = 1; + ctx->enc_count = 0; + ctx->enc_type = 0; + ctx->enc_packmode = ctx->new_packmode; + ++ts; + break; + case 'Z': + got_Z = 1; + ++ts; + if (*ts != 'f' && *ts != 'd' && *ts != 'g') { + __Pyx_BufFmt_RaiseUnexpectedChar('Z'); + return NULL; + } + CYTHON_FALLTHROUGH; + case '?': case 'c': case 'b': case 'B': case 'h': case 'H': case 'i': case 'I': + case 'l': case 'L': case 'q': case 'Q': + case 'f': case 'd': case 'g': + case 'O': case 'p': + if ((ctx->enc_type == *ts) && (got_Z == ctx->is_complex) && + (ctx->enc_packmode == ctx->new_packmode) && (!ctx->is_valid_array)) { + ctx->enc_count += ctx->new_count; + ctx->new_count = 1; + got_Z = 0; + ++ts; + break; + } + CYTHON_FALLTHROUGH; + case 's': + if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL; + ctx->enc_count = ctx->new_count; + ctx->enc_packmode = ctx->new_packmode; + ctx->enc_type = *ts; + ctx->is_complex = got_Z; + ++ts; + ctx->new_count = 1; + got_Z = 0; + break; + case ':': + ++ts; + while(*ts != ':') ++ts; + ++ts; + break; + case '(': + if (!__pyx_buffmt_parse_array(ctx, &ts)) return NULL; + break; + default: + { + int number = __Pyx_BufFmt_ExpectNumber(&ts); + if (number == -1) return NULL; + ctx->new_count = (size_t)number; + } + } + } +} + +/* BufferGetAndValidate */ + static CYTHON_INLINE void __Pyx_SafeReleaseBuffer(Py_buffer* info) { + if (unlikely(info->buf == NULL)) return; + if (info->suboffsets == __Pyx_minusones) info->suboffsets = NULL; + __Pyx_ReleaseBuffer(info); +} +static void __Pyx_ZeroBuffer(Py_buffer* buf) { + buf->buf = NULL; + buf->obj = NULL; + buf->strides = __Pyx_zeros; + buf->shape = __Pyx_zeros; + buf->suboffsets = __Pyx_minusones; +} +static int __Pyx__GetBufferAndValidate( + Py_buffer* buf, PyObject* obj, __Pyx_TypeInfo* dtype, int flags, + int nd, int cast, __Pyx_BufFmt_StackElem* stack) +{ + buf->buf = NULL; + if (unlikely(__Pyx_GetBuffer(obj, buf, flags) == -1)) { + __Pyx_ZeroBuffer(buf); + return -1; + } + if (unlikely(buf->ndim != nd)) { + PyErr_Format(PyExc_ValueError, + "Buffer has wrong number of dimensions (expected %d, got %d)", + nd, buf->ndim); + goto fail; + } + if (!cast) { + __Pyx_BufFmt_Context ctx; + __Pyx_BufFmt_Init(&ctx, stack, dtype); + if (!__Pyx_BufFmt_CheckString(&ctx, buf->format)) goto fail; + } + if (unlikely((size_t)buf->itemsize != dtype->size)) { + PyErr_Format(PyExc_ValueError, + "Item size of buffer (%" CYTHON_FORMAT_SSIZE_T "d byte%s) does not match size of '%s' (%" CYTHON_FORMAT_SSIZE_T "d byte%s)", + buf->itemsize, (buf->itemsize > 1) ? "s" : "", + dtype->name, (Py_ssize_t)dtype->size, (dtype->size > 1) ? "s" : ""); + goto fail; + } + if (buf->suboffsets == NULL) buf->suboffsets = __Pyx_minusones; + return 0; +fail:; + __Pyx_SafeReleaseBuffer(buf); + return -1; +} + +/* PyDictVersioning */ + #if CYTHON_USE_DICT_VERSIONS && CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PY_UINT64_T __Pyx_get_tp_dict_version(PyObject *obj) { + PyObject *dict = Py_TYPE(obj)->tp_dict; + return likely(dict) ? __PYX_GET_DICT_VERSION(dict) : 0; +} +static CYTHON_INLINE PY_UINT64_T __Pyx_get_object_dict_version(PyObject *obj) { + PyObject **dictptr = NULL; + Py_ssize_t offset = Py_TYPE(obj)->tp_dictoffset; + if (offset) { +#if CYTHON_COMPILING_IN_CPYTHON + dictptr = (likely(offset > 0)) ? (PyObject **) ((char *)obj + offset) : _PyObject_GetDictPtr(obj); +#else + dictptr = _PyObject_GetDictPtr(obj); +#endif + } + return (dictptr && *dictptr) ? __PYX_GET_DICT_VERSION(*dictptr) : 0; +} +static CYTHON_INLINE int __Pyx_object_dict_version_matches(PyObject* obj, PY_UINT64_T tp_dict_version, PY_UINT64_T obj_dict_version) { + PyObject *dict = Py_TYPE(obj)->tp_dict; + if (unlikely(!dict) || unlikely(tp_dict_version != __PYX_GET_DICT_VERSION(dict))) + return 0; + return obj_dict_version == __Pyx_get_object_dict_version(obj); +} +#endif + +/* GetModuleGlobalName */ + #if CYTHON_USE_DICT_VERSIONS +static PyObject *__Pyx__GetModuleGlobalName(PyObject *name, PY_UINT64_T *dict_version, PyObject **dict_cached_value) +#else +static CYTHON_INLINE PyObject *__Pyx__GetModuleGlobalName(PyObject *name) +#endif +{ + PyObject *result; +#if !CYTHON_AVOID_BORROWED_REFS +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 + result = _PyDict_GetItem_KnownHash(__pyx_d, name, ((PyASCIIObject *) name)->hash); + __PYX_UPDATE_DICT_CACHE(__pyx_d, result, *dict_cached_value, *dict_version) + if (likely(result)) { + return __Pyx_NewRef(result); + } else if (unlikely(PyErr_Occurred())) { + return NULL; + } +#else + result = PyDict_GetItem(__pyx_d, name); + __PYX_UPDATE_DICT_CACHE(__pyx_d, result, *dict_cached_value, *dict_version) + if (likely(result)) { + return __Pyx_NewRef(result); + } +#endif +#else + result = PyObject_GetItem(__pyx_d, name); + __PYX_UPDATE_DICT_CACHE(__pyx_d, result, *dict_cached_value, *dict_version) + if (likely(result)) { + return __Pyx_NewRef(result); + } + PyErr_Clear(); +#endif + return __Pyx_GetBuiltinName(name); +} + +/* PyObjectCall */ + #if CYTHON_COMPILING_IN_CPYTHON +static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg, PyObject *kw) { + PyObject *result; + ternaryfunc call = Py_TYPE(func)->tp_call; + if (unlikely(!call)) + return PyObject_Call(func, arg, kw); + if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) + return NULL; + result = (*call)(func, arg, kw); + Py_LeaveRecursiveCall(); + if (unlikely(!result) && unlikely(!PyErr_Occurred())) { + PyErr_SetString( + PyExc_SystemError, + "NULL result without error in PyObject_Call"); + } + return result; +} +#endif + +/* ExtTypeTest */ + static CYTHON_INLINE int __Pyx_TypeTest(PyObject *obj, PyTypeObject *type) { + if (unlikely(!type)) { + PyErr_SetString(PyExc_SystemError, "Missing type object"); + return 0; + } + if (likely(__Pyx_TypeCheck(obj, type))) + return 1; + PyErr_Format(PyExc_TypeError, "Cannot convert %.200s to %.200s", + Py_TYPE(obj)->tp_name, type->tp_name); + return 0; +} + +/* BufferIndexError */ + static void __Pyx_RaiseBufferIndexError(int axis) { + PyErr_Format(PyExc_IndexError, + "Out of bounds on buffer access (axis %d)", axis); +} + +/* PyErrFetchRestore */ + #if CYTHON_FAST_THREAD_STATE +static CYTHON_INLINE void __Pyx_ErrRestoreInState(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb) { + PyObject *tmp_type, *tmp_value, *tmp_tb; + tmp_type = tstate->curexc_type; + tmp_value = tstate->curexc_value; + tmp_tb = tstate->curexc_traceback; + tstate->curexc_type = type; + tstate->curexc_value = value; + tstate->curexc_traceback = tb; + Py_XDECREF(tmp_type); + Py_XDECREF(tmp_value); + Py_XDECREF(tmp_tb); +} +static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { + *type = tstate->curexc_type; + *value = tstate->curexc_value; + *tb = tstate->curexc_traceback; + tstate->curexc_type = 0; + tstate->curexc_value = 0; + tstate->curexc_traceback = 0; +} +#endif + +/* GetTopmostException */ + #if CYTHON_USE_EXC_INFO_STACK +static _PyErr_StackItem * +__Pyx_PyErr_GetTopmostException(PyThreadState *tstate) +{ + _PyErr_StackItem *exc_info = tstate->exc_info; + while ((exc_info->exc_type == NULL || exc_info->exc_type == Py_None) && + exc_info->previous_item != NULL) + { + exc_info = exc_info->previous_item; + } + return exc_info; +} +#endif + +/* SaveResetException */ + #if CYTHON_FAST_THREAD_STATE +static CYTHON_INLINE void __Pyx__ExceptionSave(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { + #if CYTHON_USE_EXC_INFO_STACK + _PyErr_StackItem *exc_info = __Pyx_PyErr_GetTopmostException(tstate); + *type = exc_info->exc_type; + *value = exc_info->exc_value; + *tb = exc_info->exc_traceback; + #else + *type = tstate->exc_type; + *value = tstate->exc_value; + *tb = tstate->exc_traceback; + #endif + Py_XINCREF(*type); + Py_XINCREF(*value); + Py_XINCREF(*tb); +} +static CYTHON_INLINE void __Pyx__ExceptionReset(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb) { + PyObject *tmp_type, *tmp_value, *tmp_tb; + #if CYTHON_USE_EXC_INFO_STACK + _PyErr_StackItem *exc_info = tstate->exc_info; + tmp_type = exc_info->exc_type; + tmp_value = exc_info->exc_value; + tmp_tb = exc_info->exc_traceback; + exc_info->exc_type = type; + exc_info->exc_value = value; + exc_info->exc_traceback = tb; + #else + tmp_type = tstate->exc_type; + tmp_value = tstate->exc_value; + tmp_tb = tstate->exc_traceback; + tstate->exc_type = type; + tstate->exc_value = value; + tstate->exc_traceback = tb; + #endif + Py_XDECREF(tmp_type); + Py_XDECREF(tmp_value); + Py_XDECREF(tmp_tb); +} +#endif + +/* PyErrExceptionMatches */ + #if CYTHON_FAST_THREAD_STATE +static int __Pyx_PyErr_ExceptionMatchesTuple(PyObject *exc_type, PyObject *tuple) { + Py_ssize_t i, n; + n = PyTuple_GET_SIZE(tuple); +#if PY_MAJOR_VERSION >= 3 + for (i=0; icurexc_type; + if (exc_type == err) return 1; + if (unlikely(!exc_type)) return 0; + if (unlikely(PyTuple_Check(err))) + return __Pyx_PyErr_ExceptionMatchesTuple(exc_type, err); + return __Pyx_PyErr_GivenExceptionMatches(exc_type, err); +} +#endif + +/* GetException */ + #if CYTHON_FAST_THREAD_STATE +static int __Pyx__GetException(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) +#else +static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) +#endif +{ + PyObject *local_type, *local_value, *local_tb; +#if CYTHON_FAST_THREAD_STATE + PyObject *tmp_type, *tmp_value, *tmp_tb; + local_type = tstate->curexc_type; + local_value = tstate->curexc_value; + local_tb = tstate->curexc_traceback; + tstate->curexc_type = 0; + tstate->curexc_value = 0; + tstate->curexc_traceback = 0; +#else + PyErr_Fetch(&local_type, &local_value, &local_tb); +#endif + PyErr_NormalizeException(&local_type, &local_value, &local_tb); +#if CYTHON_FAST_THREAD_STATE + if (unlikely(tstate->curexc_type)) +#else + if (unlikely(PyErr_Occurred())) +#endif + goto bad; + #if PY_MAJOR_VERSION >= 3 + if (local_tb) { + if (unlikely(PyException_SetTraceback(local_value, local_tb) < 0)) + goto bad; + } + #endif + Py_XINCREF(local_tb); + Py_XINCREF(local_type); + Py_XINCREF(local_value); + *type = local_type; + *value = local_value; + *tb = local_tb; +#if CYTHON_FAST_THREAD_STATE + #if CYTHON_USE_EXC_INFO_STACK + { + _PyErr_StackItem *exc_info = tstate->exc_info; + tmp_type = exc_info->exc_type; + tmp_value = exc_info->exc_value; + tmp_tb = exc_info->exc_traceback; + exc_info->exc_type = local_type; + exc_info->exc_value = local_value; + exc_info->exc_traceback = local_tb; + } + #else + tmp_type = tstate->exc_type; + tmp_value = tstate->exc_value; + tmp_tb = tstate->exc_traceback; + tstate->exc_type = local_type; + tstate->exc_value = local_value; + tstate->exc_traceback = local_tb; + #endif + Py_XDECREF(tmp_type); + Py_XDECREF(tmp_value); + Py_XDECREF(tmp_tb); +#else + PyErr_SetExcInfo(local_type, local_value, local_tb); +#endif + return 0; +bad: + *type = 0; + *value = 0; + *tb = 0; + Py_XDECREF(local_type); + Py_XDECREF(local_value); + Py_XDECREF(local_tb); + return -1; +} + +/* RaiseException */ + #if PY_MAJOR_VERSION < 3 +static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, + CYTHON_UNUSED PyObject *cause) { + __Pyx_PyThreadState_declare + Py_XINCREF(type); + if (!value || value == Py_None) + value = NULL; + else + Py_INCREF(value); + if (!tb || tb == Py_None) + tb = NULL; + else { + Py_INCREF(tb); + if (!PyTraceBack_Check(tb)) { + PyErr_SetString(PyExc_TypeError, + "raise: arg 3 must be a traceback or None"); + goto raise_error; + } + } + if (PyType_Check(type)) { +#if CYTHON_COMPILING_IN_PYPY + if (!value) { + Py_INCREF(Py_None); + value = Py_None; + } +#endif + PyErr_NormalizeException(&type, &value, &tb); + } else { + if (value) { + PyErr_SetString(PyExc_TypeError, + "instance exception may not have a separate value"); + goto raise_error; + } + value = type; + type = (PyObject*) Py_TYPE(type); + Py_INCREF(type); + if (!PyType_IsSubtype((PyTypeObject *)type, (PyTypeObject *)PyExc_BaseException)) { + PyErr_SetString(PyExc_TypeError, + "raise: exception class must be a subclass of BaseException"); + goto raise_error; + } + } + __Pyx_PyThreadState_assign + __Pyx_ErrRestore(type, value, tb); + return; +raise_error: + Py_XDECREF(value); + Py_XDECREF(type); + Py_XDECREF(tb); + return; +} +#else +static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause) { + PyObject* owned_instance = NULL; + if (tb == Py_None) { + tb = 0; + } else if (tb && !PyTraceBack_Check(tb)) { + PyErr_SetString(PyExc_TypeError, + "raise: arg 3 must be a traceback or None"); + goto bad; + } + if (value == Py_None) + value = 0; + if (PyExceptionInstance_Check(type)) { + if (value) { + PyErr_SetString(PyExc_TypeError, + "instance exception may not have a separate value"); + goto bad; + } + value = type; + type = (PyObject*) Py_TYPE(value); + } else if (PyExceptionClass_Check(type)) { + PyObject *instance_class = NULL; + if (value && PyExceptionInstance_Check(value)) { + instance_class = (PyObject*) Py_TYPE(value); + if (instance_class != type) { + int is_subclass = PyObject_IsSubclass(instance_class, type); + if (!is_subclass) { + instance_class = NULL; + } else if (unlikely(is_subclass == -1)) { + goto bad; + } else { + type = instance_class; + } + } + } + if (!instance_class) { + PyObject *args; + if (!value) + args = PyTuple_New(0); + else if (PyTuple_Check(value)) { + Py_INCREF(value); + args = value; + } else + args = PyTuple_Pack(1, value); + if (!args) + goto bad; + owned_instance = PyObject_Call(type, args, NULL); + Py_DECREF(args); + if (!owned_instance) + goto bad; + value = owned_instance; + if (!PyExceptionInstance_Check(value)) { + PyErr_Format(PyExc_TypeError, + "calling %R should have returned an instance of " + "BaseException, not %R", + type, Py_TYPE(value)); + goto bad; + } + } + } else { + PyErr_SetString(PyExc_TypeError, + "raise: exception class must be a subclass of BaseException"); + goto bad; + } + if (cause) { + PyObject *fixed_cause; + if (cause == Py_None) { + fixed_cause = NULL; + } else if (PyExceptionClass_Check(cause)) { + fixed_cause = PyObject_CallObject(cause, NULL); + if (fixed_cause == NULL) + goto bad; + } else if (PyExceptionInstance_Check(cause)) { + fixed_cause = cause; + Py_INCREF(fixed_cause); + } else { + PyErr_SetString(PyExc_TypeError, + "exception causes must derive from " + "BaseException"); + goto bad; + } + PyException_SetCause(value, fixed_cause); + } + PyErr_SetObject(type, value); + if (tb) { +#if CYTHON_COMPILING_IN_PYPY + PyObject *tmp_type, *tmp_value, *tmp_tb; + PyErr_Fetch(&tmp_type, &tmp_value, &tmp_tb); + Py_INCREF(tb); + PyErr_Restore(tmp_type, tmp_value, tb); + Py_XDECREF(tmp_tb); +#else + PyThreadState *tstate = __Pyx_PyThreadState_Current; + PyObject* tmp_tb = tstate->curexc_traceback; + if (tb != tmp_tb) { + Py_INCREF(tb); + tstate->curexc_traceback = tb; + Py_XDECREF(tmp_tb); + } +#endif + } +bad: + Py_XDECREF(owned_instance); + return; +} +#endif + +/* TypeImport */ + #ifndef __PYX_HAVE_RT_ImportType +#define __PYX_HAVE_RT_ImportType +static PyTypeObject *__Pyx_ImportType(PyObject *module, const char *module_name, const char *class_name, + size_t size, enum __Pyx_ImportType_CheckSize check_size) +{ + PyObject *result = 0; + char warning[200]; + Py_ssize_t basicsize; +#ifdef Py_LIMITED_API + PyObject *py_basicsize; +#endif + result = PyObject_GetAttrString(module, class_name); + if (!result) + goto bad; + if (!PyType_Check(result)) { + PyErr_Format(PyExc_TypeError, + "%.200s.%.200s is not a type object", + module_name, class_name); + goto bad; + } +#ifndef Py_LIMITED_API + basicsize = ((PyTypeObject *)result)->tp_basicsize; +#else + py_basicsize = PyObject_GetAttrString(result, "__basicsize__"); + if (!py_basicsize) + goto bad; + basicsize = PyLong_AsSsize_t(py_basicsize); + Py_DECREF(py_basicsize); + py_basicsize = 0; + if (basicsize == (Py_ssize_t)-1 && PyErr_Occurred()) + goto bad; +#endif + if ((size_t)basicsize < size) { + PyErr_Format(PyExc_ValueError, + "%.200s.%.200s size changed, may indicate binary incompatibility. " + "Expected %zd from C header, got %zd from PyObject", + module_name, class_name, size, basicsize); + goto bad; + } + if (check_size == __Pyx_ImportType_CheckSize_Error && (size_t)basicsize != size) { + PyErr_Format(PyExc_ValueError, + "%.200s.%.200s size changed, may indicate binary incompatibility. " + "Expected %zd from C header, got %zd from PyObject", + module_name, class_name, size, basicsize); + goto bad; + } + else if (check_size == __Pyx_ImportType_CheckSize_Warn && (size_t)basicsize > size) { + PyOS_snprintf(warning, sizeof(warning), + "%s.%s size changed, may indicate binary incompatibility. " + "Expected %zd from C header, got %zd from PyObject", + module_name, class_name, size, basicsize); + if (PyErr_WarnEx(NULL, warning, 0) < 0) goto bad; + } + return (PyTypeObject *)result; +bad: + Py_XDECREF(result); + return NULL; +} +#endif + +/* Import */ + static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { + PyObject *empty_list = 0; + PyObject *module = 0; + PyObject *global_dict = 0; + PyObject *empty_dict = 0; + PyObject *list; + #if PY_MAJOR_VERSION < 3 + PyObject *py_import; + py_import = __Pyx_PyObject_GetAttrStr(__pyx_b, __pyx_n_s_import); + if (!py_import) + goto bad; + #endif + if (from_list) + list = from_list; + else { + empty_list = PyList_New(0); + if (!empty_list) + goto bad; + list = empty_list; + } + global_dict = PyModule_GetDict(__pyx_m); + if (!global_dict) + goto bad; + empty_dict = PyDict_New(); + if (!empty_dict) + goto bad; + { + #if PY_MAJOR_VERSION >= 3 + if (level == -1) { + if ((1) && (strchr(__Pyx_MODULE_NAME, '.'))) { + module = PyImport_ImportModuleLevelObject( + name, global_dict, empty_dict, list, 1); + if (!module) { + if (!PyErr_ExceptionMatches(PyExc_ImportError)) + goto bad; + PyErr_Clear(); + } + } + level = 0; + } + #endif + if (!module) { + #if PY_MAJOR_VERSION < 3 + PyObject *py_level = PyInt_FromLong(level); + if (!py_level) + goto bad; + module = PyObject_CallFunctionObjArgs(py_import, + name, global_dict, empty_dict, list, py_level, (PyObject *)NULL); + Py_DECREF(py_level); + #else + module = PyImport_ImportModuleLevelObject( + name, global_dict, empty_dict, list, level); + #endif + } + } +bad: + #if PY_MAJOR_VERSION < 3 + Py_XDECREF(py_import); + #endif + Py_XDECREF(empty_list); + Py_XDECREF(empty_dict); + return module; +} + +/* CLineInTraceback */ + #ifndef CYTHON_CLINE_IN_TRACEBACK +static int __Pyx_CLineForTraceback(CYTHON_NCP_UNUSED PyThreadState *tstate, int c_line) { + PyObject *use_cline; + PyObject *ptype, *pvalue, *ptraceback; +#if CYTHON_COMPILING_IN_CPYTHON + PyObject **cython_runtime_dict; +#endif + if (unlikely(!__pyx_cython_runtime)) { + return c_line; + } + __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); +#if CYTHON_COMPILING_IN_CPYTHON + cython_runtime_dict = _PyObject_GetDictPtr(__pyx_cython_runtime); + if (likely(cython_runtime_dict)) { + __PYX_PY_DICT_LOOKUP_IF_MODIFIED( + use_cline, *cython_runtime_dict, + __Pyx_PyDict_GetItemStr(*cython_runtime_dict, __pyx_n_s_cline_in_traceback)) + } else +#endif + { + PyObject *use_cline_obj = __Pyx_PyObject_GetAttrStr(__pyx_cython_runtime, __pyx_n_s_cline_in_traceback); + if (use_cline_obj) { + use_cline = PyObject_Not(use_cline_obj) ? Py_False : Py_True; + Py_DECREF(use_cline_obj); + } else { + PyErr_Clear(); + use_cline = NULL; + } + } + if (!use_cline) { + c_line = 0; + (void) PyObject_SetAttr(__pyx_cython_runtime, __pyx_n_s_cline_in_traceback, Py_False); + } + else if (use_cline == Py_False || (use_cline != Py_True && PyObject_Not(use_cline) != 0)) { + c_line = 0; + } + __Pyx_ErrRestoreInState(tstate, ptype, pvalue, ptraceback); + return c_line; +} +#endif + +/* CodeObjectCache */ + static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { + int start = 0, mid = 0, end = count - 1; + if (end >= 0 && code_line > entries[end].code_line) { + return count; + } + while (start < end) { + mid = start + (end - start) / 2; + if (code_line < entries[mid].code_line) { + end = mid; + } else if (code_line > entries[mid].code_line) { + start = mid + 1; + } else { + return mid; + } + } + if (code_line <= entries[mid].code_line) { + return mid; + } else { + return mid + 1; + } +} +static PyCodeObject *__pyx_find_code_object(int code_line) { + PyCodeObject* code_object; + int pos; + if (unlikely(!code_line) || unlikely(!__pyx_code_cache.entries)) { + return NULL; + } + pos = __pyx_bisect_code_objects(__pyx_code_cache.entries, __pyx_code_cache.count, code_line); + if (unlikely(pos >= __pyx_code_cache.count) || unlikely(__pyx_code_cache.entries[pos].code_line != code_line)) { + return NULL; + } + code_object = __pyx_code_cache.entries[pos].code_object; + Py_INCREF(code_object); + return code_object; +} +static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) { + int pos, i; + __Pyx_CodeObjectCacheEntry* entries = __pyx_code_cache.entries; + if (unlikely(!code_line)) { + return; + } + if (unlikely(!entries)) { + entries = (__Pyx_CodeObjectCacheEntry*)PyMem_Malloc(64*sizeof(__Pyx_CodeObjectCacheEntry)); + if (likely(entries)) { + __pyx_code_cache.entries = entries; + __pyx_code_cache.max_count = 64; + __pyx_code_cache.count = 1; + entries[0].code_line = code_line; + entries[0].code_object = code_object; + Py_INCREF(code_object); + } + return; + } + pos = __pyx_bisect_code_objects(__pyx_code_cache.entries, __pyx_code_cache.count, code_line); + if ((pos < __pyx_code_cache.count) && unlikely(__pyx_code_cache.entries[pos].code_line == code_line)) { + PyCodeObject* tmp = entries[pos].code_object; + entries[pos].code_object = code_object; + Py_DECREF(tmp); + return; + } + if (__pyx_code_cache.count == __pyx_code_cache.max_count) { + int new_max = __pyx_code_cache.max_count + 64; + entries = (__Pyx_CodeObjectCacheEntry*)PyMem_Realloc( + __pyx_code_cache.entries, ((size_t)new_max) * sizeof(__Pyx_CodeObjectCacheEntry)); + if (unlikely(!entries)) { + return; + } + __pyx_code_cache.entries = entries; + __pyx_code_cache.max_count = new_max; + } + for (i=__pyx_code_cache.count; i>pos; i--) { + entries[i] = entries[i-1]; + } + entries[pos].code_line = code_line; + entries[pos].code_object = code_object; + __pyx_code_cache.count++; + Py_INCREF(code_object); +} + +/* AddTraceback */ + #include "compile.h" +#include "frameobject.h" +#include "traceback.h" +static PyCodeObject* __Pyx_CreateCodeObjectForTraceback( + const char *funcname, int c_line, + int py_line, const char *filename) { + PyCodeObject *py_code = NULL; + PyObject *py_funcname = NULL; + #if PY_MAJOR_VERSION < 3 + PyObject *py_srcfile = NULL; + py_srcfile = PyString_FromString(filename); + if (!py_srcfile) goto bad; + #endif + if (c_line) { + #if PY_MAJOR_VERSION < 3 + py_funcname = PyString_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line); + if (!py_funcname) goto bad; + #else + py_funcname = PyUnicode_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line); + if (!py_funcname) goto bad; + funcname = PyUnicode_AsUTF8(py_funcname); + if (!funcname) goto bad; + #endif + } + else { + #if PY_MAJOR_VERSION < 3 + py_funcname = PyString_FromString(funcname); + if (!py_funcname) goto bad; + #endif + } + #if PY_MAJOR_VERSION < 3 + py_code = __Pyx_PyCode_New( + 0, + 0, + 0, + 0, + 0, + __pyx_empty_bytes, /*PyObject *code,*/ + __pyx_empty_tuple, /*PyObject *consts,*/ + __pyx_empty_tuple, /*PyObject *names,*/ + __pyx_empty_tuple, /*PyObject *varnames,*/ + __pyx_empty_tuple, /*PyObject *freevars,*/ + __pyx_empty_tuple, /*PyObject *cellvars,*/ + py_srcfile, /*PyObject *filename,*/ + py_funcname, /*PyObject *name,*/ + py_line, + __pyx_empty_bytes /*PyObject *lnotab*/ + ); + Py_DECREF(py_srcfile); + #else + py_code = PyCode_NewEmpty(filename, funcname, py_line); + #endif + Py_XDECREF(py_funcname); // XDECREF since it's only set on Py3 if cline + return py_code; +bad: + Py_XDECREF(py_funcname); + #if PY_MAJOR_VERSION < 3 + Py_XDECREF(py_srcfile); + #endif + return NULL; +} +static void __Pyx_AddTraceback(const char *funcname, int c_line, + int py_line, const char *filename) { + PyCodeObject *py_code = 0; + PyFrameObject *py_frame = 0; + PyThreadState *tstate = __Pyx_PyThreadState_Current; + if (c_line) { + c_line = __Pyx_CLineForTraceback(tstate, c_line); + } + py_code = __pyx_find_code_object(c_line ? -c_line : py_line); + if (!py_code) { + py_code = __Pyx_CreateCodeObjectForTraceback( + funcname, c_line, py_line, filename); + if (!py_code) goto bad; + __pyx_insert_code_object(c_line ? -c_line : py_line, py_code); + } + py_frame = PyFrame_New( + tstate, /*PyThreadState *tstate,*/ + py_code, /*PyCodeObject *code,*/ + __pyx_d, /*PyObject *globals,*/ + 0 /*PyObject *locals*/ + ); + if (!py_frame) goto bad; + __Pyx_PyFrame_SetLineNumber(py_frame, py_line); + PyTraceBack_Here(py_frame); +bad: + Py_XDECREF(py_code); + Py_XDECREF(py_frame); +} + +#if PY_MAJOR_VERSION < 3 +static int __Pyx_GetBuffer(PyObject *obj, Py_buffer *view, int flags) { + if (PyObject_CheckBuffer(obj)) return PyObject_GetBuffer(obj, view, flags); + PyErr_Format(PyExc_TypeError, "'%.200s' does not have the buffer interface", Py_TYPE(obj)->tp_name); + return -1; +} +static void __Pyx_ReleaseBuffer(Py_buffer *view) { + PyObject *obj = view->obj; + if (!obj) return; + if (PyObject_CheckBuffer(obj)) { + PyBuffer_Release(view); + return; + } + if ((0)) {} + view->obj = NULL; + Py_DECREF(obj); +} +#endif + + + /* CIntFromPyVerify */ + #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ + __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 0) +#define __PYX_VERIFY_RETURN_INT_EXC(target_type, func_type, func_value)\ + __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 1) +#define __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, exc)\ + {\ + func_type value = func_value;\ + if (sizeof(target_type) < sizeof(func_type)) {\ + if (unlikely(value != (func_type) (target_type) value)) {\ + func_type zero = 0;\ + if (exc && unlikely(value == (func_type)-1 && PyErr_Occurred()))\ + return (target_type) -1;\ + if (is_unsigned && unlikely(value < zero))\ + goto raise_neg_overflow;\ + else\ + goto raise_overflow;\ + }\ + }\ + return (target_type) value;\ + } + +/* Declarations */ + #if CYTHON_CCOMPLEX + #ifdef __cplusplus + static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) { + return ::std::complex< float >(x, y); + } + #else + static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) { + return x + y*(__pyx_t_float_complex)_Complex_I; + } + #endif +#else + static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) { + __pyx_t_float_complex z; + z.real = x; + z.imag = y; + return z; + } +#endif + +/* Arithmetic */ + #if CYTHON_CCOMPLEX +#else + static CYTHON_INLINE int __Pyx_c_eq_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { + return (a.real == b.real) && (a.imag == b.imag); + } + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_sum_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { + __pyx_t_float_complex z; + z.real = a.real + b.real; + z.imag = a.imag + b.imag; + return z; + } + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_diff_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { + __pyx_t_float_complex z; + z.real = a.real - b.real; + z.imag = a.imag - b.imag; + return z; + } + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_prod_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { + __pyx_t_float_complex z; + z.real = a.real * b.real - a.imag * b.imag; + z.imag = a.real * b.imag + a.imag * b.real; + return z; + } + #if 1 + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_quot_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { + if (b.imag == 0) { + return __pyx_t_float_complex_from_parts(a.real / b.real, a.imag / b.real); + } else if (fabsf(b.real) >= fabsf(b.imag)) { + if (b.real == 0 && b.imag == 0) { + return __pyx_t_float_complex_from_parts(a.real / b.real, a.imag / b.imag); + } else { + float r = b.imag / b.real; + float s = (float)(1.0) / (b.real + b.imag * r); + return __pyx_t_float_complex_from_parts( + (a.real + a.imag * r) * s, (a.imag - a.real * r) * s); + } + } else { + float r = b.real / b.imag; + float s = (float)(1.0) / (b.imag + b.real * r); + return __pyx_t_float_complex_from_parts( + (a.real * r + a.imag) * s, (a.imag * r - a.real) * s); + } + } + #else + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_quot_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { + if (b.imag == 0) { + return __pyx_t_float_complex_from_parts(a.real / b.real, a.imag / b.real); + } else { + float denom = b.real * b.real + b.imag * b.imag; + return __pyx_t_float_complex_from_parts( + (a.real * b.real + a.imag * b.imag) / denom, + (a.imag * b.real - a.real * b.imag) / denom); + } + } + #endif + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_neg_float(__pyx_t_float_complex a) { + __pyx_t_float_complex z; + z.real = -a.real; + z.imag = -a.imag; + return z; + } + static CYTHON_INLINE int __Pyx_c_is_zero_float(__pyx_t_float_complex a) { + return (a.real == 0) && (a.imag == 0); + } + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_conj_float(__pyx_t_float_complex a) { + __pyx_t_float_complex z; + z.real = a.real; + z.imag = -a.imag; + return z; + } + #if 1 + static CYTHON_INLINE float __Pyx_c_abs_float(__pyx_t_float_complex z) { + #if !defined(HAVE_HYPOT) || defined(_MSC_VER) + return sqrtf(z.real*z.real + z.imag*z.imag); + #else + return hypotf(z.real, z.imag); + #endif + } + static CYTHON_INLINE __pyx_t_float_complex __Pyx_c_pow_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { + __pyx_t_float_complex z; + float r, lnr, theta, z_r, z_theta; + if (b.imag == 0 && b.real == (int)b.real) { + if (b.real < 0) { + float denom = a.real * a.real + a.imag * a.imag; + a.real = a.real / denom; + a.imag = -a.imag / denom; + b.real = -b.real; + } + switch ((int)b.real) { + case 0: + z.real = 1; + z.imag = 0; + return z; + case 1: + return a; + case 2: + return __Pyx_c_prod_float(a, a); + case 3: + z = __Pyx_c_prod_float(a, a); + return __Pyx_c_prod_float(z, a); + case 4: + z = __Pyx_c_prod_float(a, a); + return __Pyx_c_prod_float(z, z); + } + } + if (a.imag == 0) { + if (a.real == 0) { + return a; + } else if (b.imag == 0) { + z.real = powf(a.real, b.real); + z.imag = 0; + return z; + } else if (a.real > 0) { + r = a.real; + theta = 0; + } else { + r = -a.real; + theta = atan2f(0.0, -1.0); + } + } else { + r = __Pyx_c_abs_float(a); + theta = atan2f(a.imag, a.real); + } + lnr = logf(r); + z_r = expf(lnr * b.real - theta * b.imag); + z_theta = theta * b.real + lnr * b.imag; + z.real = z_r * cosf(z_theta); + z.imag = z_r * sinf(z_theta); + return z; + } + #endif +#endif + +/* Declarations */ + #if CYTHON_CCOMPLEX + #ifdef __cplusplus + static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) { + return ::std::complex< double >(x, y); + } + #else + static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) { + return x + y*(__pyx_t_double_complex)_Complex_I; + } + #endif +#else + static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) { + __pyx_t_double_complex z; + z.real = x; + z.imag = y; + return z; + } +#endif + +/* Arithmetic */ + #if CYTHON_CCOMPLEX +#else + static CYTHON_INLINE int __Pyx_c_eq_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { + return (a.real == b.real) && (a.imag == b.imag); + } + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_sum_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { + __pyx_t_double_complex z; + z.real = a.real + b.real; + z.imag = a.imag + b.imag; + return z; + } + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_diff_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { + __pyx_t_double_complex z; + z.real = a.real - b.real; + z.imag = a.imag - b.imag; + return z; + } + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_prod_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { + __pyx_t_double_complex z; + z.real = a.real * b.real - a.imag * b.imag; + z.imag = a.real * b.imag + a.imag * b.real; + return z; + } + #if 1 + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_quot_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { + if (b.imag == 0) { + return __pyx_t_double_complex_from_parts(a.real / b.real, a.imag / b.real); + } else if (fabs(b.real) >= fabs(b.imag)) { + if (b.real == 0 && b.imag == 0) { + return __pyx_t_double_complex_from_parts(a.real / b.real, a.imag / b.imag); + } else { + double r = b.imag / b.real; + double s = (double)(1.0) / (b.real + b.imag * r); + return __pyx_t_double_complex_from_parts( + (a.real + a.imag * r) * s, (a.imag - a.real * r) * s); + } + } else { + double r = b.real / b.imag; + double s = (double)(1.0) / (b.imag + b.real * r); + return __pyx_t_double_complex_from_parts( + (a.real * r + a.imag) * s, (a.imag * r - a.real) * s); + } + } + #else + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_quot_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { + if (b.imag == 0) { + return __pyx_t_double_complex_from_parts(a.real / b.real, a.imag / b.real); + } else { + double denom = b.real * b.real + b.imag * b.imag; + return __pyx_t_double_complex_from_parts( + (a.real * b.real + a.imag * b.imag) / denom, + (a.imag * b.real - a.real * b.imag) / denom); + } + } + #endif + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_neg_double(__pyx_t_double_complex a) { + __pyx_t_double_complex z; + z.real = -a.real; + z.imag = -a.imag; + return z; + } + static CYTHON_INLINE int __Pyx_c_is_zero_double(__pyx_t_double_complex a) { + return (a.real == 0) && (a.imag == 0); + } + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_conj_double(__pyx_t_double_complex a) { + __pyx_t_double_complex z; + z.real = a.real; + z.imag = -a.imag; + return z; + } + #if 1 + static CYTHON_INLINE double __Pyx_c_abs_double(__pyx_t_double_complex z) { + #if !defined(HAVE_HYPOT) || defined(_MSC_VER) + return sqrt(z.real*z.real + z.imag*z.imag); + #else + return hypot(z.real, z.imag); + #endif + } + static CYTHON_INLINE __pyx_t_double_complex __Pyx_c_pow_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { + __pyx_t_double_complex z; + double r, lnr, theta, z_r, z_theta; + if (b.imag == 0 && b.real == (int)b.real) { + if (b.real < 0) { + double denom = a.real * a.real + a.imag * a.imag; + a.real = a.real / denom; + a.imag = -a.imag / denom; + b.real = -b.real; + } + switch ((int)b.real) { + case 0: + z.real = 1; + z.imag = 0; + return z; + case 1: + return a; + case 2: + return __Pyx_c_prod_double(a, a); + case 3: + z = __Pyx_c_prod_double(a, a); + return __Pyx_c_prod_double(z, a); + case 4: + z = __Pyx_c_prod_double(a, a); + return __Pyx_c_prod_double(z, z); + } + } + if (a.imag == 0) { + if (a.real == 0) { + return a; + } else if (b.imag == 0) { + z.real = pow(a.real, b.real); + z.imag = 0; + return z; + } else if (a.real > 0) { + r = a.real; + theta = 0; + } else { + r = -a.real; + theta = atan2(0.0, -1.0); + } + } else { + r = __Pyx_c_abs_double(a); + theta = atan2(a.imag, a.real); + } + lnr = log(r); + z_r = exp(lnr * b.real - theta * b.imag); + z_theta = theta * b.real + lnr * b.imag; + z.real = z_r * cos(z_theta); + z.imag = z_r * sin(z_theta); + return z; + } + #endif +#endif + +/* CIntToPy */ + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_unsigned_int(unsigned int value) { +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wconversion" +#endif + const unsigned int neg_one = (unsigned int) -1, const_zero = (unsigned int) 0; +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic pop +#endif + const int is_unsigned = neg_one > const_zero; + if (is_unsigned) { + if (sizeof(unsigned int) < sizeof(long)) { + return PyInt_FromLong((long) value); + } else if (sizeof(unsigned int) <= sizeof(unsigned long)) { + return PyLong_FromUnsignedLong((unsigned long) value); +#ifdef HAVE_LONG_LONG + } else if (sizeof(unsigned int) <= sizeof(unsigned PY_LONG_LONG)) { + return PyLong_FromUnsignedLongLong((unsigned PY_LONG_LONG) value); +#endif + } + } else { + if (sizeof(unsigned int) <= sizeof(long)) { + return PyInt_FromLong((long) value); +#ifdef HAVE_LONG_LONG + } else if (sizeof(unsigned int) <= sizeof(PY_LONG_LONG)) { + return PyLong_FromLongLong((PY_LONG_LONG) value); +#endif + } + } + { + int one = 1; int little = (int)*(unsigned char *)&one; + unsigned char *bytes = (unsigned char *)&value; + return _PyLong_FromByteArray(bytes, sizeof(unsigned int), + little, !is_unsigned); + } +} + +/* CIntFromPy */ + static CYTHON_INLINE unsigned int __Pyx_PyInt_As_unsigned_int(PyObject *x) { +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wconversion" +#endif + const unsigned int neg_one = (unsigned int) -1, const_zero = (unsigned int) 0; +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic pop +#endif + const int is_unsigned = neg_one > const_zero; +#if PY_MAJOR_VERSION < 3 + if (likely(PyInt_Check(x))) { + if (sizeof(unsigned int) < sizeof(long)) { + __PYX_VERIFY_RETURN_INT(unsigned int, long, PyInt_AS_LONG(x)) + } else { + long val = PyInt_AS_LONG(x); + if (is_unsigned && unlikely(val < 0)) { + goto raise_neg_overflow; + } + return (unsigned int) val; + } + } else +#endif + if (likely(PyLong_Check(x))) { + if (is_unsigned) { +#if CYTHON_USE_PYLONG_INTERNALS + const digit* digits = ((PyLongObject*)x)->ob_digit; + switch (Py_SIZE(x)) { + case 0: return (unsigned int) 0; + case 1: __PYX_VERIFY_RETURN_INT(unsigned int, digit, digits[0]) + case 2: + if (8 * sizeof(unsigned int) > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) >= 2 * PyLong_SHIFT) { + return (unsigned int) (((((unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0])); + } + } + break; + case 3: + if (8 * sizeof(unsigned int) > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) >= 3 * PyLong_SHIFT) { + return (unsigned int) (((((((unsigned int)digits[2]) << PyLong_SHIFT) | (unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0])); + } + } + break; + case 4: + if (8 * sizeof(unsigned int) > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) >= 4 * PyLong_SHIFT) { + return (unsigned int) (((((((((unsigned int)digits[3]) << PyLong_SHIFT) | (unsigned int)digits[2]) << PyLong_SHIFT) | (unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0])); + } + } + break; + } +#endif +#if CYTHON_COMPILING_IN_CPYTHON + if (unlikely(Py_SIZE(x) < 0)) { + goto raise_neg_overflow; + } +#else + { + int result = PyObject_RichCompareBool(x, Py_False, Py_LT); + if (unlikely(result < 0)) + return (unsigned int) -1; + if (unlikely(result == 1)) + goto raise_neg_overflow; + } +#endif + if (sizeof(unsigned int) <= sizeof(unsigned long)) { + __PYX_VERIFY_RETURN_INT_EXC(unsigned int, unsigned long, PyLong_AsUnsignedLong(x)) +#ifdef HAVE_LONG_LONG + } else if (sizeof(unsigned int) <= sizeof(unsigned PY_LONG_LONG)) { + __PYX_VERIFY_RETURN_INT_EXC(unsigned int, unsigned PY_LONG_LONG, PyLong_AsUnsignedLongLong(x)) +#endif + } + } else { +#if CYTHON_USE_PYLONG_INTERNALS + const digit* digits = ((PyLongObject*)x)->ob_digit; + switch (Py_SIZE(x)) { + case 0: return (unsigned int) 0; + case -1: __PYX_VERIFY_RETURN_INT(unsigned int, sdigit, (sdigit) (-(sdigit)digits[0])) + case 1: __PYX_VERIFY_RETURN_INT(unsigned int, digit, +digits[0]) + case -2: + if (8 * sizeof(unsigned int) - 1 > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, long, -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) - 1 > 2 * PyLong_SHIFT) { + return (unsigned int) (((unsigned int)-1)*(((((unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0]))); + } + } + break; + case 2: + if (8 * sizeof(unsigned int) > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) - 1 > 2 * PyLong_SHIFT) { + return (unsigned int) ((((((unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0]))); + } + } + break; + case -3: + if (8 * sizeof(unsigned int) - 1 > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, long, -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) - 1 > 3 * PyLong_SHIFT) { + return (unsigned int) (((unsigned int)-1)*(((((((unsigned int)digits[2]) << PyLong_SHIFT) | (unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0]))); + } + } + break; + case 3: + if (8 * sizeof(unsigned int) > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) - 1 > 3 * PyLong_SHIFT) { + return (unsigned int) ((((((((unsigned int)digits[2]) << PyLong_SHIFT) | (unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0]))); + } + } + break; + case -4: + if (8 * sizeof(unsigned int) - 1 > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, long, -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) - 1 > 4 * PyLong_SHIFT) { + return (unsigned int) (((unsigned int)-1)*(((((((((unsigned int)digits[3]) << PyLong_SHIFT) | (unsigned int)digits[2]) << PyLong_SHIFT) | (unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0]))); + } + } + break; + case 4: + if (8 * sizeof(unsigned int) > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(unsigned int, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(unsigned int) - 1 > 4 * PyLong_SHIFT) { + return (unsigned int) ((((((((((unsigned int)digits[3]) << PyLong_SHIFT) | (unsigned int)digits[2]) << PyLong_SHIFT) | (unsigned int)digits[1]) << PyLong_SHIFT) | (unsigned int)digits[0]))); + } + } + break; + } +#endif + if (sizeof(unsigned int) <= sizeof(long)) { + __PYX_VERIFY_RETURN_INT_EXC(unsigned int, long, PyLong_AsLong(x)) +#ifdef HAVE_LONG_LONG + } else if (sizeof(unsigned int) <= sizeof(PY_LONG_LONG)) { + __PYX_VERIFY_RETURN_INT_EXC(unsigned int, PY_LONG_LONG, PyLong_AsLongLong(x)) +#endif + } + } + { +#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray) + PyErr_SetString(PyExc_RuntimeError, + "_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers"); +#else + unsigned int val; + PyObject *v = __Pyx_PyNumber_IntOrLong(x); + #if PY_MAJOR_VERSION < 3 + if (likely(v) && !PyLong_Check(v)) { + PyObject *tmp = v; + v = PyNumber_Long(tmp); + Py_DECREF(tmp); + } + #endif + if (likely(v)) { + int one = 1; int is_little = (int)*(unsigned char *)&one; + unsigned char *bytes = (unsigned char *)&val; + int ret = _PyLong_AsByteArray((PyLongObject *)v, + bytes, sizeof(val), + is_little, !is_unsigned); + Py_DECREF(v); + if (likely(!ret)) + return val; + } +#endif + return (unsigned int) -1; + } + } else { + unsigned int val; + PyObject *tmp = __Pyx_PyNumber_IntOrLong(x); + if (!tmp) return (unsigned int) -1; + val = __Pyx_PyInt_As_unsigned_int(tmp); + Py_DECREF(tmp); + return val; + } +raise_overflow: + PyErr_SetString(PyExc_OverflowError, + "value too large to convert to unsigned int"); + return (unsigned int) -1; +raise_neg_overflow: + PyErr_SetString(PyExc_OverflowError, + "can't convert negative value to unsigned int"); + return (unsigned int) -1; +} + +/* CIntToPy */ + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wconversion" +#endif + const long neg_one = (long) -1, const_zero = (long) 0; +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic pop +#endif + const int is_unsigned = neg_one > const_zero; + if (is_unsigned) { + if (sizeof(long) < sizeof(long)) { + return PyInt_FromLong((long) value); + } else if (sizeof(long) <= sizeof(unsigned long)) { + return PyLong_FromUnsignedLong((unsigned long) value); +#ifdef HAVE_LONG_LONG + } else if (sizeof(long) <= sizeof(unsigned PY_LONG_LONG)) { + return PyLong_FromUnsignedLongLong((unsigned PY_LONG_LONG) value); +#endif + } + } else { + if (sizeof(long) <= sizeof(long)) { + return PyInt_FromLong((long) value); +#ifdef HAVE_LONG_LONG + } else if (sizeof(long) <= sizeof(PY_LONG_LONG)) { + return PyLong_FromLongLong((PY_LONG_LONG) value); +#endif + } + } + { + int one = 1; int little = (int)*(unsigned char *)&one; + unsigned char *bytes = (unsigned char *)&value; + return _PyLong_FromByteArray(bytes, sizeof(long), + little, !is_unsigned); + } +} + +/* CIntFromPy */ + static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wconversion" +#endif + const long neg_one = (long) -1, const_zero = (long) 0; +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic pop +#endif + const int is_unsigned = neg_one > const_zero; +#if PY_MAJOR_VERSION < 3 + if (likely(PyInt_Check(x))) { + if (sizeof(long) < sizeof(long)) { + __PYX_VERIFY_RETURN_INT(long, long, PyInt_AS_LONG(x)) + } else { + long val = PyInt_AS_LONG(x); + if (is_unsigned && unlikely(val < 0)) { + goto raise_neg_overflow; + } + return (long) val; + } + } else +#endif + if (likely(PyLong_Check(x))) { + if (is_unsigned) { +#if CYTHON_USE_PYLONG_INTERNALS + const digit* digits = ((PyLongObject*)x)->ob_digit; + switch (Py_SIZE(x)) { + case 0: return (long) 0; + case 1: __PYX_VERIFY_RETURN_INT(long, digit, digits[0]) + case 2: + if (8 * sizeof(long) > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) >= 2 * PyLong_SHIFT) { + return (long) (((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0])); + } + } + break; + case 3: + if (8 * sizeof(long) > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) >= 3 * PyLong_SHIFT) { + return (long) (((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0])); + } + } + break; + case 4: + if (8 * sizeof(long) > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) >= 4 * PyLong_SHIFT) { + return (long) (((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0])); + } + } + break; + } +#endif +#if CYTHON_COMPILING_IN_CPYTHON + if (unlikely(Py_SIZE(x) < 0)) { + goto raise_neg_overflow; + } +#else + { + int result = PyObject_RichCompareBool(x, Py_False, Py_LT); + if (unlikely(result < 0)) + return (long) -1; + if (unlikely(result == 1)) + goto raise_neg_overflow; + } +#endif + if (sizeof(long) <= sizeof(unsigned long)) { + __PYX_VERIFY_RETURN_INT_EXC(long, unsigned long, PyLong_AsUnsignedLong(x)) +#ifdef HAVE_LONG_LONG + } else if (sizeof(long) <= sizeof(unsigned PY_LONG_LONG)) { + __PYX_VERIFY_RETURN_INT_EXC(long, unsigned PY_LONG_LONG, PyLong_AsUnsignedLongLong(x)) +#endif + } + } else { +#if CYTHON_USE_PYLONG_INTERNALS + const digit* digits = ((PyLongObject*)x)->ob_digit; + switch (Py_SIZE(x)) { + case 0: return (long) 0; + case -1: __PYX_VERIFY_RETURN_INT(long, sdigit, (sdigit) (-(sdigit)digits[0])) + case 1: __PYX_VERIFY_RETURN_INT(long, digit, +digits[0]) + case -2: + if (8 * sizeof(long) - 1 > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { + return (long) (((long)-1)*(((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); + } + } + break; + case 2: + if (8 * sizeof(long) > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { + return (long) ((((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); + } + } + break; + case -3: + if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { + return (long) (((long)-1)*(((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); + } + } + break; + case 3: + if (8 * sizeof(long) > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { + return (long) ((((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); + } + } + break; + case -4: + if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { + return (long) (((long)-1)*(((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); + } + } + break; + case 4: + if (8 * sizeof(long) > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { + return (long) ((((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); + } + } + break; + } +#endif + if (sizeof(long) <= sizeof(long)) { + __PYX_VERIFY_RETURN_INT_EXC(long, long, PyLong_AsLong(x)) +#ifdef HAVE_LONG_LONG + } else if (sizeof(long) <= sizeof(PY_LONG_LONG)) { + __PYX_VERIFY_RETURN_INT_EXC(long, PY_LONG_LONG, PyLong_AsLongLong(x)) +#endif + } + } + { +#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray) + PyErr_SetString(PyExc_RuntimeError, + "_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers"); +#else + long val; + PyObject *v = __Pyx_PyNumber_IntOrLong(x); + #if PY_MAJOR_VERSION < 3 + if (likely(v) && !PyLong_Check(v)) { + PyObject *tmp = v; + v = PyNumber_Long(tmp); + Py_DECREF(tmp); + } + #endif + if (likely(v)) { + int one = 1; int is_little = (int)*(unsigned char *)&one; + unsigned char *bytes = (unsigned char *)&val; + int ret = _PyLong_AsByteArray((PyLongObject *)v, + bytes, sizeof(val), + is_little, !is_unsigned); + Py_DECREF(v); + if (likely(!ret)) + return val; + } +#endif + return (long) -1; + } + } else { + long val; + PyObject *tmp = __Pyx_PyNumber_IntOrLong(x); + if (!tmp) return (long) -1; + val = __Pyx_PyInt_As_long(tmp); + Py_DECREF(tmp); + return val; + } +raise_overflow: + PyErr_SetString(PyExc_OverflowError, + "value too large to convert to long"); + return (long) -1; +raise_neg_overflow: + PyErr_SetString(PyExc_OverflowError, + "can't convert negative value to long"); + return (long) -1; +} + +/* CIntFromPy */ + static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wconversion" +#endif + const int neg_one = (int) -1, const_zero = (int) 0; +#ifdef __Pyx_HAS_GCC_DIAGNOSTIC +#pragma GCC diagnostic pop +#endif + const int is_unsigned = neg_one > const_zero; +#if PY_MAJOR_VERSION < 3 + if (likely(PyInt_Check(x))) { + if (sizeof(int) < sizeof(long)) { + __PYX_VERIFY_RETURN_INT(int, long, PyInt_AS_LONG(x)) + } else { + long val = PyInt_AS_LONG(x); + if (is_unsigned && unlikely(val < 0)) { + goto raise_neg_overflow; + } + return (int) val; + } + } else +#endif + if (likely(PyLong_Check(x))) { + if (is_unsigned) { +#if CYTHON_USE_PYLONG_INTERNALS + const digit* digits = ((PyLongObject*)x)->ob_digit; + switch (Py_SIZE(x)) { + case 0: return (int) 0; + case 1: __PYX_VERIFY_RETURN_INT(int, digit, digits[0]) + case 2: + if (8 * sizeof(int) > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) >= 2 * PyLong_SHIFT) { + return (int) (((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0])); + } + } + break; + case 3: + if (8 * sizeof(int) > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) >= 3 * PyLong_SHIFT) { + return (int) (((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0])); + } + } + break; + case 4: + if (8 * sizeof(int) > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) >= 4 * PyLong_SHIFT) { + return (int) (((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0])); + } + } + break; + } +#endif +#if CYTHON_COMPILING_IN_CPYTHON + if (unlikely(Py_SIZE(x) < 0)) { + goto raise_neg_overflow; + } +#else + { + int result = PyObject_RichCompareBool(x, Py_False, Py_LT); + if (unlikely(result < 0)) + return (int) -1; + if (unlikely(result == 1)) + goto raise_neg_overflow; + } +#endif + if (sizeof(int) <= sizeof(unsigned long)) { + __PYX_VERIFY_RETURN_INT_EXC(int, unsigned long, PyLong_AsUnsignedLong(x)) +#ifdef HAVE_LONG_LONG + } else if (sizeof(int) <= sizeof(unsigned PY_LONG_LONG)) { + __PYX_VERIFY_RETURN_INT_EXC(int, unsigned PY_LONG_LONG, PyLong_AsUnsignedLongLong(x)) +#endif + } + } else { +#if CYTHON_USE_PYLONG_INTERNALS + const digit* digits = ((PyLongObject*)x)->ob_digit; + switch (Py_SIZE(x)) { + case 0: return (int) 0; + case -1: __PYX_VERIFY_RETURN_INT(int, sdigit, (sdigit) (-(sdigit)digits[0])) + case 1: __PYX_VERIFY_RETURN_INT(int, digit, +digits[0]) + case -2: + if (8 * sizeof(int) - 1 > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) - 1 > 2 * PyLong_SHIFT) { + return (int) (((int)-1)*(((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); + } + } + break; + case 2: + if (8 * sizeof(int) > 1 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 2 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) - 1 > 2 * PyLong_SHIFT) { + return (int) ((((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); + } + } + break; + case -3: + if (8 * sizeof(int) - 1 > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) - 1 > 3 * PyLong_SHIFT) { + return (int) (((int)-1)*(((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); + } + } + break; + case 3: + if (8 * sizeof(int) > 2 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 3 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) - 1 > 3 * PyLong_SHIFT) { + return (int) ((((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); + } + } + break; + case -4: + if (8 * sizeof(int) - 1 > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) - 1 > 4 * PyLong_SHIFT) { + return (int) (((int)-1)*(((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); + } + } + break; + case 4: + if (8 * sizeof(int) > 3 * PyLong_SHIFT) { + if (8 * sizeof(unsigned long) > 4 * PyLong_SHIFT) { + __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) + } else if (8 * sizeof(int) - 1 > 4 * PyLong_SHIFT) { + return (int) ((((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); + } + } + break; + } +#endif + if (sizeof(int) <= sizeof(long)) { + __PYX_VERIFY_RETURN_INT_EXC(int, long, PyLong_AsLong(x)) +#ifdef HAVE_LONG_LONG + } else if (sizeof(int) <= sizeof(PY_LONG_LONG)) { + __PYX_VERIFY_RETURN_INT_EXC(int, PY_LONG_LONG, PyLong_AsLongLong(x)) +#endif + } + } + { +#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray) + PyErr_SetString(PyExc_RuntimeError, + "_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers"); +#else + int val; + PyObject *v = __Pyx_PyNumber_IntOrLong(x); + #if PY_MAJOR_VERSION < 3 + if (likely(v) && !PyLong_Check(v)) { + PyObject *tmp = v; + v = PyNumber_Long(tmp); + Py_DECREF(tmp); + } + #endif + if (likely(v)) { + int one = 1; int is_little = (int)*(unsigned char *)&one; + unsigned char *bytes = (unsigned char *)&val; + int ret = _PyLong_AsByteArray((PyLongObject *)v, + bytes, sizeof(val), + is_little, !is_unsigned); + Py_DECREF(v); + if (likely(!ret)) + return val; + } +#endif + return (int) -1; + } + } else { + int val; + PyObject *tmp = __Pyx_PyNumber_IntOrLong(x); + if (!tmp) return (int) -1; + val = __Pyx_PyInt_As_int(tmp); + Py_DECREF(tmp); + return val; + } +raise_overflow: + PyErr_SetString(PyExc_OverflowError, + "value too large to convert to int"); + return (int) -1; +raise_neg_overflow: + PyErr_SetString(PyExc_OverflowError, + "can't convert negative value to int"); + return (int) -1; +} + +/* FastTypeChecks */ + #if CYTHON_COMPILING_IN_CPYTHON +static int __Pyx_InBases(PyTypeObject *a, PyTypeObject *b) { + while (a) { + a = a->tp_base; + if (a == b) + return 1; + } + return b == &PyBaseObject_Type; +} +static CYTHON_INLINE int __Pyx_IsSubtype(PyTypeObject *a, PyTypeObject *b) { + PyObject *mro; + if (a == b) return 1; + mro = a->tp_mro; + if (likely(mro)) { + Py_ssize_t i, n; + n = PyTuple_GET_SIZE(mro); + for (i = 0; i < n; i++) { + if (PyTuple_GET_ITEM(mro, i) == (PyObject *)b) + return 1; + } + return 0; + } + return __Pyx_InBases(a, b); +} +#if PY_MAJOR_VERSION == 2 +static int __Pyx_inner_PyErr_GivenExceptionMatches2(PyObject *err, PyObject* exc_type1, PyObject* exc_type2) { + PyObject *exception, *value, *tb; + int res; + __Pyx_PyThreadState_declare + __Pyx_PyThreadState_assign + __Pyx_ErrFetch(&exception, &value, &tb); + res = exc_type1 ? PyObject_IsSubclass(err, exc_type1) : 0; + if (unlikely(res == -1)) { + PyErr_WriteUnraisable(err); + res = 0; + } + if (!res) { + res = PyObject_IsSubclass(err, exc_type2); + if (unlikely(res == -1)) { + PyErr_WriteUnraisable(err); + res = 0; + } + } + __Pyx_ErrRestore(exception, value, tb); + return res; +} +#else +static CYTHON_INLINE int __Pyx_inner_PyErr_GivenExceptionMatches2(PyObject *err, PyObject* exc_type1, PyObject *exc_type2) { + int res = exc_type1 ? __Pyx_IsSubtype((PyTypeObject*)err, (PyTypeObject*)exc_type1) : 0; + if (!res) { + res = __Pyx_IsSubtype((PyTypeObject*)err, (PyTypeObject*)exc_type2); + } + return res; +} +#endif +static int __Pyx_PyErr_GivenExceptionMatchesTuple(PyObject *exc_type, PyObject *tuple) { + Py_ssize_t i, n; + assert(PyExceptionClass_Check(exc_type)); + n = PyTuple_GET_SIZE(tuple); +#if PY_MAJOR_VERSION >= 3 + for (i=0; ip) { + #if PY_MAJOR_VERSION < 3 + if (t->is_unicode) { + *t->p = PyUnicode_DecodeUTF8(t->s, t->n - 1, NULL); + } else if (t->intern) { + *t->p = PyString_InternFromString(t->s); + } else { + *t->p = PyString_FromStringAndSize(t->s, t->n - 1); + } + #else + if (t->is_unicode | t->is_str) { + if (t->intern) { + *t->p = PyUnicode_InternFromString(t->s); + } else if (t->encoding) { + *t->p = PyUnicode_Decode(t->s, t->n - 1, t->encoding, NULL); + } else { + *t->p = PyUnicode_FromStringAndSize(t->s, t->n - 1); + } + } else { + *t->p = PyBytes_FromStringAndSize(t->s, t->n - 1); + } + #endif + if (!*t->p) + return -1; + if (PyObject_Hash(*t->p) == -1) + return -1; + ++t; + } + return 0; +} + +static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(const char* c_str) { + return __Pyx_PyUnicode_FromStringAndSize(c_str, (Py_ssize_t)strlen(c_str)); +} +static CYTHON_INLINE const char* __Pyx_PyObject_AsString(PyObject* o) { + Py_ssize_t ignore; + return __Pyx_PyObject_AsStringAndSize(o, &ignore); +} +#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT +#if !CYTHON_PEP393_ENABLED +static const char* __Pyx_PyUnicode_AsStringAndSize(PyObject* o, Py_ssize_t *length) { + char* defenc_c; + PyObject* defenc = _PyUnicode_AsDefaultEncodedString(o, NULL); + if (!defenc) return NULL; + defenc_c = PyBytes_AS_STRING(defenc); +#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII + { + char* end = defenc_c + PyBytes_GET_SIZE(defenc); + char* c; + for (c = defenc_c; c < end; c++) { + if ((unsigned char) (*c) >= 128) { + PyUnicode_AsASCIIString(o); + return NULL; + } + } + } +#endif + *length = PyBytes_GET_SIZE(defenc); + return defenc_c; +} +#else +static CYTHON_INLINE const char* __Pyx_PyUnicode_AsStringAndSize(PyObject* o, Py_ssize_t *length) { + if (unlikely(__Pyx_PyUnicode_READY(o) == -1)) return NULL; +#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII + if (likely(PyUnicode_IS_ASCII(o))) { + *length = PyUnicode_GET_LENGTH(o); + return PyUnicode_AsUTF8(o); + } else { + PyUnicode_AsASCIIString(o); + return NULL; + } +#else + return PyUnicode_AsUTF8AndSize(o, length); +#endif +} +#endif +#endif +static CYTHON_INLINE const char* __Pyx_PyObject_AsStringAndSize(PyObject* o, Py_ssize_t *length) { +#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT + if ( +#if PY_MAJOR_VERSION < 3 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII + __Pyx_sys_getdefaultencoding_not_ascii && +#endif + PyUnicode_Check(o)) { + return __Pyx_PyUnicode_AsStringAndSize(o, length); + } else +#endif +#if (!CYTHON_COMPILING_IN_PYPY) || (defined(PyByteArray_AS_STRING) && defined(PyByteArray_GET_SIZE)) + if (PyByteArray_Check(o)) { + *length = PyByteArray_GET_SIZE(o); + return PyByteArray_AS_STRING(o); + } else +#endif + { + char* result; + int r = PyBytes_AsStringAndSize(o, &result, length); + if (unlikely(r < 0)) { + return NULL; + } else { + return result; + } + } +} +static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject* x) { + int is_true = x == Py_True; + if (is_true | (x == Py_False) | (x == Py_None)) return is_true; + else return PyObject_IsTrue(x); +} +static CYTHON_INLINE int __Pyx_PyObject_IsTrueAndDecref(PyObject* x) { + int retval; + if (unlikely(!x)) return -1; + retval = __Pyx_PyObject_IsTrue(x); + Py_DECREF(x); + return retval; +} +static PyObject* __Pyx_PyNumber_IntOrLongWrongResultType(PyObject* result, const char* type_name) { +#if PY_MAJOR_VERSION >= 3 + if (PyLong_Check(result)) { + if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, + "__int__ returned non-int (type %.200s). " + "The ability to return an instance of a strict subclass of int " + "is deprecated, and may be removed in a future version of Python.", + Py_TYPE(result)->tp_name)) { + Py_DECREF(result); + return NULL; + } + return result; + } +#endif + PyErr_Format(PyExc_TypeError, + "__%.4s__ returned non-%.4s (type %.200s)", + type_name, type_name, Py_TYPE(result)->tp_name); + Py_DECREF(result); + return NULL; +} +static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x) { +#if CYTHON_USE_TYPE_SLOTS + PyNumberMethods *m; +#endif + const char *name = NULL; + PyObject *res = NULL; +#if PY_MAJOR_VERSION < 3 + if (likely(PyInt_Check(x) || PyLong_Check(x))) +#else + if (likely(PyLong_Check(x))) +#endif + return __Pyx_NewRef(x); +#if CYTHON_USE_TYPE_SLOTS + m = Py_TYPE(x)->tp_as_number; + #if PY_MAJOR_VERSION < 3 + if (m && m->nb_int) { + name = "int"; + res = m->nb_int(x); + } + else if (m && m->nb_long) { + name = "long"; + res = m->nb_long(x); + } + #else + if (likely(m && m->nb_int)) { + name = "int"; + res = m->nb_int(x); + } + #endif +#else + if (!PyBytes_CheckExact(x) && !PyUnicode_CheckExact(x)) { + res = PyNumber_Int(x); + } +#endif + if (likely(res)) { +#if PY_MAJOR_VERSION < 3 + if (unlikely(!PyInt_Check(res) && !PyLong_Check(res))) { +#else + if (unlikely(!PyLong_CheckExact(res))) { +#endif + return __Pyx_PyNumber_IntOrLongWrongResultType(res, name); + } + } + else if (!PyErr_Occurred()) { + PyErr_SetString(PyExc_TypeError, + "an integer is required"); + } + return res; +} +static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) { + Py_ssize_t ival; + PyObject *x; +#if PY_MAJOR_VERSION < 3 + if (likely(PyInt_CheckExact(b))) { + if (sizeof(Py_ssize_t) >= sizeof(long)) + return PyInt_AS_LONG(b); + else + return PyInt_AsSsize_t(b); + } +#endif + if (likely(PyLong_CheckExact(b))) { + #if CYTHON_USE_PYLONG_INTERNALS + const digit* digits = ((PyLongObject*)b)->ob_digit; + const Py_ssize_t size = Py_SIZE(b); + if (likely(__Pyx_sst_abs(size) <= 1)) { + ival = likely(size) ? digits[0] : 0; + if (size == -1) ival = -ival; + return ival; + } else { + switch (size) { + case 2: + if (8 * sizeof(Py_ssize_t) > 2 * PyLong_SHIFT) { + return (Py_ssize_t) (((((size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); + } + break; + case -2: + if (8 * sizeof(Py_ssize_t) > 2 * PyLong_SHIFT) { + return -(Py_ssize_t) (((((size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); + } + break; + case 3: + if (8 * sizeof(Py_ssize_t) > 3 * PyLong_SHIFT) { + return (Py_ssize_t) (((((((size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); + } + break; + case -3: + if (8 * sizeof(Py_ssize_t) > 3 * PyLong_SHIFT) { + return -(Py_ssize_t) (((((((size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); + } + break; + case 4: + if (8 * sizeof(Py_ssize_t) > 4 * PyLong_SHIFT) { + return (Py_ssize_t) (((((((((size_t)digits[3]) << PyLong_SHIFT) | (size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); + } + break; + case -4: + if (8 * sizeof(Py_ssize_t) > 4 * PyLong_SHIFT) { + return -(Py_ssize_t) (((((((((size_t)digits[3]) << PyLong_SHIFT) | (size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); + } + break; + } + } + #endif + return PyLong_AsSsize_t(b); + } + x = PyNumber_Index(b); + if (!x) return -1; + ival = PyInt_AsSsize_t(x); + Py_DECREF(x); + return ival; +} +static CYTHON_INLINE Py_hash_t __Pyx_PyIndex_AsHash_t(PyObject* o) { + if (sizeof(Py_hash_t) == sizeof(Py_ssize_t)) { + return (Py_hash_t) __Pyx_PyIndex_AsSsize_t(o); +#if PY_MAJOR_VERSION < 3 + } else if (likely(PyInt_CheckExact(o))) { + return PyInt_AS_LONG(o); +#endif + } else { + Py_ssize_t ival; + PyObject *x; + x = PyNumber_Index(o); + if (!x) return -1; + ival = PyInt_AsLong(x); + Py_DECREF(x); + return ival; + } +} +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b) { + return b ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False); +} +static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) { + return PyInt_FromSize_t(ival); +} + + +#endif /* Py_PYTHON_H */ diff --git a/src/cython-bbox/src/cython_bbox.pyx b/src/cython-bbox/src/cython_bbox.pyx new file mode 100644 index 0000000000000000000000000000000000000000..e14780ddd99a2a202fc632a143a808198629a1c5 --- /dev/null +++ b/src/cython-bbox/src/cython_bbox.pyx @@ -0,0 +1,55 @@ +# -------------------------------------------------------- +# Fast R-CNN +# Copyright (c) 2015 Microsoft +# Licensed under The MIT License [see LICENSE for details] +# Written by Sergey Karayev +# -------------------------------------------------------- + +cimport cython +import numpy as np +cimport numpy as np + +DTYPE = np.float +ctypedef np.float_t DTYPE_t + +def bbox_overlaps( + np.ndarray[DTYPE_t, ndim=2] boxes, + np.ndarray[DTYPE_t, ndim=2] query_boxes): + """ + Parameters + ---------- + boxes: (N, 4) ndarray of float + query_boxes: (K, 4) ndarray of float + Returns + ------- + overlaps: (N, K) ndarray of overlap between boxes and query_boxes + """ + cdef unsigned int N = boxes.shape[0] + cdef unsigned int K = query_boxes.shape[0] + cdef np.ndarray[DTYPE_t, ndim=2] overlaps = np.zeros((N, K), dtype=DTYPE) + cdef DTYPE_t iw, ih, box_area + cdef DTYPE_t ua + cdef unsigned int k, n + for k in range(K): + box_area = ( + (query_boxes[k, 2] - query_boxes[k, 0] + 1) * + (query_boxes[k, 3] - query_boxes[k, 1] + 1) + ) + for n in range(N): + iw = ( + min(boxes[n, 2], query_boxes[k, 2]) - + max(boxes[n, 0], query_boxes[k, 0]) + 1 + ) + if iw > 0: + ih = ( + min(boxes[n, 3], query_boxes[k, 3]) - + max(boxes[n, 1], query_boxes[k, 1]) + 1 + ) + if ih > 0: + ua = float( + (boxes[n, 2] - boxes[n, 0] + 1) * + (boxes[n, 3] - boxes[n, 1] + 1) + + box_area - iw * ih + ) + overlaps[n, k] = iw * ih / ua + return overlaps diff --git a/test.mp4 b/test.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9b48363c41a7f42ebf9f4c55efcd7ca7aaf6b3e2 --- /dev/null +++ b/test.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2889085278e9562c68a10d44788b61ee7132372782486ec4f29c5d7c6e747200 +size 1387289 diff --git a/utils/__init__.py b/utils/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc --- /dev/null +++ b/utils/__init__.py @@ -0,0 +1 @@ + diff --git a/utils/__pycache__/__init__.cpython-310.pyc b/utils/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..79ba291988ef2e906ac20eb480f354820650e474 Binary files /dev/null and b/utils/__pycache__/__init__.cpython-310.pyc differ diff --git a/utils/__pycache__/__init__.cpython-39.pyc b/utils/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6d95d814417e321d6c33fe5329d54724000f0f26 Binary files /dev/null and b/utils/__pycache__/__init__.cpython-39.pyc differ diff --git a/utils/__pycache__/datasets.cpython-310.pyc b/utils/__pycache__/datasets.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..76cde711a7f15d4c096f6de33f321eef0c06c281 Binary files /dev/null and b/utils/__pycache__/datasets.cpython-310.pyc differ diff --git a/utils/__pycache__/datasets.cpython-39.pyc b/utils/__pycache__/datasets.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..925597ba0908db77fc7081302489139b6bac0087 Binary files /dev/null and b/utils/__pycache__/datasets.cpython-39.pyc differ diff --git a/utils/__pycache__/general.cpython-310.pyc b/utils/__pycache__/general.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e06110a45aa44cec83f3441441828347e09cf269 Binary files /dev/null and b/utils/__pycache__/general.cpython-310.pyc differ diff --git a/utils/__pycache__/general.cpython-39.pyc b/utils/__pycache__/general.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4aeab646e1826c05f4cf7ae633f10ec425e1cab3 Binary files /dev/null and b/utils/__pycache__/general.cpython-39.pyc differ diff --git a/utils/__pycache__/google_utils.cpython-310.pyc b/utils/__pycache__/google_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ba23af6c327fe0a5c5e4b4a0595bf34ec2fee9cc Binary files /dev/null and b/utils/__pycache__/google_utils.cpython-310.pyc differ diff --git a/utils/__pycache__/google_utils.cpython-39.pyc b/utils/__pycache__/google_utils.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..277cb43da79629855a7f0961ef6bf1105cd7f502 Binary files /dev/null and b/utils/__pycache__/google_utils.cpython-39.pyc differ diff --git a/utils/__pycache__/layers.cpython-310.pyc b/utils/__pycache__/layers.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..eb6935f7e754073fb1023f668dd969624286c694 Binary files /dev/null and b/utils/__pycache__/layers.cpython-310.pyc differ diff --git a/utils/__pycache__/layers.cpython-39.pyc b/utils/__pycache__/layers.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f2bddc72d64fa573bfc659d3dda8aff13504a979 Binary files /dev/null and b/utils/__pycache__/layers.cpython-39.pyc differ diff --git a/utils/__pycache__/metrics.cpython-310.pyc b/utils/__pycache__/metrics.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a74cf55c8e2d3ab94707387a245be75163d51421 Binary files /dev/null and b/utils/__pycache__/metrics.cpython-310.pyc differ diff --git a/utils/__pycache__/metrics.cpython-39.pyc b/utils/__pycache__/metrics.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..72e9696da71cf1040249c19a2d7b85e76dc45347 Binary files /dev/null and b/utils/__pycache__/metrics.cpython-39.pyc differ diff --git a/utils/__pycache__/parse_config.cpython-310.pyc b/utils/__pycache__/parse_config.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..be7205370bf712eae74d0dd70499af27b18a862d Binary files /dev/null and b/utils/__pycache__/parse_config.cpython-310.pyc differ diff --git a/utils/__pycache__/parse_config.cpython-39.pyc b/utils/__pycache__/parse_config.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..56f52aced3593689732d09dd5d43cc8dae1dd573 Binary files /dev/null and b/utils/__pycache__/parse_config.cpython-39.pyc differ diff --git a/utils/__pycache__/plots.cpython-310.pyc b/utils/__pycache__/plots.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ca9bbf952d311d7ff782872c7dc26b6e57273e72 Binary files /dev/null and b/utils/__pycache__/plots.cpython-310.pyc differ diff --git a/utils/__pycache__/plots.cpython-39.pyc b/utils/__pycache__/plots.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2e4fc4765b93d1b3de86cbc976be8854cbe08334 Binary files /dev/null and b/utils/__pycache__/plots.cpython-39.pyc differ diff --git a/utils/__pycache__/torch_utils.cpython-310.pyc b/utils/__pycache__/torch_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..af74e6783c389715fe81a3356b96742ade71a3d6 Binary files /dev/null and b/utils/__pycache__/torch_utils.cpython-310.pyc differ diff --git a/utils/__pycache__/torch_utils.cpython-39.pyc b/utils/__pycache__/torch_utils.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..707e10ac18b62c17d30d401faee062d1e84ba2de Binary files /dev/null and b/utils/__pycache__/torch_utils.cpython-39.pyc differ diff --git a/utils/activations.py b/utils/activations.py new file mode 100644 index 0000000000000000000000000000000000000000..ba6b854ddcc4ba2004440b8e2c946911d37f0af1 --- /dev/null +++ b/utils/activations.py @@ -0,0 +1,72 @@ +# Activation functions + +import torch +import torch.nn as nn +import torch.nn.functional as F + + +# Swish https://arxiv.org/pdf/1905.02244.pdf --------------------------------------------------------------------------- +class Swish(nn.Module): # + @staticmethod + def forward(x): + return x * torch.sigmoid(x) + + +class Hardswish(nn.Module): # export-friendly version of nn.Hardswish() + @staticmethod + def forward(x): + # return x * F.hardsigmoid(x) # for torchscript and CoreML + return x * F.hardtanh(x + 3, 0., 6.) / 6. # for torchscript, CoreML and ONNX + + +class MemoryEfficientSwish(nn.Module): + class F(torch.autograd.Function): + @staticmethod + def forward(ctx, x): + ctx.save_for_backward(x) + return x * torch.sigmoid(x) + + @staticmethod + def backward(ctx, grad_output): + x = ctx.saved_tensors[0] + sx = torch.sigmoid(x) + return grad_output * (sx * (1 + x * (1 - sx))) + + def forward(self, x): + return self.F.apply(x) + + +# Mish https://github.com/digantamisra98/Mish -------------------------------------------------------------------------- +class Mish(nn.Module): + @staticmethod + def forward(x): + return x * F.softplus(x).tanh() + + +class MemoryEfficientMish(nn.Module): + class F(torch.autograd.Function): + @staticmethod + def forward(ctx, x): + ctx.save_for_backward(x) + return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x))) + + @staticmethod + def backward(ctx, grad_output): + x = ctx.saved_tensors[0] + sx = torch.sigmoid(x) + fx = F.softplus(x).tanh() + return grad_output * (fx + x * sx * (1 - fx * fx)) + + def forward(self, x): + return self.F.apply(x) + + +# FReLU https://arxiv.org/abs/2007.11824 ------------------------------------------------------------------------------- +class FReLU(nn.Module): + def __init__(self, c1, k=3): # ch_in, kernel + super().__init__() + self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1) + self.bn = nn.BatchNorm2d(c1) + + def forward(self, x): + return torch.max(x, self.bn(self.conv(x))) diff --git a/utils/autoanchor.py b/utils/autoanchor.py new file mode 100644 index 0000000000000000000000000000000000000000..1e82492bf09050013cb1bee6fbec6baef5ff22a5 --- /dev/null +++ b/utils/autoanchor.py @@ -0,0 +1,152 @@ +# Auto-anchor utils + +import numpy as np +import torch +import yaml +from scipy.cluster.vq import kmeans +from tqdm import tqdm + + +def check_anchor_order(m): + # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary + a = m.anchor_grid.prod(-1).view(-1) # anchor area + da = a[-1] - a[0] # delta a + ds = m.stride[-1] - m.stride[0] # delta s + if da.sign() != ds.sign(): # same order + print('Reversing anchor order') + m.anchors[:] = m.anchors.flip(0) + m.anchor_grid[:] = m.anchor_grid.flip(0) + + +def check_anchors(dataset, model, thr=4.0, imgsz=640): + # Check anchor fit to data, recompute if necessary + print('\nAnalyzing anchors... ', end='') + m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect() + shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True) + scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale + wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh + + def metric(k): # compute metric + r = wh[:, None] / k[None] + x = torch.min(r, 1. / r).min(2)[0] # ratio metric + best = x.max(1)[0] # best_x + aat = (x > 1. / thr).float().sum(1).mean() # anchors above threshold + bpr = (best > 1. / thr).float().mean() # best possible recall + return bpr, aat + + bpr, aat = metric(m.anchor_grid.clone().cpu().view(-1, 2)) + print('anchors/target = %.2f, Best Possible Recall (BPR) = %.4f' % (aat, bpr), end='') + if bpr < 0.98: # threshold to recompute + print('. Attempting to improve anchors, please wait...') + na = m.anchor_grid.numel() // 2 # number of anchors + new_anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False) + new_bpr = metric(new_anchors.reshape(-1, 2))[0] + if new_bpr > bpr: # replace anchors + new_anchors = torch.tensor(new_anchors, device=m.anchors.device).type_as(m.anchors) + m.anchor_grid[:] = new_anchors.clone().view_as(m.anchor_grid) # for inference + m.anchors[:] = new_anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss + check_anchor_order(m) + print('New anchors saved to model. Update model *.yaml to use these anchors in the future.') + else: + print('Original anchors better than new anchors. Proceeding with original anchors.') + print('') # newline + + +def kmean_anchors(path='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True): + """ Creates kmeans-evolved anchors from training dataset + + Arguments: + path: path to dataset *.yaml, or a loaded dataset + n: number of anchors + img_size: image size used for training + thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0 + gen: generations to evolve anchors using genetic algorithm + verbose: print all results + + Return: + k: kmeans evolved anchors + + Usage: + from utils.general import *; _ = kmean_anchors() + """ + thr = 1. / thr + + def metric(k, wh): # compute metrics + r = wh[:, None] / k[None] + x = torch.min(r, 1. / r).min(2)[0] # ratio metric + # x = wh_iou(wh, torch.tensor(k)) # iou metric + return x, x.max(1)[0] # x, best_x + + def anchor_fitness(k): # mutation fitness + _, best = metric(torch.tensor(k, dtype=torch.float32), wh) + return (best * (best > thr).float()).mean() # fitness + + def print_results(k): + k = k[np.argsort(k.prod(1))] # sort small to large + x, best = metric(k, wh0) + bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr + print('thr=%.2f: %.4f best possible recall, %.2f anchors past thr' % (thr, bpr, aat)) + print('n=%g, img_size=%s, metric_all=%.3f/%.3f-mean/best, past_thr=%.3f-mean: ' % + (n, img_size, x.mean(), best.mean(), x[x > thr].mean()), end='') + for i, x in enumerate(k): + print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg + return k + + if isinstance(path, str): # *.yaml file + with open(path) as f: + data_dict = yaml.load(f, Loader=yaml.FullLoader) # model dict + from utils.datasets import LoadImagesAndLabels + dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True) + else: + dataset = path # dataset + + # Get label wh + shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True) + wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh + + # Filter + i = (wh0 < 3.0).any(1).sum() + if i: + print('WARNING: Extremely small objects found. ' + '%g of %g labels are < 3 pixels in width or height.' % (i, len(wh0))) + wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels + + # Kmeans calculation + print('Running kmeans for %g anchors on %g points...' % (n, len(wh))) + s = wh.std(0) # sigmas for whitening + k, dist = kmeans(wh / s, n, iter=30) # points, mean distance + k *= s + wh = torch.tensor(wh, dtype=torch.float32) # filtered + wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered + k = print_results(k) + + # Plot + # k, d = [None] * 20, [None] * 20 + # for i in tqdm(range(1, 21)): + # k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance + # fig, ax = plt.subplots(1, 2, figsize=(14, 7)) + # ax = ax.ravel() + # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.') + # fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh + # ax[0].hist(wh[wh[:, 0]<100, 0],400) + # ax[1].hist(wh[wh[:, 1]<100, 1],400) + # fig.tight_layout() + # fig.savefig('wh.png', dpi=200) + + # Evolve + npr = np.random + f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma + pbar = tqdm(range(gen), desc='Evolving anchors with Genetic Algorithm') # progress bar + for _ in pbar: + v = np.ones(sh) + while (v == 1).all(): # mutate until a change occurs (prevent duplicates) + v = ((npr.random(sh) < mp) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0) + kg = (k.copy() * v).clip(min=2.0) + fg = anchor_fitness(kg) + if fg > f: + f, k = fg, kg.copy() + pbar.desc = 'Evolving anchors with Genetic Algorithm: fitness = %.4f' % f + if verbose: + print_results(k) + + return print_results(k) diff --git a/utils/datasets.py b/utils/datasets.py new file mode 100644 index 0000000000000000000000000000000000000000..116cd41369e4510e3fc4e260d958bf30fbe9799d --- /dev/null +++ b/utils/datasets.py @@ -0,0 +1,1297 @@ +# Dataset utils and dataloaders + +import glob +import math +import os +import random +import shutil +import time +from itertools import repeat +from multiprocessing.pool import ThreadPool +from pathlib import Path +from threading import Thread + +import cv2 +import numpy as np +import torch +from PIL import Image, ExifTags +from torch.utils.data import Dataset +from tqdm import tqdm + +import pickle +from copy import deepcopy +from pycocotools import mask as maskUtils +from torchvision.utils import save_image + +from utils.general import xyxy2xywh, xywh2xyxy +from utils.torch_utils import torch_distributed_zero_first + +# Parameters +help_url = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data' +img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng'] # acceptable image suffixes +vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv'] # acceptable video suffixes + +# Get orientation exif tag +for orientation in ExifTags.TAGS.keys(): + if ExifTags.TAGS[orientation] == 'Orientation': + break + + +def get_hash(files): + # Returns a single hash value of a list of files + return sum(os.path.getsize(f) for f in files if os.path.isfile(f)) + + +def exif_size(img): + # Returns exif-corrected PIL size + s = img.size # (width, height) + try: + rotation = dict(img._getexif().items())[orientation] + if rotation == 6: # rotation 270 + s = (s[1], s[0]) + elif rotation == 8: # rotation 90 + s = (s[1], s[0]) + except: + pass + + return s + + +def create_dataloader(path, imgsz, batch_size, stride, opt, hyp=None, augment=False, cache=False, pad=0.0, rect=False, + rank=-1, world_size=1, workers=8): + # Make sure only the first process in DDP process the dataset first, and the following others can use the cache + with torch_distributed_zero_first(rank): + dataset = LoadImagesAndLabels(path, imgsz, batch_size, + augment=augment, # augment images + hyp=hyp, # augmentation hyperparameters + rect=rect, # rectangular training + cache_images=cache, + single_cls=opt.single_cls, + stride=int(stride), + pad=pad, + rank=rank) + + batch_size = min(batch_size, len(dataset)) + nw = min([os.cpu_count() // world_size, batch_size if batch_size > 1 else 0, workers]) # number of workers + sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None + dataloader = InfiniteDataLoader(dataset, + batch_size=batch_size, + num_workers=nw, + sampler=sampler, + pin_memory=True, + collate_fn=LoadImagesAndLabels.collate_fn) # torch.utils.data.DataLoader() + return dataloader, dataset + + +def create_dataloader9(path, imgsz, batch_size, stride, opt, hyp=None, augment=False, cache=False, pad=0.0, rect=False, + rank=-1, world_size=1, workers=8): + # Make sure only the first process in DDP process the dataset first, and the following others can use the cache + with torch_distributed_zero_first(rank): + dataset = LoadImagesAndLabels9(path, imgsz, batch_size, + augment=augment, # augment images + hyp=hyp, # augmentation hyperparameters + rect=rect, # rectangular training + cache_images=cache, + single_cls=opt.single_cls, + stride=int(stride), + pad=pad, + rank=rank) + + batch_size = min(batch_size, len(dataset)) + nw = min([os.cpu_count() // world_size, batch_size if batch_size > 1 else 0, workers]) # number of workers + sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None + dataloader = InfiniteDataLoader(dataset, + batch_size=batch_size, + num_workers=nw, + sampler=sampler, + pin_memory=True, + collate_fn=LoadImagesAndLabels9.collate_fn) # torch.utils.data.DataLoader() + return dataloader, dataset + + +class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader): + """ Dataloader that reuses workers + + Uses same syntax as vanilla DataLoader + """ + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler)) + self.iterator = super().__iter__() + + def __len__(self): + return len(self.batch_sampler.sampler) + + def __iter__(self): + for i in range(len(self)): + yield next(self.iterator) + + +class _RepeatSampler(object): + """ Sampler that repeats forever + + Args: + sampler (Sampler) + """ + + def __init__(self, sampler): + self.sampler = sampler + + def __iter__(self): + while True: + yield from iter(self.sampler) + + +class LoadImages: # for inference + def __init__(self, path, img_size=640, auto_size=32): + p = str(Path(path)) # os-agnostic + p = os.path.abspath(p) # absolute path + if '*' in p: + files = sorted(glob.glob(p, recursive=True)) # glob + elif os.path.isdir(p): + files = sorted(glob.glob(os.path.join(p, '*.*'))) # dir + elif os.path.isfile(p): + files = [p] # files + else: + raise Exception('ERROR: %s does not exist' % p) + + images = [x for x in files if x.split('.')[-1].lower() in img_formats] + videos = [x for x in files if x.split('.')[-1].lower() in vid_formats] + ni, nv = len(images), len(videos) + + self.img_size = img_size + self.auto_size = auto_size + self.files = images + videos + self.nf = ni + nv # number of files + self.video_flag = [False] * ni + [True] * nv + self.mode = 'images' + if any(videos): + self.new_video(videos[0]) # new video + else: + self.cap = None + assert self.nf > 0, 'No images or videos found in %s. Supported formats are:\nimages: %s\nvideos: %s' % \ + (p, img_formats, vid_formats) + + def __iter__(self): + self.count = 0 + return self + + def __next__(self): + if self.count == self.nf: + raise StopIteration + path = self.files[self.count] + + if self.video_flag[self.count]: + # Read video + self.mode = 'video' + ret_val, img0 = self.cap.read() + if not ret_val: + self.count += 1 + self.cap.release() + if self.count == self.nf: # last video + raise StopIteration + else: + path = self.files[self.count] + self.new_video(path) + ret_val, img0 = self.cap.read() + + self.frame += 1 + print('video %g/%g (%g/%g) %s: ' % (self.count + 1, self.nf, self.frame, self.nframes, path), end='') + + else: + # Read image + self.count += 1 + img0 = cv2.imread(path) # BGR + assert img0 is not None, 'Image Not Found ' + path + print('image %g/%g %s: ' % (self.count, self.nf, path), end='') + + # Padded resize + img = letterbox(img0, new_shape=self.img_size, auto_size=self.auto_size)[0] + + # Convert + img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 + img = np.ascontiguousarray(img) + + return path, img, img0, self.cap + + def new_video(self, path): + self.frame = 0 + self.cap = cv2.VideoCapture(path) + self.nframes = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT)) + + def __len__(self): + return self.nf # number of files + + +class LoadWebcam: # for inference + def __init__(self, pipe='0', img_size=640): + self.img_size = img_size + + if pipe.isnumeric(): + pipe = eval(pipe) # local camera + # pipe = 'rtsp://192.168.1.64/1' # IP camera + # pipe = 'rtsp://username:password@192.168.1.64/1' # IP camera with login + # pipe = 'http://wmccpinetop.axiscam.net/mjpg/video.mjpg' # IP golf camera + + self.pipe = pipe + self.cap = cv2.VideoCapture(pipe) # video capture object + self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3) # set buffer size + + def __iter__(self): + self.count = -1 + return self + + def __next__(self): + self.count += 1 + if cv2.waitKey(1) == ord('q'): # q to quit + self.cap.release() + cv2.destroyAllWindows() + raise StopIteration + + # Read frame + if self.pipe == 0: # local camera + ret_val, img0 = self.cap.read() + img0 = cv2.flip(img0, 1) # flip left-right + else: # IP camera + n = 0 + while True: + n += 1 + self.cap.grab() + if n % 30 == 0: # skip frames + ret_val, img0 = self.cap.retrieve() + if ret_val: + break + + # Print + assert ret_val, 'Camera Error %s' % self.pipe + img_path = 'webcam.jpg' + print('webcam %g: ' % self.count, end='') + + # Padded resize + img = letterbox(img0, new_shape=self.img_size)[0] + + # Convert + img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 + img = np.ascontiguousarray(img) + + return img_path, img, img0, None + + def __len__(self): + return 0 + + +class LoadStreams: # multiple IP or RTSP cameras + def __init__(self, sources='streams.txt', img_size=640): + self.mode = 'images' + self.img_size = img_size + + if os.path.isfile(sources): + with open(sources, 'r') as f: + sources = [x.strip() for x in f.read().splitlines() if len(x.strip())] + else: + sources = [sources] + + n = len(sources) + self.imgs = [None] * n + self.sources = sources + for i, s in enumerate(sources): + # Start the thread to read frames from the video stream + print('%g/%g: %s... ' % (i + 1, n, s), end='') + cap = cv2.VideoCapture(eval(s) if s.isnumeric() else s) + assert cap.isOpened(), 'Failed to open %s' % s + w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) + h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) + fps = cap.get(cv2.CAP_PROP_FPS) % 100 + _, self.imgs[i] = cap.read() # guarantee first frame + thread = Thread(target=self.update, args=([i, cap]), daemon=True) + print(' success (%gx%g at %.2f FPS).' % (w, h, fps)) + thread.start() + print('') # newline + + # check for common shapes + s = np.stack([letterbox(x, new_shape=self.img_size)[0].shape for x in self.imgs], 0) # inference shapes + self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal + if not self.rect: + print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.') + + def update(self, index, cap): + # Read next stream frame in a daemon thread + n = 0 + while cap.isOpened(): + n += 1 + # _, self.imgs[index] = cap.read() + cap.grab() + if n == 4: # read every 4th frame + _, self.imgs[index] = cap.retrieve() + n = 0 + time.sleep(0.01) # wait time + + def __iter__(self): + self.count = -1 + return self + + def __next__(self): + self.count += 1 + img0 = self.imgs.copy() + if cv2.waitKey(1) == ord('q'): # q to quit + cv2.destroyAllWindows() + raise StopIteration + + # Letterbox + img = [letterbox(x, new_shape=self.img_size, auto=self.rect)[0] for x in img0] + + # Stack + img = np.stack(img, 0) + + # Convert + img = img[:, :, :, ::-1].transpose(0, 3, 1, 2) # BGR to RGB, to bsx3x416x416 + img = np.ascontiguousarray(img) + + return self.sources, img, img0, None + + def __len__(self): + return 0 # 1E12 frames = 32 streams at 30 FPS for 30 years + + +class LoadImagesAndLabels(Dataset): # for training/testing + def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False, + cache_images=False, single_cls=False, stride=32, pad=0.0, rank=-1): + self.img_size = img_size + self.augment = augment + self.hyp = hyp + self.image_weights = image_weights + self.rect = False if image_weights else rect + self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training) + self.mosaic_border = [-img_size // 2, -img_size // 2] + self.stride = stride + + def img2label_paths(img_paths): + # Define label paths as a function of image paths + sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep # /images/, /labels/ substrings + return [x.replace(sa, sb, 1).replace(x.split('.')[-1], 'txt') for x in img_paths] + + try: + f = [] # image files + for p in path if isinstance(path, list) else [path]: + p = Path(p) # os-agnostic + if p.is_dir(): # dir + f += glob.glob(str(p / '**' / '*.*'), recursive=True) + elif p.is_file(): # file + with open(p, 'r') as t: + t = t.read().splitlines() + parent = str(p.parent) + os.sep + f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path + else: + raise Exception('%s does not exist' % p) + self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in img_formats]) + assert self.img_files, 'No images found' + except Exception as e: + raise Exception('Error loading data from %s: %s\nSee %s' % (path, e, help_url)) + + # Check cache + self.label_files = img2label_paths(self.img_files) # labels + cache_path = str(Path(self.label_files[0]).parent) + '.cache3' # cached labels + if os.path.isfile(cache_path): + cache = torch.load(cache_path) # load + if cache['hash'] != get_hash(self.label_files + self.img_files): # dataset changed + cache = self.cache_labels(cache_path) # re-cache + else: + cache = self.cache_labels(cache_path) # cache + + # Read cache + cache.pop('hash') # remove hash + labels, shapes = zip(*cache.values()) + self.labels = list(labels) + self.shapes = np.array(shapes, dtype=np.float64) + self.img_files = list(cache.keys()) # update + self.label_files = img2label_paths(cache.keys()) # update + + n = len(shapes) # number of images + bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index + nb = bi[-1] + 1 # number of batches + self.batch = bi # batch index of image + self.n = n + + # Rectangular Training + if self.rect: + # Sort by aspect ratio + s = self.shapes # wh + ar = s[:, 1] / s[:, 0] # aspect ratio + irect = ar.argsort() + self.img_files = [self.img_files[i] for i in irect] + self.label_files = [self.label_files[i] for i in irect] + self.labels = [self.labels[i] for i in irect] + self.shapes = s[irect] # wh + ar = ar[irect] + + # Set training image shapes + shapes = [[1, 1]] * nb + for i in range(nb): + ari = ar[bi == i] + mini, maxi = ari.min(), ari.max() + if maxi < 1: + shapes[i] = [maxi, 1] + elif mini > 1: + shapes[i] = [1, 1 / mini] + + self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride + + # Check labels + create_datasubset, extract_bounding_boxes, labels_loaded = False, False, False + nm, nf, ne, ns, nd = 0, 0, 0, 0, 0 # number missing, found, empty, datasubset, duplicate + pbar = enumerate(self.label_files) + if rank in [-1, 0]: + pbar = tqdm(pbar) + for i, file in pbar: + l = self.labels[i] # label + if l is not None and l.shape[0]: + assert l.shape[1] == 5, '> 5 label columns: %s' % file + assert (l >= 0).all(), 'negative labels: %s' % file + assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels: %s' % file + if np.unique(l, axis=0).shape[0] < l.shape[0]: # duplicate rows + nd += 1 # print('WARNING: duplicate rows in %s' % self.label_files[i]) # duplicate rows + if single_cls: + l[:, 0] = 0 # force dataset into single-class mode + self.labels[i] = l + nf += 1 # file found + + # Create subdataset (a smaller dataset) + if create_datasubset and ns < 1E4: + if ns == 0: + create_folder(path='./datasubset') + os.makedirs('./datasubset/images') + exclude_classes = 43 + if exclude_classes not in l[:, 0]: + ns += 1 + # shutil.copy(src=self.img_files[i], dst='./datasubset/images/') # copy image + with open('./datasubset/images.txt', 'a') as f: + f.write(self.img_files[i] + '\n') + + # Extract object detection boxes for a second stage classifier + if extract_bounding_boxes: + p = Path(self.img_files[i]) + img = cv2.imread(str(p)) + h, w = img.shape[:2] + for j, x in enumerate(l): + f = '%s%sclassifier%s%g_%g_%s' % (p.parent.parent, os.sep, os.sep, x[0], j, p.name) + if not os.path.exists(Path(f).parent): + os.makedirs(Path(f).parent) # make new output folder + + b = x[1:] * [w, h, w, h] # box + b[2:] = b[2:].max() # rectangle to square + b[2:] = b[2:] * 1.3 + 30 # pad + b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int) + + b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image + b[[1, 3]] = np.clip(b[[1, 3]], 0, h) + assert cv2.imwrite(f, img[b[1]:b[3], b[0]:b[2]]), 'Failure extracting classifier boxes' + else: + ne += 1 # print('empty labels for image %s' % self.img_files[i]) # file empty + # os.system("rm '%s' '%s'" % (self.img_files[i], self.label_files[i])) # remove + + if rank in [-1, 0]: + pbar.desc = 'Scanning labels %s (%g found, %g missing, %g empty, %g duplicate, for %g images)' % ( + cache_path, nf, nm, ne, nd, n) + if nf == 0: + s = 'WARNING: No labels found in %s. See %s' % (os.path.dirname(file) + os.sep, help_url) + print(s) + assert not augment, '%s. Can not train without labels.' % s + + # Cache images into memory for faster training (WARNING: large datasets may exceed system RAM) + self.imgs = [None] * n + if cache_images: + gb = 0 # Gigabytes of cached images + self.img_hw0, self.img_hw = [None] * n, [None] * n + results = ThreadPool(8).imap(lambda x: load_image(*x), zip(repeat(self), range(n))) # 8 threads + pbar = tqdm(enumerate(results), total=n) + for i, x in pbar: + self.imgs[i], self.img_hw0[i], self.img_hw[i] = x # img, hw_original, hw_resized = load_image(self, i) + gb += self.imgs[i].nbytes + pbar.desc = 'Caching images (%.1fGB)' % (gb / 1E9) + + def cache_labels(self, path='labels.cache3'): + # Cache dataset labels, check images and read shapes + x = {} # dict + pbar = tqdm(zip(self.img_files, self.label_files), desc='Scanning images', total=len(self.img_files)) + for (img, label) in pbar: + try: + l = [] + im = Image.open(img) + im.verify() # PIL verify + shape = exif_size(im) # image size + assert (shape[0] > 9) & (shape[1] > 9), 'image size <10 pixels' + if os.path.isfile(label): + with open(label, 'r') as f: + l = np.array([x.split() for x in f.read().splitlines()], dtype=np.float32) # labels + if len(l) == 0: + l = np.zeros((0, 5), dtype=np.float32) + x[img] = [l, shape] + except Exception as e: + print('WARNING: Ignoring corrupted image and/or label %s: %s' % (img, e)) + + x['hash'] = get_hash(self.label_files + self.img_files) + torch.save(x, path) # save for next time + return x + + def __len__(self): + return len(self.img_files) + + # def __iter__(self): + # self.count = -1 + # print('ran dataset iter') + # #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF) + # return self + + def __getitem__(self, index): + if self.image_weights: + index = self.indices[index] + + hyp = self.hyp + mosaic = self.mosaic and random.random() < hyp['mosaic'] + if mosaic: + # Load mosaic + img, labels = load_mosaic(self, index) + #img, labels = load_mosaic9(self, index) + shapes = None + + # MixUp https://arxiv.org/pdf/1710.09412.pdf + if random.random() < hyp['mixup']: + img2, labels2 = load_mosaic(self, random.randint(0, len(self.labels) - 1)) + #img2, labels2 = load_mosaic9(self, random.randint(0, len(self.labels) - 1)) + r = np.random.beta(8.0, 8.0) # mixup ratio, alpha=beta=8.0 + img = (img * r + img2 * (1 - r)).astype(np.uint8) + labels = np.concatenate((labels, labels2), 0) + + else: + # Load image + img, (h0, w0), (h, w) = load_image(self, index) + + # Letterbox + shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape + img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment) + shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling + + # Load labels + labels = [] + x = self.labels[index] + if x.size > 0: + # Normalized xywh to pixel xyxy format + labels = x.copy() + labels[:, 1] = ratio[0] * w * (x[:, 1] - x[:, 3] / 2) + pad[0] # pad width + labels[:, 2] = ratio[1] * h * (x[:, 2] - x[:, 4] / 2) + pad[1] # pad height + labels[:, 3] = ratio[0] * w * (x[:, 1] + x[:, 3] / 2) + pad[0] + labels[:, 4] = ratio[1] * h * (x[:, 2] + x[:, 4] / 2) + pad[1] + + if self.augment: + # Augment imagespace + if not mosaic: + img, labels = random_perspective(img, labels, + degrees=hyp['degrees'], + translate=hyp['translate'], + scale=hyp['scale'], + shear=hyp['shear'], + perspective=hyp['perspective']) + + # Augment colorspace + augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v']) + + # Apply cutouts + # if random.random() < 0.9: + # labels = cutout(img, labels) + + nL = len(labels) # number of labels + if nL: + labels[:, 1:5] = xyxy2xywh(labels[:, 1:5]) # convert xyxy to xywh + labels[:, [2, 4]] /= img.shape[0] # normalized height 0-1 + labels[:, [1, 3]] /= img.shape[1] # normalized width 0-1 + + if self.augment: + # flip up-down + if random.random() < hyp['flipud']: + img = np.flipud(img) + if nL: + labels[:, 2] = 1 - labels[:, 2] + + # flip left-right + if random.random() < hyp['fliplr']: + img = np.fliplr(img) + if nL: + labels[:, 1] = 1 - labels[:, 1] + + labels_out = torch.zeros((nL, 6)) + if nL: + labels_out[:, 1:] = torch.from_numpy(labels) + + # Convert + img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 + img = np.ascontiguousarray(img) + + return torch.from_numpy(img), labels_out, self.img_files[index], shapes + + @staticmethod + def collate_fn(batch): + img, label, path, shapes = zip(*batch) # transposed + for i, l in enumerate(label): + l[:, 0] = i # add target image index for build_targets() + return torch.stack(img, 0), torch.cat(label, 0), path, shapes + + +class LoadImagesAndLabels9(Dataset): # for training/testing + def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False, + cache_images=False, single_cls=False, stride=32, pad=0.0, rank=-1): + self.img_size = img_size + self.augment = augment + self.hyp = hyp + self.image_weights = image_weights + self.rect = False if image_weights else rect + self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training) + self.mosaic_border = [-img_size // 2, -img_size // 2] + self.stride = stride + + def img2label_paths(img_paths): + # Define label paths as a function of image paths + sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep # /images/, /labels/ substrings + return [x.replace(sa, sb, 1).replace(x.split('.')[-1], 'txt') for x in img_paths] + + try: + f = [] # image files + for p in path if isinstance(path, list) else [path]: + p = Path(p) # os-agnostic + if p.is_dir(): # dir + f += glob.glob(str(p / '**' / '*.*'), recursive=True) + elif p.is_file(): # file + with open(p, 'r') as t: + t = t.read().splitlines() + parent = str(p.parent) + os.sep + f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path + else: + raise Exception('%s does not exist' % p) + self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in img_formats]) + assert self.img_files, 'No images found' + except Exception as e: + raise Exception('Error loading data from %s: %s\nSee %s' % (path, e, help_url)) + + # Check cache + self.label_files = img2label_paths(self.img_files) # labels + cache_path = str(Path(self.label_files[0]).parent) + '.cache3' # cached labels + if os.path.isfile(cache_path): + cache = torch.load(cache_path) # load + if cache['hash'] != get_hash(self.label_files + self.img_files): # dataset changed + cache = self.cache_labels(cache_path) # re-cache + else: + cache = self.cache_labels(cache_path) # cache + + # Read cache + cache.pop('hash') # remove hash + labels, shapes = zip(*cache.values()) + self.labels = list(labels) + self.shapes = np.array(shapes, dtype=np.float64) + self.img_files = list(cache.keys()) # update + self.label_files = img2label_paths(cache.keys()) # update + + n = len(shapes) # number of images + bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index + nb = bi[-1] + 1 # number of batches + self.batch = bi # batch index of image + self.n = n + + # Rectangular Training + if self.rect: + # Sort by aspect ratio + s = self.shapes # wh + ar = s[:, 1] / s[:, 0] # aspect ratio + irect = ar.argsort() + self.img_files = [self.img_files[i] for i in irect] + self.label_files = [self.label_files[i] for i in irect] + self.labels = [self.labels[i] for i in irect] + self.shapes = s[irect] # wh + ar = ar[irect] + + # Set training image shapes + shapes = [[1, 1]] * nb + for i in range(nb): + ari = ar[bi == i] + mini, maxi = ari.min(), ari.max() + if maxi < 1: + shapes[i] = [maxi, 1] + elif mini > 1: + shapes[i] = [1, 1 / mini] + + self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride + + # Check labels + create_datasubset, extract_bounding_boxes, labels_loaded = False, False, False + nm, nf, ne, ns, nd = 0, 0, 0, 0, 0 # number missing, found, empty, datasubset, duplicate + pbar = enumerate(self.label_files) + if rank in [-1, 0]: + pbar = tqdm(pbar) + for i, file in pbar: + l = self.labels[i] # label + if l is not None and l.shape[0]: + assert l.shape[1] == 5, '> 5 label columns: %s' % file + assert (l >= 0).all(), 'negative labels: %s' % file + assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels: %s' % file + if np.unique(l, axis=0).shape[0] < l.shape[0]: # duplicate rows + nd += 1 # print('WARNING: duplicate rows in %s' % self.label_files[i]) # duplicate rows + if single_cls: + l[:, 0] = 0 # force dataset into single-class mode + self.labels[i] = l + nf += 1 # file found + + # Create subdataset (a smaller dataset) + if create_datasubset and ns < 1E4: + if ns == 0: + create_folder(path='./datasubset') + os.makedirs('./datasubset/images') + exclude_classes = 43 + if exclude_classes not in l[:, 0]: + ns += 1 + # shutil.copy(src=self.img_files[i], dst='./datasubset/images/') # copy image + with open('./datasubset/images.txt', 'a') as f: + f.write(self.img_files[i] + '\n') + + # Extract object detection boxes for a second stage classifier + if extract_bounding_boxes: + p = Path(self.img_files[i]) + img = cv2.imread(str(p)) + h, w = img.shape[:2] + for j, x in enumerate(l): + f = '%s%sclassifier%s%g_%g_%s' % (p.parent.parent, os.sep, os.sep, x[0], j, p.name) + if not os.path.exists(Path(f).parent): + os.makedirs(Path(f).parent) # make new output folder + + b = x[1:] * [w, h, w, h] # box + b[2:] = b[2:].max() # rectangle to square + b[2:] = b[2:] * 1.3 + 30 # pad + b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int) + + b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image + b[[1, 3]] = np.clip(b[[1, 3]], 0, h) + assert cv2.imwrite(f, img[b[1]:b[3], b[0]:b[2]]), 'Failure extracting classifier boxes' + else: + ne += 1 # print('empty labels for image %s' % self.img_files[i]) # file empty + # os.system("rm '%s' '%s'" % (self.img_files[i], self.label_files[i])) # remove + + if rank in [-1, 0]: + pbar.desc = 'Scanning labels %s (%g found, %g missing, %g empty, %g duplicate, for %g images)' % ( + cache_path, nf, nm, ne, nd, n) + if nf == 0: + s = 'WARNING: No labels found in %s. See %s' % (os.path.dirname(file) + os.sep, help_url) + print(s) + assert not augment, '%s. Can not train without labels.' % s + + # Cache images into memory for faster training (WARNING: large datasets may exceed system RAM) + self.imgs = [None] * n + if cache_images: + gb = 0 # Gigabytes of cached images + self.img_hw0, self.img_hw = [None] * n, [None] * n + results = ThreadPool(8).imap(lambda x: load_image(*x), zip(repeat(self), range(n))) # 8 threads + pbar = tqdm(enumerate(results), total=n) + for i, x in pbar: + self.imgs[i], self.img_hw0[i], self.img_hw[i] = x # img, hw_original, hw_resized = load_image(self, i) + gb += self.imgs[i].nbytes + pbar.desc = 'Caching images (%.1fGB)' % (gb / 1E9) + + def cache_labels(self, path='labels.cache3'): + # Cache dataset labels, check images and read shapes + x = {} # dict + pbar = tqdm(zip(self.img_files, self.label_files), desc='Scanning images', total=len(self.img_files)) + for (img, label) in pbar: + try: + l = [] + im = Image.open(img) + im.verify() # PIL verify + shape = exif_size(im) # image size + assert (shape[0] > 9) & (shape[1] > 9), 'image size <10 pixels' + if os.path.isfile(label): + with open(label, 'r') as f: + l = np.array([x.split() for x in f.read().splitlines()], dtype=np.float32) # labels + if len(l) == 0: + l = np.zeros((0, 5), dtype=np.float32) + x[img] = [l, shape] + except Exception as e: + print('WARNING: Ignoring corrupted image and/or label %s: %s' % (img, e)) + + x['hash'] = get_hash(self.label_files + self.img_files) + torch.save(x, path) # save for next time + return x + + def __len__(self): + return len(self.img_files) + + # def __iter__(self): + # self.count = -1 + # print('ran dataset iter') + # #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF) + # return self + + def __getitem__(self, index): + if self.image_weights: + index = self.indices[index] + + hyp = self.hyp + mosaic = self.mosaic and random.random() < hyp['mosaic'] + if mosaic: + # Load mosaic + #img, labels = load_mosaic(self, index) + img, labels = load_mosaic9(self, index) + shapes = None + + # MixUp https://arxiv.org/pdf/1710.09412.pdf + if random.random() < hyp['mixup']: + #img2, labels2 = load_mosaic(self, random.randint(0, len(self.labels) - 1)) + img2, labels2 = load_mosaic9(self, random.randint(0, len(self.labels) - 1)) + r = np.random.beta(8.0, 8.0) # mixup ratio, alpha=beta=8.0 + img = (img * r + img2 * (1 - r)).astype(np.uint8) + labels = np.concatenate((labels, labels2), 0) + + else: + # Load image + img, (h0, w0), (h, w) = load_image(self, index) + + # Letterbox + shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape + img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment) + shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling + + # Load labels + labels = [] + x = self.labels[index] + if x.size > 0: + # Normalized xywh to pixel xyxy format + labels = x.copy() + labels[:, 1] = ratio[0] * w * (x[:, 1] - x[:, 3] / 2) + pad[0] # pad width + labels[:, 2] = ratio[1] * h * (x[:, 2] - x[:, 4] / 2) + pad[1] # pad height + labels[:, 3] = ratio[0] * w * (x[:, 1] + x[:, 3] / 2) + pad[0] + labels[:, 4] = ratio[1] * h * (x[:, 2] + x[:, 4] / 2) + pad[1] + + if self.augment: + # Augment imagespace + if not mosaic: + img, labels = random_perspective(img, labels, + degrees=hyp['degrees'], + translate=hyp['translate'], + scale=hyp['scale'], + shear=hyp['shear'], + perspective=hyp['perspective']) + + # Augment colorspace + augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v']) + + # Apply cutouts + # if random.random() < 0.9: + # labels = cutout(img, labels) + + nL = len(labels) # number of labels + if nL: + labels[:, 1:5] = xyxy2xywh(labels[:, 1:5]) # convert xyxy to xywh + labels[:, [2, 4]] /= img.shape[0] # normalized height 0-1 + labels[:, [1, 3]] /= img.shape[1] # normalized width 0-1 + + if self.augment: + # flip up-down + if random.random() < hyp['flipud']: + img = np.flipud(img) + if nL: + labels[:, 2] = 1 - labels[:, 2] + + # flip left-right + if random.random() < hyp['fliplr']: + img = np.fliplr(img) + if nL: + labels[:, 1] = 1 - labels[:, 1] + + labels_out = torch.zeros((nL, 6)) + if nL: + labels_out[:, 1:] = torch.from_numpy(labels) + + # Convert + img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 + img = np.ascontiguousarray(img) + + return torch.from_numpy(img), labels_out, self.img_files[index], shapes + + @staticmethod + def collate_fn(batch): + img, label, path, shapes = zip(*batch) # transposed + for i, l in enumerate(label): + l[:, 0] = i # add target image index for build_targets() + return torch.stack(img, 0), torch.cat(label, 0), path, shapes + + +# Ancillary functions -------------------------------------------------------------------------------------------------- +def load_image(self, index): + # loads 1 image from dataset, returns img, original hw, resized hw + img = self.imgs[index] + if img is None: # not cached + path = self.img_files[index] + img = cv2.imread(path) # BGR + assert img is not None, 'Image Not Found ' + path + h0, w0 = img.shape[:2] # orig hw + r = self.img_size / max(h0, w0) # resize image to img_size + if r != 1: # always resize down, only resize up if training with augmentation + interp = cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR + img = cv2.resize(img, (int(w0 * r), int(h0 * r)), interpolation=interp) + return img, (h0, w0), img.shape[:2] # img, hw_original, hw_resized + else: + return self.imgs[index], self.img_hw0[index], self.img_hw[index] # img, hw_original, hw_resized + + +def augment_hsv(img, hgain=0.5, sgain=0.5, vgain=0.5): + r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains + hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV)) + dtype = img.dtype # uint8 + + x = np.arange(0, 256, dtype=np.int16) + lut_hue = ((x * r[0]) % 180).astype(dtype) + lut_sat = np.clip(x * r[1], 0, 255).astype(dtype) + lut_val = np.clip(x * r[2], 0, 255).astype(dtype) + + img_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))).astype(dtype) + cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img) # no return needed + + # Histogram equalization + # if random.random() < 0.2: + # for i in range(3): + # img[:, :, i] = cv2.equalizeHist(img[:, :, i]) + + +def load_mosaic(self, index): + # loads images in a mosaic + + labels4 = [] + s = self.img_size + yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border] # mosaic center x, y + indices = [index] + [random.randint(0, len(self.labels) - 1) for _ in range(3)] # 3 additional image indices + for i, index in enumerate(indices): + # Load image + img, _, (h, w) = load_image(self, index) + + # place img in img4 + if i == 0: # top left + img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles + x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image) + x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image) + elif i == 1: # top right + x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc + x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h + elif i == 2: # bottom left + x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h) + x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h) + elif i == 3: # bottom right + x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h) + x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h) + + img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] + padw = x1a - x1b + padh = y1a - y1b + + # Labels + x = self.labels[index] + labels = x.copy() + if x.size > 0: # Normalized xywh to pixel xyxy format + labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padw + labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + padh + labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padw + labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + padh + labels4.append(labels) + + # Concat/clip labels + if len(labels4): + labels4 = np.concatenate(labels4, 0) + np.clip(labels4[:, 1:], 0, 2 * s, out=labels4[:, 1:]) # use with random_perspective + # img4, labels4 = replicate(img4, labels4) # replicate + + # Augment + img4, labels4 = random_perspective(img4, labels4, + degrees=self.hyp['degrees'], + translate=self.hyp['translate'], + scale=self.hyp['scale'], + shear=self.hyp['shear'], + perspective=self.hyp['perspective'], + border=self.mosaic_border) # border to remove + + return img4, labels4 + + +def load_mosaic9(self, index): + # loads images in a 9-mosaic + + labels9 = [] + s = self.img_size + indices = [index] + [random.randint(0, len(self.labels) - 1) for _ in range(8)] # 8 additional image indices + for i, index in enumerate(indices): + # Load image + img, _, (h, w) = load_image(self, index) + + # place img in img9 + if i == 0: # center + img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles + h0, w0 = h, w + c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates + elif i == 1: # top + c = s, s - h, s + w, s + elif i == 2: # top right + c = s + wp, s - h, s + wp + w, s + elif i == 3: # right + c = s + w0, s, s + w0 + w, s + h + elif i == 4: # bottom right + c = s + w0, s + hp, s + w0 + w, s + hp + h + elif i == 5: # bottom + c = s + w0 - w, s + h0, s + w0, s + h0 + h + elif i == 6: # bottom left + c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h + elif i == 7: # left + c = s - w, s + h0 - h, s, s + h0 + elif i == 8: # top left + c = s - w, s + h0 - hp - h, s, s + h0 - hp + + padx, pady = c[:2] + x1, y1, x2, y2 = [max(x, 0) for x in c] # allocate coords + + # Labels + x = self.labels[index] + labels = x.copy() + if x.size > 0: # Normalized xywh to pixel xyxy format + labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padx + labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + pady + labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padx + labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + pady + labels9.append(labels) + + # Image + img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:] # img9[ymin:ymax, xmin:xmax] + hp, wp = h, w # height, width previous + + # Offset + yc, xc = [int(random.uniform(0, s)) for x in self.mosaic_border] # mosaic center x, y + img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s] + + # Concat/clip labels + if len(labels9): + labels9 = np.concatenate(labels9, 0) + labels9[:, [1, 3]] -= xc + labels9[:, [2, 4]] -= yc + + np.clip(labels9[:, 1:], 0, 2 * s, out=labels9[:, 1:]) # use with random_perspective + # img9, labels9 = replicate(img9, labels9) # replicate + + # Augment + img9, labels9 = random_perspective(img9, labels9, + degrees=self.hyp['degrees'], + translate=self.hyp['translate'], + scale=self.hyp['scale'], + shear=self.hyp['shear'], + perspective=self.hyp['perspective'], + border=self.mosaic_border) # border to remove + + return img9, labels9 + + +def replicate(img, labels): + # Replicate labels + h, w = img.shape[:2] + boxes = labels[:, 1:].astype(int) + x1, y1, x2, y2 = boxes.T + s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels) + for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices + x1b, y1b, x2b, y2b = boxes[i] + bh, bw = y2b - y1b, x2b - x1b + yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y + x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh] + img[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] + labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0) + + return img, labels + + +def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, auto_size=32): + # Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232 + shape = img.shape[:2] # current shape [height, width] + if isinstance(new_shape, int): + new_shape = (new_shape, new_shape) + + # Scale ratio (new / old) + r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) + if not scaleup: # only scale down, do not scale up (for better test mAP) + r = min(r, 1.0) + + # Compute padding + ratio = r, r # width, height ratios + new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) + dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding + if auto: # minimum rectangle + dw, dh = np.mod(dw, auto_size), np.mod(dh, auto_size) # wh padding + elif scaleFill: # stretch + dw, dh = 0.0, 0.0 + new_unpad = (new_shape[1], new_shape[0]) + ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios + + dw /= 2 # divide padding into 2 sides + dh /= 2 + + if shape[::-1] != new_unpad: # resize + img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) + top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) + left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) + img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border + return img, ratio, (dw, dh) + + +def random_perspective(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, border=(0, 0)): + # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10)) + # targets = [cls, xyxy] + + height = img.shape[0] + border[0] * 2 # shape(h,w,c) + width = img.shape[1] + border[1] * 2 + + # Center + C = np.eye(3) + C[0, 2] = -img.shape[1] / 2 # x translation (pixels) + C[1, 2] = -img.shape[0] / 2 # y translation (pixels) + + # Perspective + P = np.eye(3) + P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y) + P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x) + + # Rotation and Scale + R = np.eye(3) + a = random.uniform(-degrees, degrees) + # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations + s = random.uniform(1 - scale, 1 + scale) + # s = 2 ** random.uniform(-scale, scale) + R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) + + # Shear + S = np.eye(3) + S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg) + S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg) + + # Translation + T = np.eye(3) + T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels) + T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels) + + # Combined rotation matrix + M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT + if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed + if perspective: + img = cv2.warpPerspective(img, M, dsize=(width, height), borderValue=(114, 114, 114)) + else: # affine + img = cv2.warpAffine(img, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) + + # Visualize + # import matplotlib.pyplot as plt + # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel() + # ax[0].imshow(img[:, :, ::-1]) # base + # ax[1].imshow(img2[:, :, ::-1]) # warped + + # Transform label coordinates + n = len(targets) + if n: + # warp points + xy = np.ones((n * 4, 3)) + xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1 + xy = xy @ M.T # transform + if perspective: + xy = (xy[:, :2] / xy[:, 2:3]).reshape(n, 8) # rescale + else: # affine + xy = xy[:, :2].reshape(n, 8) + + # create new boxes + x = xy[:, [0, 2, 4, 6]] + y = xy[:, [1, 3, 5, 7]] + xy = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T + + # # apply angle-based reduction of bounding boxes + # radians = a * math.pi / 180 + # reduction = max(abs(math.sin(radians)), abs(math.cos(radians))) ** 0.5 + # x = (xy[:, 2] + xy[:, 0]) / 2 + # y = (xy[:, 3] + xy[:, 1]) / 2 + # w = (xy[:, 2] - xy[:, 0]) * reduction + # h = (xy[:, 3] - xy[:, 1]) * reduction + # xy = np.concatenate((x - w / 2, y - h / 2, x + w / 2, y + h / 2)).reshape(4, n).T + + # clip boxes + xy[:, [0, 2]] = xy[:, [0, 2]].clip(0, width) + xy[:, [1, 3]] = xy[:, [1, 3]].clip(0, height) + + # filter candidates + i = box_candidates(box1=targets[:, 1:5].T * s, box2=xy.T) + targets = targets[i] + targets[:, 1:5] = xy[i] + + return img, targets + + +def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1): # box1(4,n), box2(4,n) + # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio + w1, h1 = box1[2] - box1[0], box1[3] - box1[1] + w2, h2 = box2[2] - box2[0], box2[3] - box2[1] + ar = np.maximum(w2 / (h2 + 1e-16), h2 / (w2 + 1e-16)) # aspect ratio + return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + 1e-16) > area_thr) & (ar < ar_thr) # candidates + + +def cutout(image, labels): + # Applies image cutout augmentation https://arxiv.org/abs/1708.04552 + h, w = image.shape[:2] + + def bbox_ioa(box1, box2): + # Returns the intersection over box2 area given box1, box2. box1 is 4, box2 is nx4. boxes are x1y1x2y2 + box2 = box2.transpose() + + # Get the coordinates of bounding boxes + b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] + b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] + + # Intersection area + inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \ + (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0) + + # box2 area + box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + 1e-16 + + # Intersection over box2 area + return inter_area / box2_area + + # create random masks + scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction + for s in scales: + mask_h = random.randint(1, int(h * s)) + mask_w = random.randint(1, int(w * s)) + + # box + xmin = max(0, random.randint(0, w) - mask_w // 2) + ymin = max(0, random.randint(0, h) - mask_h // 2) + xmax = min(w, xmin + mask_w) + ymax = min(h, ymin + mask_h) + + # apply random color mask + image[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)] + + # return unobscured labels + if len(labels) and s > 0.03: + box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32) + ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area + labels = labels[ioa < 0.60] # remove >60% obscured labels + + return labels + + +def create_folder(path='./new'): + # Create folder + if os.path.exists(path): + shutil.rmtree(path) # delete output folder + os.makedirs(path) # make new output folder + + +def flatten_recursive(path='../coco128'): + # Flatten a recursive directory by bringing all files to top level + new_path = Path(path + '_flat') + create_folder(new_path) + for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)): + shutil.copyfile(file, new_path / Path(file).name) + + diff --git a/utils/general.py b/utils/general.py new file mode 100644 index 0000000000000000000000000000000000000000..9b06c8b8955ab437cb21b5866436f9b228a38439 --- /dev/null +++ b/utils/general.py @@ -0,0 +1,449 @@ +# General utils + +import glob +import logging +import math +import os +import platform +import random +import re +import subprocess +import time +from pathlib import Path + +import cv2 +import matplotlib +import numpy as np +import torch +import yaml + +from utils.google_utils import gsutil_getsize +from utils.metrics import fitness, fitness_p, fitness_r, fitness_ap50, fitness_ap, fitness_f +from utils.torch_utils import init_torch_seeds + +# Set printoptions +torch.set_printoptions(linewidth=320, precision=5, profile='long') +np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5 +matplotlib.rc('font', **{'size': 11}) + +# Prevent OpenCV from multithreading (to use PyTorch DataLoader) +cv2.setNumThreads(0) + + +def set_logging(rank=-1): + logging.basicConfig( + format="%(message)s", + level=logging.INFO if rank in [-1, 0] else logging.WARN) + + +def init_seeds(seed=0): + random.seed(seed) + np.random.seed(seed) + init_torch_seeds(seed) + + +def get_latest_run(search_dir='.'): + # Return path to most recent 'last.pt' in /runs (i.e. to --resume from) + last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True) + return max(last_list, key=os.path.getctime) if last_list else '' + + +def check_git_status(): + # Suggest 'git pull' if repo is out of date + if platform.system() in ['Linux', 'Darwin'] and not os.path.isfile('/.dockerenv'): + s = subprocess.check_output('if [ -d .git ]; then git fetch && git status -uno; fi', shell=True).decode('utf-8') + if 'Your branch is behind' in s: + print(s[s.find('Your branch is behind'):s.find('\n\n')] + '\n') + + +def check_img_size(img_size, s=32): + # Verify img_size is a multiple of stride s + new_size = make_divisible(img_size, int(s)) # ceil gs-multiple + if new_size != img_size: + print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size)) + return new_size + + +def check_file(file): + # Search for file if not found + if os.path.isfile(file) or file == '': + return file + else: + files = glob.glob('./**/' + file, recursive=True) # find file + assert len(files), 'File Not Found: %s' % file # assert file was found + assert len(files) == 1, "Multiple files match '%s', specify exact path: %s" % (file, files) # assert unique + return files[0] # return file + + +def check_dataset(dict): + # Download dataset if not found locally + val, s = dict.get('val'), dict.get('download') + if val and len(val): + val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path + if not all(x.exists() for x in val): + print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()]) + if s and len(s): # download script + print('Downloading %s ...' % s) + if s.startswith('http') and s.endswith('.zip'): # URL + f = Path(s).name # filename + torch.hub.download_url_to_file(s, f) + r = os.system('unzip -q %s -d ../ && rm %s' % (f, f)) # unzip + else: # bash script + r = os.system(s) + print('Dataset autodownload %s\n' % ('success' if r == 0 else 'failure')) # analyze return value + else: + raise Exception('Dataset not found.') + + +def make_divisible(x, divisor): + # Returns x evenly divisible by divisor + return math.ceil(x / divisor) * divisor + + +def labels_to_class_weights(labels, nc=80): + # Get class weights (inverse frequency) from training labels + if labels[0] is None: # no labels loaded + return torch.Tensor() + + labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO + classes = labels[:, 0].astype(np.int) # labels = [class xywh] + weights = np.bincount(classes, minlength=nc) # occurrences per class + + # Prepend gridpoint count (for uCE training) + # gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image + # weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start + + weights[weights == 0] = 1 # replace empty bins with 1 + weights = 1 / weights # number of targets per class + weights /= weights.sum() # normalize + return torch.from_numpy(weights) + + +def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)): + # Produces image weights based on class mAPs + n = len(labels) + class_counts = np.array([np.bincount(labels[i][:, 0].astype(np.int), minlength=nc) for i in range(n)]) + image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1) + # index = random.choices(range(n), weights=image_weights, k=1) # weight image sample + return image_weights + + +def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper) + # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/ + # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n') + # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n') + # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco + # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet + x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34, + 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, + 64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90] + return x + + +def xyxy2xywh(x): + # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center + y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center + y[:, 2] = x[:, 2] - x[:, 0] # width + y[:, 3] = x[:, 3] - x[:, 1] # height + return y + + +def xywh2xyxy(x): + # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x + y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y + y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x + y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y + return y + + +def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None): + # Rescale coords (xyxy) from img1_shape to img0_shape + if ratio_pad is None: # calculate from img0_shape + gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new + pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding + else: + gain = ratio_pad[0][0] + pad = ratio_pad[1] + + coords[:, [0, 2]] -= pad[0] # x padding + coords[:, [1, 3]] -= pad[1] # y padding + coords[:, :4] /= gain + clip_coords(coords, img0_shape) + return coords + + +def clip_coords(boxes, img_shape): + # Clip bounding xyxy bounding boxes to image shape (height, width) + boxes[:, 0].clamp_(0, img_shape[1]) # x1 + boxes[:, 1].clamp_(0, img_shape[0]) # y1 + boxes[:, 2].clamp_(0, img_shape[1]) # x2 + boxes[:, 3].clamp_(0, img_shape[0]) # y2 + + +def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, EIoU=False, ECIoU=False, eps=1e-9): + # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4 + box2 = box2.T + + # Get the coordinates of bounding boxes + if x1y1x2y2: # x1, y1, x2, y2 = box1 + b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] + b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] + else: # transform from xywh to xyxy + b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2 + b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2 + b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2 + b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2 + + # Intersection area + inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \ + (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0) + + # Union Area + w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps + w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps + union = w1 * h1 + w2 * h2 - inter + eps + + iou = inter / union + if GIoU or DIoU or CIoU or EIoU or ECIoU: + cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width + ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height + if CIoU or DIoU or EIoU or ECIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1 + c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared + rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squared + if DIoU: + return iou - rho2 / c2 # DIoU + elif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47 + v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2) + with torch.no_grad(): + alpha = v / ((1 + eps) - iou + v) + return iou - (rho2 / c2 + v * alpha) # CIoU + elif EIoU: # Efficient IoU https://arxiv.org/abs/2101.08158 + rho3 = (w1-w2) **2 + c3 = cw ** 2 + eps + rho4 = (h1-h2) **2 + c4 = ch ** 2 + eps + return iou - rho2 / c2 - rho3 / c3 - rho4 / c4 # EIoU + elif ECIoU: + v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2) + with torch.no_grad(): + alpha = v / ((1 + eps) - iou + v) + rho3 = (w1-w2) **2 + c3 = cw ** 2 + eps + rho4 = (h1-h2) **2 + c4 = ch ** 2 + eps + return iou - v * alpha - rho2 / c2 - rho3 / c3 - rho4 / c4 # ECIoU + else: # GIoU https://arxiv.org/pdf/1902.09630.pdf + c_area = cw * ch + eps # convex area + return iou - (c_area - union) / c_area # GIoU + else: + return iou # IoU + + +def box_iou(box1, box2): + # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py + """ + Return intersection-over-union (Jaccard index) of boxes. + Both sets of boxes are expected to be in (x1, y1, x2, y2) format. + Arguments: + box1 (Tensor[N, 4]) + box2 (Tensor[M, 4]) + Returns: + iou (Tensor[N, M]): the NxM matrix containing the pairwise + IoU values for every element in boxes1 and boxes2 + """ + + def box_area(box): + # box = 4xn + return (box[2] - box[0]) * (box[3] - box[1]) + + area1 = box_area(box1.T) + area2 = box_area(box2.T) + + # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) + inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2) + return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter) + + +def wh_iou(wh1, wh2): + # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2 + wh1 = wh1[:, None] # [N,1,2] + wh2 = wh2[None] # [1,M,2] + inter = torch.min(wh1, wh2).prod(2) # [N,M] + return inter / (wh1.prod(2) + wh2.prod(2) - inter) # iou = inter / (area1 + area2 - inter) + + +def non_max_suppression(prediction, conf_thres=0.1, iou_thres=0.6, merge=False, classes=None, agnostic=False): + """Performs Non-Maximum Suppression (NMS) on inference results + + Returns: + detections with shape: nx6 (x1, y1, x2, y2, conf, cls) + """ + + nc = prediction[0].shape[1] - 5 # number of classes + xc = prediction[..., 4] > conf_thres # candidates + + # Settings + min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height + max_det = 300 # maximum number of detections per image + time_limit = 10.0 # seconds to quit after + redundant = True # require redundant detections + multi_label = nc > 1 # multiple labels per box (adds 0.5ms/img) + + t = time.time() + output = [torch.zeros(0, 6)] * prediction.shape[0] + for xi, x in enumerate(prediction): # image index, image inference + # Apply constraints + # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height + x = x[xc[xi]] # confidence + + # If none remain process next image + if not x.shape[0]: + continue + + # Compute conf + x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf + + # Box (center x, center y, width, height) to (x1, y1, x2, y2) + box = xywh2xyxy(x[:, :4]) + + # Detections matrix nx6 (xyxy, conf, cls) + if multi_label: + i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T + x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1) + else: # best class only + conf, j = x[:, 5:].max(1, keepdim=True) + x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres] + + # Filter by class + if classes: + x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)] + + # Apply finite constraint + # if not torch.isfinite(x).all(): + # x = x[torch.isfinite(x).all(1)] + + # If none remain process next image + n = x.shape[0] # number of boxes + if not n: + continue + + # Sort by confidence + # x = x[x[:, 4].argsort(descending=True)] + + # Batched NMS + c = x[:, 5:6] * (0 if agnostic else max_wh) # classes + boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores + i = torch.ops.torchvision.nms(boxes, scores, iou_thres) + if i.shape[0] > max_det: # limit detections + i = i[:max_det] + if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean) + # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4) + iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix + weights = iou * scores[None] # box weights + x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes + if redundant: + i = i[iou.sum(1) > 1] # require redundancy + + output[xi] = x[i] + if (time.time() - t) > time_limit: + break # time limit exceeded + + return output + + +def strip_optimizer(f='weights/best.pt', s=''): # from utils.general import *; strip_optimizer() + # Strip optimizer from 'f' to finalize training, optionally save as 's' + x = torch.load(f, map_location=torch.device('cpu')) + x['optimizer'] = None + x['training_results'] = None + x['epoch'] = -1 + #x['model'].half() # to FP16 + #for p in x['model'].parameters(): + # p.requires_grad = False + torch.save(x, s or f) + mb = os.path.getsize(s or f) / 1E6 # filesize + print('Optimizer stripped from %s,%s %.1fMB' % (f, (' saved as %s,' % s) if s else '', mb)) + + +def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket=''): + # Print mutation results to evolve.txt (for use with train.py --evolve) + a = '%10s' * len(hyp) % tuple(hyp.keys()) # hyperparam keys + b = '%10.3g' * len(hyp) % tuple(hyp.values()) # hyperparam values + c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3) + print('\n%s\n%s\nEvolved fitness: %s\n' % (a, b, c)) + + if bucket: + url = 'gs://%s/evolve.txt' % bucket + if gsutil_getsize(url) > (os.path.getsize('evolve.txt') if os.path.exists('evolve.txt') else 0): + os.system('gsutil cp %s .' % url) # download evolve.txt if larger than local + + with open('evolve.txt', 'a') as f: # append result + f.write(c + b + '\n') + x = np.unique(np.loadtxt('evolve.txt', ndmin=2), axis=0) # load unique rows + x = x[np.argsort(-fitness(x))] # sort + np.savetxt('evolve.txt', x, '%10.3g') # save sort by fitness + + # Save yaml + for i, k in enumerate(hyp.keys()): + hyp[k] = float(x[0, i + 7]) + with open(yaml_file, 'w') as f: + results = tuple(x[0, :7]) + c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3) + f.write('# Hyperparameter Evolution Results\n# Generations: %g\n# Metrics: ' % len(x) + c + '\n\n') + yaml.dump(hyp, f, sort_keys=False) + + if bucket: + os.system('gsutil cp evolve.txt %s gs://%s' % (yaml_file, bucket)) # upload + + +def apply_classifier(x, model, img, im0): + # applies a second stage classifier to yolo outputs + im0 = [im0] if isinstance(im0, np.ndarray) else im0 + for i, d in enumerate(x): # per image + if d is not None and len(d): + d = d.clone() + + # Reshape and pad cutouts + b = xyxy2xywh(d[:, :4]) # boxes + b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square + b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad + d[:, :4] = xywh2xyxy(b).long() + + # Rescale boxes from img_size to im0 size + scale_coords(img.shape[2:], d[:, :4], im0[i].shape) + + # Classes + pred_cls1 = d[:, 5].long() + ims = [] + for j, a in enumerate(d): # per item + cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])] + im = cv2.resize(cutout, (224, 224)) # BGR + # cv2.imwrite('test%i.jpg' % j, cutout) + + im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 + im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32 + im /= 255.0 # 0 - 255 to 0.0 - 1.0 + ims.append(im) + + pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction + x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections + + return x + + +def increment_path(path, exist_ok=True, sep=''): + # Increment path, i.e. runs/exp --> runs/exp{sep}0, runs/exp{sep}1 etc. + path = Path(path) # os-agnostic + if (path.exists() and exist_ok) or (not path.exists()): + return str(path) + else: + dirs = glob.glob(f"{path}{sep}*") # similar paths + matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs] + i = [int(m.groups()[0]) for m in matches if m] # indices + n = max(i) + 1 if i else 2 # increment number + return f"{path}{sep}{n}" # update path diff --git a/utils/google_utils.py b/utils/google_utils.py new file mode 100644 index 0000000000000000000000000000000000000000..0ff8bbd3241955204cf8885bfcb322b026cd8b16 --- /dev/null +++ b/utils/google_utils.py @@ -0,0 +1,120 @@ +# Google utils: https://cloud.google.com/storage/docs/reference/libraries + +import os +import platform +import subprocess +import time +from pathlib import Path + +import torch + + +def gsutil_getsize(url=''): + # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du + s = subprocess.check_output('gsutil du %s' % url, shell=True).decode('utf-8') + return eval(s.split(' ')[0]) if len(s) else 0 # bytes + + +def attempt_download(weights): + # Attempt to download pretrained weights if not found locally + weights = weights.strip().replace("'", '') + file = Path(weights).name + + msg = weights + ' missing, try downloading from https://github.com/WongKinYiu/yolor/releases/' + models = ['yolor_p6.pt', 'yolor_w6.pt'] # available models + + if file in models and not os.path.isfile(weights): + + try: # GitHub + url = 'https://github.com/WongKinYiu/yolor/releases/download/v1.0/' + file + print('Downloading %s to %s...' % (url, weights)) + torch.hub.download_url_to_file(url, weights) + assert os.path.exists(weights) and os.path.getsize(weights) > 1E6 # check + except Exception as e: # GCP + print('ERROR: Download failure.') + print('') + + +def attempt_load(weights, map_location=None): + # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a + model = Ensemble() + for w in weights if isinstance(weights, list) else [weights]: + attempt_download(w) + model.append(torch.load(w, map_location=map_location)['model'].float().fuse().eval()) # load FP32 model + + if len(model) == 1: + return model[-1] # return model + else: + print('Ensemble created with %s\n' % weights) + for k in ['names', 'stride']: + setattr(model, k, getattr(model[-1], k)) + return model # return ensemble + + +def gdrive_download(id='1n_oKgR81BJtqk75b00eAjdv03qVCQn2f', name='coco128.zip'): + # Downloads a file from Google Drive. from utils.google_utils import *; gdrive_download() + t = time.time() + + print('Downloading https://drive.google.com/uc?export=download&id=%s as %s... ' % (id, name), end='') + os.remove(name) if os.path.exists(name) else None # remove existing + os.remove('cookie') if os.path.exists('cookie') else None + + # Attempt file download + out = "NUL" if platform.system() == "Windows" else "/dev/null" + os.system('curl -c ./cookie -s -L "drive.google.com/uc?export=download&id=%s" > %s ' % (id, out)) + if os.path.exists('cookie'): # large file + s = 'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm=%s&id=%s" -o %s' % (get_token(), id, name) + else: # small file + s = 'curl -s -L -o %s "drive.google.com/uc?export=download&id=%s"' % (name, id) + r = os.system(s) # execute, capture return + os.remove('cookie') if os.path.exists('cookie') else None + + # Error check + if r != 0: + os.remove(name) if os.path.exists(name) else None # remove partial + print('Download error ') # raise Exception('Download error') + return r + + # Unzip if archive + if name.endswith('.zip'): + print('unzipping... ', end='') + os.system('unzip -q %s' % name) # unzip + os.remove(name) # remove zip to free space + + print('Done (%.1fs)' % (time.time() - t)) + return r + + +def get_token(cookie="./cookie"): + with open(cookie) as f: + for line in f: + if "download" in line: + return line.split()[-1] + return "" + +# def upload_blob(bucket_name, source_file_name, destination_blob_name): +# # Uploads a file to a bucket +# # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python +# +# storage_client = storage.Client() +# bucket = storage_client.get_bucket(bucket_name) +# blob = bucket.blob(destination_blob_name) +# +# blob.upload_from_filename(source_file_name) +# +# print('File {} uploaded to {}.'.format( +# source_file_name, +# destination_blob_name)) +# +# +# def download_blob(bucket_name, source_blob_name, destination_file_name): +# # Uploads a blob from a bucket +# storage_client = storage.Client() +# bucket = storage_client.get_bucket(bucket_name) +# blob = bucket.blob(source_blob_name) +# +# blob.download_to_filename(destination_file_name) +# +# print('Blob {} downloaded to {}.'.format( +# source_blob_name, +# destination_file_name)) diff --git a/utils/layers.py b/utils/layers.py new file mode 100644 index 0000000000000000000000000000000000000000..218da9e90c7cac45ade504b45866f8f35fac5163 --- /dev/null +++ b/utils/layers.py @@ -0,0 +1,534 @@ +import torch.nn.functional as F + +from utils.general import * + +import torch +from torch import nn + +try: + from mish_cuda import MishCuda as Mish + +except: + class Mish(nn.Module): # https://github.com/digantamisra98/Mish + def forward(self, x): + return x * F.softplus(x).tanh() + +try: + from pytorch_wavelets import DWTForward, DWTInverse + + class DWT(nn.Module): + def __init__(self): + super(DWT, self).__init__() + self.xfm = DWTForward(J=1, wave='db1', mode='zero') + + def forward(self, x): + b,c,w,h = x.shape + yl, yh = self.xfm(x) + return torch.cat([yl/2., yh[0].view(b,-1,w//2,h//2)/2.+.5], 1) + +except: # using Reorg instead + class DWT(nn.Module): + def forward(self, x): + return torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1) + + +class Reorg(nn.Module): + def forward(self, x): + return torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1) + + +def make_divisible(v, divisor): + # Function ensures all layers have a channel number that is divisible by 8 + # https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py + return math.ceil(v / divisor) * divisor + + +class Flatten(nn.Module): + # Use after nn.AdaptiveAvgPool2d(1) to remove last 2 dimensions + def forward(self, x): + return x.view(x.size(0), -1) + + +class Concat(nn.Module): + # Concatenate a list of tensors along dimension + def __init__(self, dimension=1): + super(Concat, self).__init__() + self.d = dimension + + def forward(self, x): + return torch.cat(x, self.d) + + +class FeatureConcat(nn.Module): + def __init__(self, layers): + super(FeatureConcat, self).__init__() + self.layers = layers # layer indices + self.multiple = len(layers) > 1 # multiple layers flag + + def forward(self, x, outputs): + return torch.cat([outputs[i] for i in self.layers], 1) if self.multiple else outputs[self.layers[0]] + + +class FeatureConcat2(nn.Module): + def __init__(self, layers): + super(FeatureConcat2, self).__init__() + self.layers = layers # layer indices + self.multiple = len(layers) > 1 # multiple layers flag + + def forward(self, x, outputs): + return torch.cat([outputs[self.layers[0]], outputs[self.layers[1]].detach()], 1) + + +class FeatureConcat3(nn.Module): + def __init__(self, layers): + super(FeatureConcat3, self).__init__() + self.layers = layers # layer indices + self.multiple = len(layers) > 1 # multiple layers flag + + def forward(self, x, outputs): + return torch.cat([outputs[self.layers[0]], outputs[self.layers[1]].detach(), outputs[self.layers[2]].detach()], 1) + + +class FeatureConcat_l(nn.Module): + def __init__(self, layers): + super(FeatureConcat_l, self).__init__() + self.layers = layers # layer indices + self.multiple = len(layers) > 1 # multiple layers flag + + def forward(self, x, outputs): + return torch.cat([outputs[i][:,:outputs[i].shape[1]//2,:,:] for i in self.layers], 1) if self.multiple else outputs[self.layers[0]][:,:outputs[self.layers[0]].shape[1]//2,:,:] + + +class WeightedFeatureFusion(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers, weight=False): + super(WeightedFeatureFusion, self).__init__() + self.layers = layers # layer indices + self.weight = weight # apply weights boolean + self.n = len(layers) + 1 # number of layers + if weight: + self.w = nn.Parameter(torch.zeros(self.n), requires_grad=True) # layer weights + + def forward(self, x, outputs): + # Weights + if self.weight: + w = torch.sigmoid(self.w) * (2 / self.n) # sigmoid weights (0-1) + x = x * w[0] + + # Fusion + nx = x.shape[1] # input channels + for i in range(self.n - 1): + a = outputs[self.layers[i]] * w[i + 1] if self.weight else outputs[self.layers[i]] # feature to add + na = a.shape[1] # feature channels + + # Adjust channels + if nx == na: # same shape + x = x + a + elif nx > na: # slice input + x[:, :na] = x[:, :na] + a # or a = nn.ZeroPad2d((0, 0, 0, 0, 0, dc))(a); x = x + a + else: # slice feature + x = x + a[:, :nx] + + return x + + +class MixConv2d(nn.Module): # MixConv: Mixed Depthwise Convolutional Kernels https://arxiv.org/abs/1907.09595 + def __init__(self, in_ch, out_ch, k=(3, 5, 7), stride=1, dilation=1, bias=True, method='equal_params'): + super(MixConv2d, self).__init__() + + groups = len(k) + if method == 'equal_ch': # equal channels per group + i = torch.linspace(0, groups - 1E-6, out_ch).floor() # out_ch indices + ch = [(i == g).sum() for g in range(groups)] + else: # 'equal_params': equal parameter count per group + b = [out_ch] + [0] * groups + a = np.eye(groups + 1, groups, k=-1) + a -= np.roll(a, 1, axis=1) + a *= np.array(k) ** 2 + a[0] = 1 + ch = np.linalg.lstsq(a, b, rcond=None)[0].round().astype(int) # solve for equal weight indices, ax = b + + self.m = nn.ModuleList([nn.Conv2d(in_channels=in_ch, + out_channels=ch[g], + kernel_size=k[g], + stride=stride, + padding=k[g] // 2, # 'same' pad + dilation=dilation, + bias=bias) for g in range(groups)]) + + def forward(self, x): + return torch.cat([m(x) for m in self.m], 1) + + +# Activation functions below ------------------------------------------------------------------------------------------- +class SwishImplementation(torch.autograd.Function): + @staticmethod + def forward(ctx, x): + ctx.save_for_backward(x) + return x * torch.sigmoid(x) + + @staticmethod + def backward(ctx, grad_output): + x = ctx.saved_tensors[0] + sx = torch.sigmoid(x) # sigmoid(ctx) + return grad_output * (sx * (1 + x * (1 - sx))) + + +class MishImplementation(torch.autograd.Function): + @staticmethod + def forward(ctx, x): + ctx.save_for_backward(x) + return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x))) + + @staticmethod + def backward(ctx, grad_output): + x = ctx.saved_tensors[0] + sx = torch.sigmoid(x) + fx = F.softplus(x).tanh() + return grad_output * (fx + x * sx * (1 - fx * fx)) + + +class MemoryEfficientSwish(nn.Module): + def forward(self, x): + return SwishImplementation.apply(x) + + +class MemoryEfficientMish(nn.Module): + def forward(self, x): + return MishImplementation.apply(x) + + +class Swish(nn.Module): + def forward(self, x): + return x * torch.sigmoid(x) + + +class HardSwish(nn.Module): # https://arxiv.org/pdf/1905.02244.pdf + def forward(self, x): + return x * F.hardtanh(x + 3, 0., 6., True) / 6. + + +class DeformConv2d(nn.Module): + def __init__(self, inc, outc, kernel_size=3, padding=1, stride=1, bias=None, modulation=False): + """ + Args: + modulation (bool, optional): If True, Modulated Defomable Convolution (Deformable ConvNets v2). + """ + super(DeformConv2d, self).__init__() + self.kernel_size = kernel_size + self.padding = padding + self.stride = stride + self.zero_padding = nn.ZeroPad2d(padding) + self.conv = nn.Conv2d(inc, outc, kernel_size=kernel_size, stride=kernel_size, bias=bias) + + self.p_conv = nn.Conv2d(inc, 2*kernel_size*kernel_size, kernel_size=3, padding=1, stride=stride) + nn.init.constant_(self.p_conv.weight, 0) + self.p_conv.register_backward_hook(self._set_lr) + + self.modulation = modulation + if modulation: + self.m_conv = nn.Conv2d(inc, kernel_size*kernel_size, kernel_size=3, padding=1, stride=stride) + nn.init.constant_(self.m_conv.weight, 0) + self.m_conv.register_backward_hook(self._set_lr) + + @staticmethod + def _set_lr(module, grad_input, grad_output): + grad_input = (grad_input[i] * 0.1 for i in range(len(grad_input))) + grad_output = (grad_output[i] * 0.1 for i in range(len(grad_output))) + + def forward(self, x): + offset = self.p_conv(x) + if self.modulation: + m = torch.sigmoid(self.m_conv(x)) + + dtype = offset.data.type() + ks = self.kernel_size + N = offset.size(1) // 2 + + if self.padding: + x = self.zero_padding(x) + + # (b, 2N, h, w) + p = self._get_p(offset, dtype) + + # (b, h, w, 2N) + p = p.contiguous().permute(0, 2, 3, 1) + q_lt = p.detach().floor() + q_rb = q_lt + 1 + + q_lt = torch.cat([torch.clamp(q_lt[..., :N], 0, x.size(2)-1), torch.clamp(q_lt[..., N:], 0, x.size(3)-1)], dim=-1).long() + q_rb = torch.cat([torch.clamp(q_rb[..., :N], 0, x.size(2)-1), torch.clamp(q_rb[..., N:], 0, x.size(3)-1)], dim=-1).long() + q_lb = torch.cat([q_lt[..., :N], q_rb[..., N:]], dim=-1) + q_rt = torch.cat([q_rb[..., :N], q_lt[..., N:]], dim=-1) + + # clip p + p = torch.cat([torch.clamp(p[..., :N], 0, x.size(2)-1), torch.clamp(p[..., N:], 0, x.size(3)-1)], dim=-1) + + # bilinear kernel (b, h, w, N) + g_lt = (1 + (q_lt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_lt[..., N:].type_as(p) - p[..., N:])) + g_rb = (1 - (q_rb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_rb[..., N:].type_as(p) - p[..., N:])) + g_lb = (1 + (q_lb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_lb[..., N:].type_as(p) - p[..., N:])) + g_rt = (1 - (q_rt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_rt[..., N:].type_as(p) - p[..., N:])) + + # (b, c, h, w, N) + x_q_lt = self._get_x_q(x, q_lt, N) + x_q_rb = self._get_x_q(x, q_rb, N) + x_q_lb = self._get_x_q(x, q_lb, N) + x_q_rt = self._get_x_q(x, q_rt, N) + + # (b, c, h, w, N) + x_offset = g_lt.unsqueeze(dim=1) * x_q_lt + \ + g_rb.unsqueeze(dim=1) * x_q_rb + \ + g_lb.unsqueeze(dim=1) * x_q_lb + \ + g_rt.unsqueeze(dim=1) * x_q_rt + + # modulation + if self.modulation: + m = m.contiguous().permute(0, 2, 3, 1) + m = m.unsqueeze(dim=1) + m = torch.cat([m for _ in range(x_offset.size(1))], dim=1) + x_offset *= m + + x_offset = self._reshape_x_offset(x_offset, ks) + out = self.conv(x_offset) + + return out + + def _get_p_n(self, N, dtype): + p_n_x, p_n_y = torch.meshgrid( + torch.arange(-(self.kernel_size-1)//2, (self.kernel_size-1)//2+1), + torch.arange(-(self.kernel_size-1)//2, (self.kernel_size-1)//2+1)) + # (2N, 1) + p_n = torch.cat([torch.flatten(p_n_x), torch.flatten(p_n_y)], 0) + p_n = p_n.view(1, 2*N, 1, 1).type(dtype) + + return p_n + + def _get_p_0(self, h, w, N, dtype): + p_0_x, p_0_y = torch.meshgrid( + torch.arange(1, h*self.stride+1, self.stride), + torch.arange(1, w*self.stride+1, self.stride)) + p_0_x = torch.flatten(p_0_x).view(1, 1, h, w).repeat(1, N, 1, 1) + p_0_y = torch.flatten(p_0_y).view(1, 1, h, w).repeat(1, N, 1, 1) + p_0 = torch.cat([p_0_x, p_0_y], 1).type(dtype) + + return p_0 + + def _get_p(self, offset, dtype): + N, h, w = offset.size(1)//2, offset.size(2), offset.size(3) + + # (1, 2N, 1, 1) + p_n = self._get_p_n(N, dtype) + # (1, 2N, h, w) + p_0 = self._get_p_0(h, w, N, dtype) + p = p_0 + p_n + offset + return p + + def _get_x_q(self, x, q, N): + b, h, w, _ = q.size() + padded_w = x.size(3) + c = x.size(1) + # (b, c, h*w) + x = x.contiguous().view(b, c, -1) + + # (b, h, w, N) + index = q[..., :N]*padded_w + q[..., N:] # offset_x*w + offset_y + # (b, c, h*w*N) + index = index.contiguous().unsqueeze(dim=1).expand(-1, c, -1, -1, -1).contiguous().view(b, c, -1) + + x_offset = x.gather(dim=-1, index=index).contiguous().view(b, c, h, w, N) + + return x_offset + + @staticmethod + def _reshape_x_offset(x_offset, ks): + b, c, h, w, N = x_offset.size() + x_offset = torch.cat([x_offset[..., s:s+ks].contiguous().view(b, c, h, w*ks) for s in range(0, N, ks)], dim=-1) + x_offset = x_offset.contiguous().view(b, c, h*ks, w*ks) + + return x_offset + + +class GAP(nn.Module): + def __init__(self): + super(GAP, self).__init__() + self.avg_pool = nn.AdaptiveAvgPool2d(1) + def forward(self, x): + #b, c, _, _ = x.size() + return self.avg_pool(x)#.view(b, c) + + +class Silence(nn.Module): + def __init__(self): + super(Silence, self).__init__() + def forward(self, x): + return x + + +class ScaleChannel(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(ScaleChannel, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]] + return x.expand_as(a) * a + + +class ShiftChannel(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(ShiftChannel, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]] + return a.expand_as(x) + x + + +class ShiftChannel2D(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(ShiftChannel2D, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]].view(1,-1,1,1) + return a.expand_as(x) + x + + +class ControlChannel(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(ControlChannel, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]] + return a.expand_as(x) * x + + +class ControlChannel2D(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(ControlChannel2D, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]].view(1,-1,1,1) + return a.expand_as(x) * x + + +class AlternateChannel(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(AlternateChannel, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]] + return torch.cat([a.expand_as(x), x], dim=1) + + +class AlternateChannel2D(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(AlternateChannel2D, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]].view(1,-1,1,1) + return torch.cat([a.expand_as(x), x], dim=1) + + +class SelectChannel(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(SelectChannel, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]] + return a.sigmoid().expand_as(x) * x + + +class SelectChannel2D(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(SelectChannel2D, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]].view(1,-1,1,1) + return a.sigmoid().expand_as(x) * x + + +class ScaleSpatial(nn.Module): # weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, layers): + super(ScaleSpatial, self).__init__() + self.layers = layers # layer indices + + def forward(self, x, outputs): + a = outputs[self.layers[0]] + return x * a + + +class ImplicitA(nn.Module): + def __init__(self, channel): + super(ImplicitA, self).__init__() + self.channel = channel + self.implicit = nn.Parameter(torch.zeros(1, channel, 1, 1)) + nn.init.normal_(self.implicit, std=.02) + + def forward(self): + return self.implicit + + +class ImplicitC(nn.Module): + def __init__(self, channel): + super(ImplicitC, self).__init__() + self.channel = channel + self.implicit = nn.Parameter(torch.zeros(1, channel, 1, 1)) + nn.init.normal_(self.implicit, std=.02) + + def forward(self): + return self.implicit + + +class ImplicitM(nn.Module): + def __init__(self, channel): + super(ImplicitM, self).__init__() + self.channel = channel + self.implicit = nn.Parameter(torch.ones(1, channel, 1, 1)) + nn.init.normal_(self.implicit, mean=1., std=.02) + + def forward(self): + return self.implicit + + + +class Implicit2DA(nn.Module): + def __init__(self, atom, channel): + super(Implicit2DA, self).__init__() + self.channel = channel + self.implicit = nn.Parameter(torch.zeros(1, atom, channel, 1)) + nn.init.normal_(self.implicit, std=.02) + + def forward(self): + return self.implicit + + +class Implicit2DC(nn.Module): + def __init__(self, atom, channel): + super(Implicit2DC, self).__init__() + self.channel = channel + self.implicit = nn.Parameter(torch.zeros(1, atom, channel, 1)) + nn.init.normal_(self.implicit, std=.02) + + def forward(self): + return self.implicit + + +class Implicit2DM(nn.Module): + def __init__(self, atom, channel): + super(Implicit2DM, self).__init__() + self.channel = channel + self.implicit = nn.Parameter(torch.ones(1, atom, channel, 1)) + nn.init.normal_(self.implicit, mean=1., std=.02) + + def forward(self): + return self.implicit + + + \ No newline at end of file diff --git a/utils/loss.py b/utils/loss.py new file mode 100644 index 0000000000000000000000000000000000000000..8eeb60bdf7a777bb10b136e334d9331ebdd040b2 --- /dev/null +++ b/utils/loss.py @@ -0,0 +1,173 @@ +# Loss functions + +import torch +import torch.nn as nn + +from utils.general import bbox_iou +from utils.torch_utils import is_parallel + + +def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441 + # return positive, negative label smoothing BCE targets + return 1.0 - 0.5 * eps, 0.5 * eps + + +class BCEBlurWithLogitsLoss(nn.Module): + # BCEwithLogitLoss() with reduced missing label effects. + def __init__(self, alpha=0.05): + super(BCEBlurWithLogitsLoss, self).__init__() + self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss() + self.alpha = alpha + + def forward(self, pred, true): + loss = self.loss_fcn(pred, true) + pred = torch.sigmoid(pred) # prob from logits + dx = pred - true # reduce only missing label effects + # dx = (pred - true).abs() # reduce missing label and false label effects + alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4)) + loss *= alpha_factor + return loss.mean() + + +class FocalLoss(nn.Module): + # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) + def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): + super(FocalLoss, self).__init__() + self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() + self.gamma = gamma + self.alpha = alpha + self.reduction = loss_fcn.reduction + self.loss_fcn.reduction = 'none' # required to apply FL to each element + + def forward(self, pred, true): + loss = self.loss_fcn(pred, true) + # p_t = torch.exp(-loss) + # loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability + + # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py + pred_prob = torch.sigmoid(pred) # prob from logits + p_t = true * pred_prob + (1 - true) * (1 - pred_prob) + alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) + modulating_factor = (1.0 - p_t) ** self.gamma + loss *= alpha_factor * modulating_factor + + if self.reduction == 'mean': + return loss.mean() + elif self.reduction == 'sum': + return loss.sum() + else: # 'none' + return loss + + +def compute_loss(p, targets, model): # predictions, targets, model + device = targets.device + #print(device) + lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device) + tcls, tbox, indices, anchors = build_targets(p, targets, model) # targets + h = model.hyp # hyperparameters + + # Define criteria + BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.Tensor([h['cls_pw']])).to(device) + BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.Tensor([h['obj_pw']])).to(device) + + # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3 + cp, cn = smooth_BCE(eps=0.0) + + # Focal loss + g = h['fl_gamma'] # focal loss gamma + if g > 0: + BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g) + + # Losses + nt = 0 # number of targets + no = len(p) # number of outputs + balance = [4.0, 1.0, 0.4] if no == 3 else [4.0, 1.0, 0.4, 0.1] # P3-5 or P3-6 + balance = [4.0, 1.0, 0.5, 0.4, 0.1] if no == 5 else balance + for i, pi in enumerate(p): # layer index, layer predictions + b, a, gj, gi = indices[i] # image, anchor, gridy, gridx + tobj = torch.zeros_like(pi[..., 0], device=device) # target obj + + n = b.shape[0] # number of targets + if n: + nt += n # cumulative targets + ps = pi[b, a, gj, gi] # prediction subset corresponding to targets + + # Regression + pxy = ps[:, :2].sigmoid() * 2. - 0.5 + pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i] + pbox = torch.cat((pxy, pwh), 1).to(device) # predicted box + iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target) + lbox += (1.0 - iou).mean() # iou loss + + # Objectness + tobj[b, a, gj, gi] = (1.0 - model.gr) + model.gr * iou.detach().clamp(0).type(tobj.dtype) # iou ratio + + # Classification + if model.nc > 1: # cls loss (only if multiple classes) + t = torch.full_like(ps[:, 5:], cn, device=device) # targets + t[range(n), tcls[i]] = cp + lcls += BCEcls(ps[:, 5:], t) # BCE + + # Append targets to text file + # with open('targets.txt', 'a') as file: + # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] + + lobj += BCEobj(pi[..., 4], tobj) * balance[i] # obj loss + + s = 3 / no # output count scaling + lbox *= h['box'] * s + lobj *= h['obj'] * s * (1.4 if no >= 4 else 1.) + lcls *= h['cls'] * s + bs = tobj.shape[0] # batch size + + loss = lbox + lobj + lcls + return loss * bs, torch.cat((lbox, lobj, lcls, loss)).detach() + + +def build_targets(p, targets, model): + nt = targets.shape[0] # number of anchors, targets + tcls, tbox, indices, anch = [], [], [], [] + gain = torch.ones(6, device=targets.device) # normalized to gridspace gain + off = torch.tensor([[1, 0], [0, 1], [-1, 0], [0, -1]], device=targets.device).float() # overlap offsets + + g = 0.5 # offset + multi_gpu = is_parallel(model) + for i, jj in enumerate(model.module.yolo_layers if multi_gpu else model.yolo_layers): + # get number of grid points and anchor vec for this yolo layer + anchors = model.module.module_list[jj].anchor_vec if multi_gpu else model.module_list[jj].anchor_vec + gain[2:] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain + + # Match targets to anchors + a, t, offsets = [], targets * gain, 0 + if nt: + na = anchors.shape[0] # number of anchors + at = torch.arange(na).view(na, 1).repeat(1, nt) # anchor tensor, same as .repeat_interleave(nt) + r = t[None, :, 4:6] / anchors[:, None] # wh ratio + j = torch.max(r, 1. / r).max(2)[0] < model.hyp['anchor_t'] # compare + # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n) = wh_iou(anchors(3,2), gwh(n,2)) + a, t = at[j], t.repeat(na, 1, 1)[j] # filter + + # overlaps + gxy = t[:, 2:4] # grid xy + z = torch.zeros_like(gxy) + j, k = ((gxy % 1. < g) & (gxy > 1.)).T + l, m = ((gxy % 1. > (1 - g)) & (gxy < (gain[[2, 3]] - 1.))).T + a, t = torch.cat((a, a[j], a[k], a[l], a[m]), 0), torch.cat((t, t[j], t[k], t[l], t[m]), 0) + offsets = torch.cat((z, z[j] + off[0], z[k] + off[1], z[l] + off[2], z[m] + off[3]), 0) * g + + # Define + b, c = t[:, :2].long().T # image, class + gxy = t[:, 2:4] # grid xy + gwh = t[:, 4:6] # grid wh + gij = (gxy - offsets).long() + gi, gj = gij.T # grid xy indices + + # Append + #indices.append((b, a, gj, gi)) # image, anchor, grid indices + indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices + tbox.append(torch.cat((gxy - gij, gwh), 1)) # box + anch.append(anchors[a]) # anchors + tcls.append(c) # class + + return tcls, tbox, indices, anch + diff --git a/utils/metrics.py b/utils/metrics.py new file mode 100644 index 0000000000000000000000000000000000000000..04c578a98ae45b6a026f528a45bd9c23566ffd20 --- /dev/null +++ b/utils/metrics.py @@ -0,0 +1,140 @@ +# Model validation metrics + +import matplotlib.pyplot as plt +import numpy as np + + +def fitness(x): + # Model fitness as a weighted combination of metrics + w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] + return (x[:, :4] * w).sum(1) + + +def fitness_p(x): + # Model fitness as a weighted combination of metrics + w = [1.0, 0.0, 0.0, 0.0] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] + return (x[:, :4] * w).sum(1) + + +def fitness_r(x): + # Model fitness as a weighted combination of metrics + w = [0.0, 1.0, 0.0, 0.0] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] + return (x[:, :4] * w).sum(1) + + +def fitness_ap50(x): + # Model fitness as a weighted combination of metrics + w = [0.0, 0.0, 1.0, 0.0] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] + return (x[:, :4] * w).sum(1) + + +def fitness_ap(x): + # Model fitness as a weighted combination of metrics + w = [0.0, 0.0, 0.0, 1.0] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] + return (x[:, :4] * w).sum(1) + + +def fitness_f(x): + # Model fitness as a weighted combination of metrics + #w = [0.0, 0.0, 0.0, 1.0] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] + return ((x[:, 0]*x[:, 1])/(x[:, 0]+x[:, 1])) + + +def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, fname='precision-recall_curve.png'): + """ Compute the average precision, given the recall and precision curves. + Source: https://github.com/rafaelpadilla/Object-Detection-Metrics. + # Arguments + tp: True positives (nparray, nx1 or nx10). + conf: Objectness value from 0-1 (nparray). + pred_cls: Predicted object classes (nparray). + target_cls: True object classes (nparray). + plot: Plot precision-recall curve at mAP@0.5 + fname: Plot filename + # Returns + The average precision as computed in py-faster-rcnn. + """ + + # Sort by objectness + i = np.argsort(-conf) + tp, conf, pred_cls = tp[i], conf[i], pred_cls[i] + + # Find unique classes + unique_classes = np.unique(target_cls) + + # Create Precision-Recall curve and compute AP for each class + px, py = np.linspace(0, 1, 1000), [] # for plotting + pr_score = 0.1 # score to evaluate P and R https://github.com/ultralytics/yolov3/issues/898 + s = [unique_classes.shape[0], tp.shape[1]] # number class, number iou thresholds (i.e. 10 for mAP0.5...0.95) + ap, p, r = np.zeros(s), np.zeros(s), np.zeros(s) + for ci, c in enumerate(unique_classes): + i = pred_cls == c + n_l = (target_cls == c).sum() # number of labels + n_p = i.sum() # number of predictions + + if n_p == 0 or n_l == 0: + continue + else: + # Accumulate FPs and TPs + fpc = (1 - tp[i]).cumsum(0) + tpc = tp[i].cumsum(0) + + # Recall + recall = tpc / (n_l + 1e-16) # recall curve + r[ci] = np.interp(-pr_score, -conf[i], recall[:, 0]) # r at pr_score, negative x, xp because xp decreases + + # Precision + precision = tpc / (tpc + fpc) # precision curve + p[ci] = np.interp(-pr_score, -conf[i], precision[:, 0]) # p at pr_score + + # AP from recall-precision curve + for j in range(tp.shape[1]): + ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j]) + if j == 0: + py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5 + + # Compute F1 score (harmonic mean of precision and recall) + f1 = 2 * p * r / (p + r + 1e-16) + + if plot: + py = np.stack(py, axis=1) + fig, ax = plt.subplots(1, 1, figsize=(5, 5)) + ax.plot(px, py, linewidth=0.5, color='grey') # plot(recall, precision) + ax.plot(px, py.mean(1), linewidth=2, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean()) + ax.set_xlabel('Recall') + ax.set_ylabel('Precision') + ax.set_xlim(0, 1) + ax.set_ylim(0, 1) + plt.legend() + fig.tight_layout() + fig.savefig(fname, dpi=200) + + return p, r, ap, f1, unique_classes.astype('int32') + + +def compute_ap(recall, precision): + """ Compute the average precision, given the recall and precision curves. + Source: https://github.com/rbgirshick/py-faster-rcnn. + # Arguments + recall: The recall curve (list). + precision: The precision curve (list). + # Returns + The average precision as computed in py-faster-rcnn. + """ + + # Append sentinel values to beginning and end + mrec = recall # np.concatenate(([0.], recall, [recall[-1] + 1E-3])) + mpre = precision # np.concatenate(([0.], precision, [0.])) + + # Compute the precision envelope + mpre = np.flip(np.maximum.accumulate(np.flip(mpre))) + + # Integrate area under curve + method = 'interp' # methods: 'continuous', 'interp' + if method == 'interp': + x = np.linspace(0, 1, 101) # 101-point interp (COCO) + ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate + else: # 'continuous' + i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes + ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve + + return ap, mpre, mrec diff --git a/utils/parse_config.py b/utils/parse_config.py new file mode 100644 index 0000000000000000000000000000000000000000..d6cbfdd81f54c7017bcd35bfeccca7f6578f25ae --- /dev/null +++ b/utils/parse_config.py @@ -0,0 +1,71 @@ +import os + +import numpy as np + + +def parse_model_cfg(path): + # Parse the yolo *.cfg file and return module definitions path may be 'cfg/yolov3.cfg', 'yolov3.cfg', or 'yolov3' + if not path.endswith('.cfg'): # add .cfg suffix if omitted + path += '.cfg' + if not os.path.exists(path) and os.path.exists('cfg' + os.sep + path): # add cfg/ prefix if omitted + path = 'cfg' + os.sep + path + + with open(path, 'r') as f: + lines = f.read().split('\n') + lines = [x for x in lines if x and not x.startswith('#')] + lines = [x.rstrip().lstrip() for x in lines] # get rid of fringe whitespaces + mdefs = [] # module definitions + for line in lines: + if line.startswith('['): # This marks the start of a new block + mdefs.append({}) + mdefs[-1]['type'] = line[1:-1].rstrip() + if mdefs[-1]['type'] == 'convolutional': + mdefs[-1]['batch_normalize'] = 0 # pre-populate with zeros (may be overwritten later) + + else: + key, val = line.split("=") + key = key.rstrip() + + if key == 'anchors': # return nparray + mdefs[-1][key] = np.array([float(x) for x in val.split(',')]).reshape((-1, 2)) # np anchors + elif (key in ['from', 'layers', 'mask']) or (key == 'size' and ',' in val): # return array + mdefs[-1][key] = [int(x) for x in val.split(',')] + else: + val = val.strip() + if val.isnumeric(): # return int or float + mdefs[-1][key] = int(val) if (int(val) - float(val)) == 0 else float(val) + else: + mdefs[-1][key] = val # return string + + # Check all fields are supported + supported = ['type', 'batch_normalize', 'filters', 'size', 'stride', 'pad', 'activation', 'layers', 'groups', + 'from', 'mask', 'anchors', 'classes', 'num', 'jitter', 'ignore_thresh', 'truth_thresh', 'random', + 'stride_x', 'stride_y', 'weights_type', 'weights_normalization', 'scale_x_y', 'beta_nms', 'nms_kind', + 'iou_loss', 'iou_normalizer', 'cls_normalizer', 'iou_thresh', 'atoms', 'na', 'nc'] + + f = [] # fields + for x in mdefs[1:]: + [f.append(k) for k in x if k not in f] + u = [x for x in f if x not in supported] # unsupported fields + assert not any(u), "Unsupported fields %s in %s. See https://github.com/ultralytics/yolov3/issues/631" % (u, path) + + return mdefs + + +def parse_data_cfg(path): + # Parses the data configuration file + if not os.path.exists(path) and os.path.exists('data' + os.sep + path): # add data/ prefix if omitted + path = 'data' + os.sep + path + + with open(path, 'r') as f: + lines = f.readlines() + + options = dict() + for line in lines: + line = line.strip() + if line == '' or line.startswith('#'): + continue + key, val = line.split('=') + options[key.strip()] = val.strip() + + return options diff --git a/utils/plots.py b/utils/plots.py new file mode 100644 index 0000000000000000000000000000000000000000..c90a96b8fabbf7d4d3f0c88a927199ccc3858a96 --- /dev/null +++ b/utils/plots.py @@ -0,0 +1,380 @@ +# Plotting utils + +import glob +import math +import os +import random +from copy import copy +from pathlib import Path + +import cv2 +import matplotlib +import matplotlib.pyplot as plt +import numpy as np +import torch +import yaml +from PIL import Image +from scipy.signal import butter, filtfilt + +from utils.general import xywh2xyxy, xyxy2xywh +from utils.metrics import fitness + +# Settings +matplotlib.use('Agg') # for writing to files only + + +def color_list(): + # Return first 10 plt colors as (r,g,b) https://stackoverflow.com/questions/51350872/python-from-color-name-to-rgb + def hex2rgb(h): + return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4)) + + return [hex2rgb(h) for h in plt.rcParams['axes.prop_cycle'].by_key()['color']] + + +def hist2d(x, y, n=100): + # 2d histogram used in labels.png and evolve.png + xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n) + hist, xedges, yedges = np.histogram2d(x, y, (xedges, yedges)) + xidx = np.clip(np.digitize(x, xedges) - 1, 0, hist.shape[0] - 1) + yidx = np.clip(np.digitize(y, yedges) - 1, 0, hist.shape[1] - 1) + return np.log(hist[xidx, yidx]) + + +def butter_lowpass_filtfilt(data, cutoff=1500, fs=50000, order=5): + # https://stackoverflow.com/questions/28536191/how-to-filter-smooth-with-scipy-numpy + def butter_lowpass(cutoff, fs, order): + nyq = 0.5 * fs + normal_cutoff = cutoff / nyq + return butter(order, normal_cutoff, btype='low', analog=False) + + b, a = butter_lowpass(cutoff, fs, order=order) + return filtfilt(b, a, data) # forward-backward filter + + +def plot_one_box(x, img, color=None, label=None, line_thickness=None): + # Plots one bounding box on image img + tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness + color = color or [random.randint(0, 255) for _ in range(3)] + c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3])) + cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA) + if label: + tf = max(tl - 1, 1) # font thickness + t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0] + c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3 + cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled + cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA) + + +def plot_wh_methods(): # from utils.general import *; plot_wh_methods() + # Compares the two methods for width-height anchor multiplication + # https://github.com/ultralytics/yolov3/issues/168 + x = np.arange(-4.0, 4.0, .1) + ya = np.exp(x) + yb = torch.sigmoid(torch.from_numpy(x)).numpy() * 2 + + fig = plt.figure(figsize=(6, 3), dpi=150) + plt.plot(x, ya, '.-', label='YOLO') + plt.plot(x, yb ** 2, '.-', label='YOLO ^2') + plt.plot(x, yb ** 1.6, '.-', label='YOLO ^1.6') + plt.xlim(left=-4, right=4) + plt.ylim(bottom=0, top=6) + plt.xlabel('input') + plt.ylabel('output') + plt.grid() + plt.legend() + fig.tight_layout() + fig.savefig('comparison.png', dpi=200) + + +def output_to_target(output, width, height): + # Convert model output to target format [batch_id, class_id, x, y, w, h, conf] + if isinstance(output, torch.Tensor): + output = output.cpu().numpy() + + targets = [] + for i, o in enumerate(output): + if o is not None: + for pred in o: + box = pred[:4] + w = (box[2] - box[0]) / width + h = (box[3] - box[1]) / height + x = box[0] / width + w / 2 + y = box[1] / height + h / 2 + conf = pred[4] + cls = int(pred[5]) + + targets.append([i, cls, x, y, w, h, conf]) + + return np.array(targets) + + +def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=640, max_subplots=16): + # Plot image grid with labels + + if isinstance(images, torch.Tensor): + images = images.cpu().float().numpy() + if isinstance(targets, torch.Tensor): + targets = targets.cpu().numpy() + + # un-normalise + if np.max(images[0]) <= 1: + images *= 255 + + tl = 3 # line thickness + tf = max(tl - 1, 1) # font thickness + bs, _, h, w = images.shape # batch size, _, height, width + bs = min(bs, max_subplots) # limit plot images + ns = np.ceil(bs ** 0.5) # number of subplots (square) + + # Check if we should resize + scale_factor = max_size / max(h, w) + if scale_factor < 1: + h = math.ceil(scale_factor * h) + w = math.ceil(scale_factor * w) + + colors = color_list() # list of colors + mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init + for i, img in enumerate(images): + if i == max_subplots: # if last batch has fewer images than we expect + break + + block_x = int(w * (i // ns)) + block_y = int(h * (i % ns)) + + img = img.transpose(1, 2, 0) + if scale_factor < 1: + img = cv2.resize(img, (w, h)) + + mosaic[block_y:block_y + h, block_x:block_x + w, :] = img + if len(targets) > 0: + image_targets = targets[targets[:, 0] == i] + boxes = xywh2xyxy(image_targets[:, 2:6]).T + classes = image_targets[:, 1].astype('int') + labels = image_targets.shape[1] == 6 # labels if no conf column + conf = None if labels else image_targets[:, 6] # check for confidence presence (label vs pred) + + boxes[[0, 2]] *= w + boxes[[0, 2]] += block_x + boxes[[1, 3]] *= h + boxes[[1, 3]] += block_y + for j, box in enumerate(boxes.T): + cls = int(classes[j]) + color = colors[cls % len(colors)] + cls = names[cls] if names else cls + if labels or conf[j] > 0.25: # 0.25 conf thresh + label = '%s' % cls if labels else '%s %.1f' % (cls, conf[j]) + plot_one_box(box, mosaic, label=label, color=color, line_thickness=tl) + + # Draw image filename labels + if paths: + label = Path(paths[i]).name[:40] # trim to 40 char + t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0] + cv2.putText(mosaic, label, (block_x + 5, block_y + t_size[1] + 5), 0, tl / 3, [220, 220, 220], thickness=tf, + lineType=cv2.LINE_AA) + + # Image border + cv2.rectangle(mosaic, (block_x, block_y), (block_x + w, block_y + h), (255, 255, 255), thickness=3) + + if fname: + r = min(1280. / max(h, w) / ns, 1.0) # ratio to limit image size + mosaic = cv2.resize(mosaic, (int(ns * w * r), int(ns * h * r)), interpolation=cv2.INTER_AREA) + # cv2.imwrite(fname, cv2.cvtColor(mosaic, cv2.COLOR_BGR2RGB)) # cv2 save + Image.fromarray(mosaic).save(fname) # PIL save + return mosaic + + +def plot_lr_scheduler(optimizer, scheduler, epochs=300, save_dir=''): + # Plot LR simulating training for full epochs + optimizer, scheduler = copy(optimizer), copy(scheduler) # do not modify originals + y = [] + for _ in range(epochs): + scheduler.step() + y.append(optimizer.param_groups[0]['lr']) + plt.plot(y, '.-', label='LR') + plt.xlabel('epoch') + plt.ylabel('LR') + plt.grid() + plt.xlim(0, epochs) + plt.ylim(0) + plt.tight_layout() + plt.savefig(Path(save_dir) / 'LR.png', dpi=200) + + +def plot_test_txt(): # from utils.general import *; plot_test() + # Plot test.txt histograms + x = np.loadtxt('test.txt', dtype=np.float32) + box = xyxy2xywh(x[:, :4]) + cx, cy = box[:, 0], box[:, 1] + + fig, ax = plt.subplots(1, 1, figsize=(6, 6), tight_layout=True) + ax.hist2d(cx, cy, bins=600, cmax=10, cmin=0) + ax.set_aspect('equal') + plt.savefig('hist2d.png', dpi=300) + + fig, ax = plt.subplots(1, 2, figsize=(12, 6), tight_layout=True) + ax[0].hist(cx, bins=600) + ax[1].hist(cy, bins=600) + plt.savefig('hist1d.png', dpi=200) + + +def plot_targets_txt(): # from utils.general import *; plot_targets_txt() + # Plot targets.txt histograms + x = np.loadtxt('targets.txt', dtype=np.float32).T + s = ['x targets', 'y targets', 'width targets', 'height targets'] + fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True) + ax = ax.ravel() + for i in range(4): + ax[i].hist(x[i], bins=100, label='%.3g +/- %.3g' % (x[i].mean(), x[i].std())) + ax[i].legend() + ax[i].set_title(s[i]) + plt.savefig('targets.jpg', dpi=200) + + +def plot_study_txt(f='study.txt', x=None): # from utils.general import *; plot_study_txt() + # Plot study.txt generated by test.py + fig, ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True) + ax = ax.ravel() + + fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True) + for f in ['study/study_coco_yolo%s.txt' % x for x in ['s', 'm', 'l', 'x']]: + y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T + x = np.arange(y.shape[1]) if x is None else np.array(x) + s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_inference (ms/img)', 't_NMS (ms/img)', 't_total (ms/img)'] + for i in range(7): + ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8) + ax[i].set_title(s[i]) + + j = y[3].argmax() + 1 + ax2.plot(y[6, :j], y[3, :j] * 1E2, '.-', linewidth=2, markersize=8, + label=Path(f).stem.replace('study_coco_', '').replace('yolo', 'YOLO')) + + ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5], + 'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet') + + ax2.grid() + ax2.set_xlim(0, 30) + ax2.set_ylim(28, 50) + ax2.set_yticks(np.arange(30, 55, 5)) + ax2.set_xlabel('GPU Speed (ms/img)') + ax2.set_ylabel('COCO AP val') + ax2.legend(loc='lower right') + plt.savefig('study_mAP_latency.png', dpi=300) + plt.savefig(f.replace('.txt', '.png'), dpi=300) + + +def plot_labels(labels, save_dir=''): + # plot dataset labels + c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes + nc = int(c.max() + 1) # number of classes + + fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True) + ax = ax.ravel() + ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8) + ax[0].set_xlabel('classes') + ax[1].scatter(b[0], b[1], c=hist2d(b[0], b[1], 90), cmap='jet') + ax[1].set_xlabel('x') + ax[1].set_ylabel('y') + ax[2].scatter(b[2], b[3], c=hist2d(b[2], b[3], 90), cmap='jet') + ax[2].set_xlabel('width') + ax[2].set_ylabel('height') + plt.savefig(Path(save_dir) / 'labels.png', dpi=200) + plt.close() + + # seaborn correlogram + try: + import seaborn as sns + import pandas as pd + x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height']) + sns.pairplot(x, corner=True, diag_kind='hist', kind='scatter', markers='o', + plot_kws=dict(s=3, edgecolor=None, linewidth=1, alpha=0.02), + diag_kws=dict(bins=50)) + plt.savefig(Path(save_dir) / 'labels_correlogram.png', dpi=200) + plt.close() + except Exception as e: + pass + + +def plot_evolution(yaml_file='data/hyp.finetune.yaml'): # from utils.general import *; plot_evolution() + # Plot hyperparameter evolution results in evolve.txt + with open(yaml_file) as f: + hyp = yaml.load(f, Loader=yaml.FullLoader) + x = np.loadtxt('evolve.txt', ndmin=2) + f = fitness(x) + # weights = (f - f.min()) ** 2 # for weighted results + plt.figure(figsize=(10, 12), tight_layout=True) + matplotlib.rc('font', **{'size': 8}) + for i, (k, v) in enumerate(hyp.items()): + y = x[:, i + 7] + # mu = (y * weights).sum() / weights.sum() # best weighted result + mu = y[f.argmax()] # best single result + plt.subplot(6, 5, i + 1) + plt.scatter(y, f, c=hist2d(y, f, 20), cmap='viridis', alpha=.8, edgecolors='none') + plt.plot(mu, f.max(), 'k+', markersize=15) + plt.title('%s = %.3g' % (k, mu), fontdict={'size': 9}) # limit to 40 characters + if i % 5 != 0: + plt.yticks([]) + print('%15s: %.3g' % (k, mu)) + plt.savefig('evolve.png', dpi=200) + print('\nPlot saved as evolve.png') + + +def plot_results_overlay(start=0, stop=0): # from utils.general import *; plot_results_overlay() + # Plot training 'results*.txt', overlaying train and val losses + s = ['train', 'train', 'train', 'Precision', 'mAP@0.5', 'val', 'val', 'val', 'Recall', 'mAP@0.5:0.95'] # legends + t = ['Box', 'Objectness', 'Classification', 'P-R', 'mAP-F1'] # titles + for f in sorted(glob.glob('results*.txt') + glob.glob('../../Downloads/results*.txt')): + results = np.loadtxt(f, usecols=[2, 3, 4, 8, 9, 12, 13, 14, 10, 11], ndmin=2).T + n = results.shape[1] # number of rows + x = range(start, min(stop, n) if stop else n) + fig, ax = plt.subplots(1, 5, figsize=(14, 3.5), tight_layout=True) + ax = ax.ravel() + for i in range(5): + for j in [i, i + 5]: + y = results[j, x] + ax[i].plot(x, y, marker='.', label=s[j]) + # y_smooth = butter_lowpass_filtfilt(y) + # ax[i].plot(x, np.gradient(y_smooth), marker='.', label=s[j]) + + ax[i].set_title(t[i]) + ax[i].legend() + ax[i].set_ylabel(f) if i == 0 else None # add filename + fig.savefig(f.replace('.txt', '.png'), dpi=200) + + +def plot_results(start=0, stop=0, bucket='', id=(), labels=(), save_dir=''): + # from utils.general import *; plot_results(save_dir='runs/train/exp0') + # Plot training 'results*.txt' + fig, ax = plt.subplots(2, 5, figsize=(12, 6)) + ax = ax.ravel() + s = ['Box', 'Objectness', 'Classification', 'Precision', 'Recall', + 'val Box', 'val Objectness', 'val Classification', 'mAP@0.5', 'mAP@0.5:0.95'] + if bucket: + # os.system('rm -rf storage.googleapis.com') + # files = ['https://storage.googleapis.com/%s/results%g.txt' % (bucket, x) for x in id] + files = ['%g.txt' % x for x in id] + c = ('gsutil cp ' + '%s ' * len(files) + '.') % tuple('gs://%s/%g.txt' % (bucket, x) for x in id) + os.system(c) + else: + files = glob.glob(str(Path(save_dir) / '*.txt')) + glob.glob('../../Downloads/results*.txt') + assert len(files), 'No results.txt files found in %s, nothing to plot.' % os.path.abspath(save_dir) + for fi, f in enumerate(files): + try: + results = np.loadtxt(f, usecols=[2, 3, 4, 8, 9, 12, 13, 14, 10, 11], ndmin=2).T + n = results.shape[1] # number of rows + x = range(start, min(stop, n) if stop else n) + for i in range(10): + y = results[i, x] + if i in [0, 1, 2, 5, 6, 7]: + y[y == 0] = np.nan # don't show zero loss values + # y /= y[0] # normalize + label = labels[fi] if len(labels) else Path(f).stem + ax[i].plot(x, y, marker='.', label=label, linewidth=1, markersize=6) + ax[i].set_title(s[i]) + # if i in [5, 6, 7]: # share train and val loss y axes + # ax[i].get_shared_y_axes().join(ax[i], ax[i - 5]) + except Exception as e: + print('Warning: Plotting error for %s; %s' % (f, e)) + + fig.tight_layout() + ax[1].legend() + fig.savefig(Path(save_dir) / 'results.png', dpi=200) diff --git a/utils/torch_utils.py b/utils/torch_utils.py new file mode 100644 index 0000000000000000000000000000000000000000..4d07baa9f06de6b32eb79ab5034f16d094aa6d67 --- /dev/null +++ b/utils/torch_utils.py @@ -0,0 +1,240 @@ +# PyTorch utils + +import logging +import math +import os +import time +from contextlib import contextmanager +from copy import deepcopy + +import torch +import torch.backends.cudnn as cudnn +import torch.nn as nn +import torch.nn.functional as F +import torchvision + +logger = logging.getLogger(__name__) + + +@contextmanager +def torch_distributed_zero_first(local_rank: int): + """ + Decorator to make all processes in distributed training wait for each local_master to do something. + """ + if local_rank not in [-1, 0]: + torch.distributed.barrier() + yield + if local_rank == 0: + torch.distributed.barrier() + + +def init_torch_seeds(seed=0): + # Speed-reproducibility tradeoff https://pytorch.org/docs/stable/notes/randomness.html + torch.manual_seed(seed) + if seed == 0: # slower, more reproducible + cudnn.deterministic = True + cudnn.benchmark = False + else: # faster, less reproducible + cudnn.deterministic = False + cudnn.benchmark = True + + +def select_device(device='', batch_size=None): + # device = 'cpu' or '0' or '0,1,2,3' + cpu_request = device.lower() == 'cpu' + if device and not cpu_request: # if device requested other than 'cpu' + os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable + assert torch.cuda.is_available(), 'CUDA unavailable, invalid device %s requested' % device # check availablity + + cuda = False if cpu_request else torch.cuda.is_available() + if cuda: + c = 1024 ** 2 # bytes to MB + ng = torch.cuda.device_count() + if ng > 1 and batch_size: # check that batch_size is compatible with device_count + assert batch_size % ng == 0, 'batch-size %g not multiple of GPU count %g' % (batch_size, ng) + x = [torch.cuda.get_device_properties(i) for i in range(ng)] + s = f'Using torch {torch.__version__} ' + for i in range(0, ng): + if i == 1: + s = ' ' * len(s) + logger.info("%sCUDA:%g (%s, %dMB)" % (s, i, x[i].name, x[i].total_memory / c)) + else: + logger.info(f'Using torch {torch.__version__} CPU') + + logger.info('') # skip a line + return torch.device('cuda:0' if cuda else 'cpu') + + +def time_synchronized(): + torch.cuda.synchronize() if torch.cuda.is_available() else None + return time.time() + + +def is_parallel(model): + return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel) + + +def intersect_dicts(da, db, exclude=()): + # Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values + return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape} + + +def initialize_weights(model): + for m in model.modules(): + t = type(m) + if t is nn.Conv2d: + pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') + elif t is nn.BatchNorm2d: + m.eps = 1e-3 + m.momentum = 0.03 + elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]: + m.inplace = True + + +def find_modules(model, mclass=nn.Conv2d): + # Finds layer indices matching module class 'mclass' + return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)] + + +def sparsity(model): + # Return global model sparsity + a, b = 0., 0. + for p in model.parameters(): + a += p.numel() + b += (p == 0).sum() + return b / a + + +def prune(model, amount=0.3): + # Prune model to requested global sparsity + import torch.nn.utils.prune as prune + print('Pruning model... ', end='') + for name, m in model.named_modules(): + if isinstance(m, nn.Conv2d): + prune.l1_unstructured(m, name='weight', amount=amount) # prune + prune.remove(m, 'weight') # make permanent + print(' %.3g global sparsity' % sparsity(model)) + + +def fuse_conv_and_bn(conv, bn): + # Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/ + fusedconv = nn.Conv2d(conv.in_channels, + conv.out_channels, + kernel_size=conv.kernel_size, + stride=conv.stride, + padding=conv.padding, + groups=conv.groups, + bias=True).requires_grad_(False).to(conv.weight.device) + + # prepare filters + w_conv = conv.weight.clone().view(conv.out_channels, -1) + w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) + fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.size())) + + # prepare spatial bias + b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias + b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps)) + fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn) + + return fusedconv + + +def model_info(model, verbose=False, img_size=640): + # Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320] + n_p = sum(x.numel() for x in model.parameters()) # number parameters + n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients + if verbose: + print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma')) + for i, (name, p) in enumerate(model.named_parameters()): + name = name.replace('module_list.', '') + print('%5g %40s %9s %12g %20s %10.3g %10.3g' % + (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std())) + + try: # FLOPS + from thop import profile + flops = profile(deepcopy(model), inputs=(torch.zeros(1, 3, img_size, img_size),), verbose=False)[0] / 1E9 * 2 + img_size = img_size if isinstance(img_size, list) else [img_size, img_size] # expand if int/float + fs = ', %.9f GFLOPS' % (flops) # 640x640 FLOPS + except (ImportError, Exception): + fs = '' + + logger.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}") + + +def load_classifier(name='resnet101', n=2): + # Loads a pretrained model reshaped to n-class output + model = torchvision.models.__dict__[name](pretrained=True) + + # ResNet model properties + # input_size = [3, 224, 224] + # input_space = 'RGB' + # input_range = [0, 1] + # mean = [0.485, 0.456, 0.406] + # std = [0.229, 0.224, 0.225] + + # Reshape output to n classes + filters = model.fc.weight.shape[1] + model.fc.bias = nn.Parameter(torch.zeros(n), requires_grad=True) + model.fc.weight = nn.Parameter(torch.zeros(n, filters), requires_grad=True) + model.fc.out_features = n + return model + + +def scale_img(img, ratio=1.0, same_shape=False): # img(16,3,256,416), r=ratio + # scales img(bs,3,y,x) by ratio + if ratio == 1.0: + return img + else: + h, w = img.shape[2:] + s = (int(h * ratio), int(w * ratio)) # new size + img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize + if not same_shape: # pad/crop img + gs = 32 # (pixels) grid size + h, w = [math.ceil(x * ratio / gs) * gs for x in (h, w)] + return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean + + +def copy_attr(a, b, include=(), exclude=()): + # Copy attributes from b to a, options to only include [...] and to exclude [...] + for k, v in b.__dict__.items(): + if (len(include) and k not in include) or k.startswith('_') or k in exclude: + continue + else: + setattr(a, k, v) + + +class ModelEMA: + """ Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models + Keep a moving average of everything in the model state_dict (parameters and buffers). + This is intended to allow functionality like + https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage + A smoothed version of the weights is necessary for some training schemes to perform well. + This class is sensitive where it is initialized in the sequence of model init, + GPU assignment and distributed training wrappers. + """ + + def __init__(self, model, decay=0.9999, updates=0): + # Create EMA + self.ema = deepcopy(model.module if is_parallel(model) else model).eval() # FP32 EMA + # if next(model.parameters()).device.type != 'cpu': + # self.ema.half() # FP16 EMA + self.updates = updates # number of EMA updates + self.decay = lambda x: decay * (1 - math.exp(-x / 2000)) # decay exponential ramp (to help early epochs) + for p in self.ema.parameters(): + p.requires_grad_(False) + + def update(self, model): + # Update EMA parameters + with torch.no_grad(): + self.updates += 1 + d = self.decay(self.updates) + + msd = model.module.state_dict() if is_parallel(model) else model.state_dict() # model state_dict + for k, v in self.ema.state_dict().items(): + if v.dtype.is_floating_point: + v *= d + v += (1. - d) * msd[k].detach() + + def update_attr(self, model, include=(), exclude=('process_group', 'reducer')): + # Update EMA attributes + copy_attr(self.ema, model, include, exclude) diff --git a/utils/yolor_streamlit_demo_base.py b/utils/yolor_streamlit_demo_base.py new file mode 100644 index 0000000000000000000000000000000000000000..b502936c888b0e475c84e0cb4d75063507c959f3 --- /dev/null +++ b/utils/yolor_streamlit_demo_base.py @@ -0,0 +1,2 @@ +# To run use +# $ streamlit run yolor_streamlit_demo.py diff --git a/yolo_v7.py b/yolo_v7.py new file mode 100644 index 0000000000000000000000000000000000000000..22b6879c9a281201761b1ab3548b8d65ba86a6f4 --- /dev/null +++ b/yolo_v7.py @@ -0,0 +1,612 @@ +import cv2 +from numpy import random +from collections import deque +import numpy as np +import math +import torch +import torch.backends.cudnn as cudnn + +from utils.google_utils import attempt_load +from utils.datasets import LoadStreams, LoadImages +from utils.general import ( + check_img_size, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, strip_optimizer) +from utils.plots import plot_one_box +from utils.torch_utils import select_device, load_classifier, time_synchronized + +from models.models import * +from utils.datasets import * +from utils.general import * + +from deep_sort_pytorch.utils.parser import get_config +from deep_sort_pytorch.deep_sort import DeepSort + +from byte_track.bytetracker import ByteTrack +from yolov7.yolov7_detector import YOLOv7Detector + +def load_classes(path): + # Loads *.names file at 'path' + with open(path, 'r') as f: + names = f.read().split('\n') + return list(filter(None, names)) # filter removes empty strings (such as last line) + +global names +names = load_classes('data/coco.names') + + +colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))] +palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1) +data_deque = {} +speed_four_line_queue = {} +object_counter = {} + +# line1 = [(250,450), (1000, 450)] + +line2 = [(200,500), (1050, 500)] + + +def xyxy_to_xywh(*xyxy): + """" Calculates the relative bounding box from absolute pixel values. """ + bbox_left = min([xyxy[0].item(), xyxy[2].item()]) + bbox_top = min([xyxy[1].item(), xyxy[3].item()]) + bbox_w = abs(xyxy[0].item() - xyxy[2].item()) + bbox_h = abs(xyxy[1].item() - xyxy[3].item()) + x_c = (bbox_left + bbox_w / 2) + y_c = (bbox_top + bbox_h / 2) + w = bbox_w + h = bbox_h + return x_c, y_c, w, h + +def xyxy_to_tlwh(bbox_xyxy): + tlwh_bboxs = [] + for i, box in enumerate(bbox_xyxy): + x1, y1, x2, y2 = [int(i) for i in box] + top = x1 + left = y1 + w = int(x2 - x1) + h = int(y2 - y1) + tlwh_obj = [top, left, w, h] + tlwh_bboxs.append(tlwh_obj) + return tlwh_bboxs + +def compute_color_for_labels(label): + """ + Simple function that adds fixed color depending on the class + """ + if label == 0: #person #BGR + color = (85,45,255) + elif label == 2: # Car + color = (222,82,175) + elif label == 3: # Motobike + color = (0, 204, 255) + elif label == 5: # Bus + color = (0, 149, 255) + else: + color = [int((p * (label ** 2 - label + 1)) % 255) for p in palette] + return tuple(color) + +def draw_border(img, pt1, pt2, color, thickness, r, d): + x1,y1 = pt1 + x2,y2 = pt2 + # Top left + cv2.line(img, (x1 + r, y1), (x1 + r + d, y1), color, thickness) + cv2.line(img, (x1, y1 + r), (x1, y1 + r + d), color, thickness) + cv2.ellipse(img, (x1 + r, y1 + r), (r, r), 180, 0, 90, color, thickness) + + # Top right + cv2.line(img, (x2 - r, y1), (x2 - r - d, y1), color, thickness) + cv2.line(img, (x2, y1 + r), (x2, y1 + r + d), color, thickness) + cv2.ellipse(img, (x2 - r, y1 + r), (r, r), 270, 0, 90, color, thickness) + # Bottom left + cv2.line(img, (x1 + r, y2), (x1 + r + d, y2), color, thickness) + cv2.line(img, (x1, y2 - r), (x1, y2 - r - d), color, thickness) + cv2.ellipse(img, (x1 + r, y2 - r), (r, r), 90, 0, 90, color, thickness) + # Bottom right + cv2.line(img, (x2 - r, y2), (x2 - r - d, y2), color, thickness) + cv2.line(img, (x2, y2 - r), (x2, y2 - r - d), color, thickness) + cv2.ellipse(img, (x2 - r, y2 - r), (r, r), 0, 0, 90, color, thickness) + + cv2.rectangle(img, (x1 + r, y1), (x2 - r, y2), color, -1, cv2.LINE_AA) + cv2.rectangle(img, (x1, y1 + r), (x2, y2 - r - d), color, -1, cv2.LINE_AA) + + cv2.circle(img, (x1 +r, y1+r), 2, color, 12) + cv2.circle(img, (x2 -r, y1+r), 2, color, 12) + cv2.circle(img, (x1 +r, y2-r), 2, color, 12) + cv2.circle(img, (x2 -r, y2-r), 2, color, 12) + + return img + +def UI_box(x, img, color=None, label=None, line_thickness=None): + # Plots one bounding box on image img + tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness + color = color or [random.randint(0, 255) for _ in range(3)] + c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3])) + # cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA) + if label: + tf = max(tl - 1, 1) # font thickness + t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0] + # c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3 + + img = draw_border(img, (c1[0], c1[1] - t_size[1] -3), (c1[0] + t_size[0], c1[1]+3), color, 1, 8, 2) + + # cv2.line(img, c1, c2, color, 30) + # cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled + cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA) + +def estimateSpeed(location1, location2): + + d_pixels = math.sqrt(math.pow(location2[0] - location1[0], 2) + math.pow(location2[1] - location1[1], 2)) + ppm = 8 #Pixels per Meter + d_meters = d_pixels / ppm + time_constant = 15 * 3.6 + speed = d_meters * time_constant + return speed + +# Return true if line segments AB and CD intersect +def intersect(A,B,C,D): + return ccw(A,C,D) != ccw(B,C,D) and ccw(A,B,C) != ccw(A,B,D) + +def ccw(A,B,C): + return (C[1]-A[1]) * (B[0]-A[0]) > (B[1]-A[1]) * (C[0]-A[0]) + + + + + + +def draw_boxes(img, bbox, object_id, identities=None, offset=(0, 0)): + # cv2.line(img, line2[0], line2[1], (0,200,0), 3) + + height, width, _ = img.shape + # remove tracked point from buffer if object is lost + for key in list(data_deque): + if key not in identities: + data_deque.pop(key) + + for i, box in enumerate(bbox): + x1, y1 = int(box[0]), int(box[1]) + x2, y2 = x1 + int(box[2]), y1 + int(box[3]) + box=[x1, y1, x2, y2] + + # x1, y1, x2, y2 = [int(i) for i in box] + x1 += offset[0] + x2 += offset[0] + y1 += offset[1] + y2 += offset[1] + + + # box_area = (x2-x1) * (y2-y1) + box_height = (y2-y1) + + # code to find center of bottom edge + center = (int((x2+x1)/ 2), int((y2+y2)/2)) + + # get ID of object + id = int(identities[i]) if identities is not None else 0 + + # create new buffer for new object + if id not in data_deque: + data_deque[id] = deque(maxlen= 64) + speed_four_line_queue[id] = [] + + color = compute_color_for_labels(int(object_id[i])) + obj_name = names[int(object_id[i])] + label = '%s' % (obj_name) + + # add center to buffer + data_deque[id].appendleft(center) + + # print("id ", id) + # print("data_deque[id] ", data_deque[id]) + + if len(data_deque[id]) >= 2: + # print("data_deque[id][i-1]", data_deque[id][1], data_deque[id][0]) + + if intersect(data_deque[id][0], data_deque[id][1], line2[0], line2[1]):# or intersect(data_deque[id][0], data_deque[id][1], line1[0], line1[1]) or intersect(data_deque[id][0], data_deque[id][1], line3[0], line3[1]) or intersect(data_deque[id][0], data_deque[id][1], line4[0], line4[1]) : + + # cv2.line(img, line2[0], line2[1], (0,100,0), 3) + + obj_speed = estimateSpeed(data_deque[id][1], data_deque[id][0]) + + speed_four_line_queue[id].append(obj_speed) + + if obj_name not in object_counter: + object_counter[obj_name] = 1 + else: + object_counter[obj_name] += 1 + + try: + label = label + " " + str(sum(speed_four_line_queue[id])//len(speed_four_line_queue[id])) + except : + pass + + UI_box(box, img, label=label, color=color, line_thickness=2) + + # draw trail + for i in range(1, len(data_deque[id])): + # check if on buffer value is none + if data_deque[id][i - 1] is None or data_deque[id][i] is None: + continue + + # generate dynamic thickness of trails + thickness = int(np.sqrt(64 / float(i + i)) * 1.5) + + # draw trails + cv2.line(img, data_deque[id][i - 1], data_deque[id][i], color, thickness) + + + count = 0 + for idx, (key, value) in enumerate(object_counter.items()): + # print(idx, key, value) + cnt_str = str(key) + ": " + str(value) + + cv2.line(img, (width - 150 ,25+ (idx*40)), (width,25 + (idx*40)), [85,45,255], 30) + cv2.putText(img, cnt_str, (width - 150, 35 + (idx*40)), 0, 1, [225, 255, 255], thickness=2, lineType=cv2.LINE_AA) + + count += value + + return img, count + +def load_yolov7_and_process_each_frame(model, vid_name, enable_GPU, save_video, confidence, assigned_class_id, kpi1_text, kpi2_text, kpi3_text, stframe): + data_deque.clear() + speed_four_line_queue.clear() + object_counter.clear() + + if model == 'yolov7': + weights = 'yolov7/weights/yolov7.onnx' + elif model == 'yolov7-tiny': + weights = 'yolov7/weights/yolov7-tiny.onnx' + else: + print('Model Not Found!') + exit() + + detector = YOLOv7Detector(weights=weights, use_cuda=enable_GPU, use_onnx=True) + tracker = ByteTrack(detector) + # dataset = LoadImages(vid_name, img_size=1280, auto_size=64) + + vdo = cv2.VideoCapture(vid_name) + results = [] + start = time.time() + count = 0 + frame_id = 0 + prevTime = 0 + + fourcc = 'mp4v' # output video codec + fps = vdo.get(cv2.CAP_PROP_FPS) + w = int(vdo.get(cv2.CAP_PROP_FRAME_WIDTH)) + h = int(vdo.get(cv2.CAP_PROP_FRAME_HEIGHT)) + vid_writer = cv2.VideoWriter('inference/output/results.mp4', cv2.VideoWriter_fourcc(*fourcc), fps, (w, h)) + + while vdo.isOpened(): + # for path, img, im0s, vid_cap in dataset: + curr_time = time.time() + frame_id +=1 + _, img = vdo.read() + + if _ == False: + break + + # img = cv2.cvtColor(ori_im, cv2.COLOR_BGR2RGB) + # img, count, obj_ids = tracker.inference(img, conf_thresh=confidence, classes=assigned_class_id) + bboxes, ids, scores, obj_ids = tracker.inference(img, conf_thresh=confidence, classes=assigned_class_id) + # print(bboxes[0].shape if len(bboxes)>0 else None) + img, count = draw_boxes(img, bboxes, obj_ids, identities=ids) + currTime = time.time() + fps = 1 / (currTime - prevTime) + prevTime = currTime + + # Save results (image with detections) + cv2.line(img, (20,25), (127,25), [85,45,255], 30) + cv2.putText(img, f'FPS: {int(fps)}', (11, 35), 0, 1, [225, 255, 255], thickness=2, lineType=cv2.LINE_AA) + + if save_video: + vid_writer.write(img) + + kpi1_text.write(f"

{fps:.1f}

", unsafe_allow_html=True) + kpi2_text.write(f"

{len(data_deque)}

", unsafe_allow_html=True) + kpi3_text.write(f"

{count}

", unsafe_allow_html=True) + # if frame_id%3==0: + # stframe.image(img, channels = 'BGR',use_column_width=True) + stframe.image(img, channels = 'BGR',use_column_width=True) + + + end = time.time() + print('Done. (%.3fs)' % (end - start)) + cv2.destroyAllWindows() + vdo.release() + vid_writer.release() + + +def load_yolor_and_process_each_frame(vid_name, enable_GPU, confidence, assigned_class_id, kpi1_text, kpi2_text, kpi3_text, stframe): + data_deque.clear() + speed_four_line_queue.clear() + object_counter.clear() + + out, source, weights, save_txt, imgsz, cfg = \ + 'inference/output', vid_name, 'yolor_p6.pt', False, 1280, 'cfg/yolor_p6.cfg' + + #webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt') + webcam = source == 0 or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt') + + # initialize deepsort + cfg_deep = get_config() + cfg_deep.merge_from_file("deep_sort_pytorch/configs/deep_sort.yaml") + # attempt_download("deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7", repo='mikel-brostrom/Yolov5_DeepSort_Pytorch') + deepsort = DeepSort(cfg_deep.DEEPSORT.REID_CKPT, + max_dist=cfg_deep.DEEPSORT.MAX_DIST, min_confidence=cfg_deep.DEEPSORT.MIN_CONFIDENCE, + nms_max_overlap=cfg_deep.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg_deep.DEEPSORT.MAX_IOU_DISTANCE, + max_age=cfg_deep.DEEPSORT.MAX_AGE, n_init=cfg_deep.DEEPSORT.N_INIT, nn_budget=cfg_deep.DEEPSORT.NN_BUDGET, + use_cuda=True) + + # Initialize GPU + if enable_GPU: + device = select_device('gpu') + else: + device = select_device('cpu') + + if os.path.exists(out): + shutil.rmtree(out) # delete output folder + os.makedirs(out) # make new output folder + half = device.type != 'cpu' # half precision only supported on CUDA + + # Load model + model = Darknet(cfg, imgsz)#.cuda() + model.load_state_dict(torch.load(weights, map_location=device)['model']) + model.to(device).eval() + if half: + model.half() # to FP16 + + # Second-stage classifier + classify = False + if classify: + modelc = load_classifier(name='resnet101', n=2) # initialize + modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']) # load weights + modelc.to(device).eval() + + # Set Dataloader + vid_path, vid_writer = None, None + if webcam: + save_img = True + print("HEREHERER") + # cudnn.benchmark = True # set True to speed up constant image size inference + # dataset = LoadStreams(source, img_size=imgsz) + else: + save_img = True + dataset = LoadImages(source, img_size=imgsz, auto_size=64) + + + # Run inference + t0 = time.time() + img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img + _ = model(img.half() if half else img) if device.type != 'cpu' else None # run once + prevTime = 0 + count = 0 + + if webcam: # code for only webcam + + vid = cv2.VideoCapture(0) + + while vid.isOpened(): + ret, img = vid.read() + if not ret: + continue + + im0s = img.copy() + print(im0s.shape) + img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to bsx3x416x416 + print(img.shape) + + img = torch.from_numpy(img.copy()).to(device) + img = img.half() if half else img.float() # uint8 to fp16/32 + img /= 255.0 # 0 - 255 to 0.0 - 1.0 + if img.ndimension() == 3: + img = img.unsqueeze(0) + + print(img.shape) + + # Inference + t1 = time_synchronized() + pred = model(img)[0] + + # Apply NMS + pred = non_max_suppression(pred, confidence, 0.5, classes=assigned_class_id, agnostic=False) + t2 = time_synchronized() + + # Apply Classifier + if classify: + pred = apply_classifier(pred, modelc, img, im0s) + + print("HERE") + # Process detections + for i, det in enumerate(pred): # detections per image + p, s, im0 = "webcam_out.mp4", '', im0s + + # save_path = str(Path(out) / Path(p).name) + # txt_path = str(Path(out) / Path(p).stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '') + s += '%gx%g ' % img.shape[2:] # print string + gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh + if det is not None and len(det): + # Rescale boxes from img_size to im0 size + det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() + + # Print results + for c in det[:, -1].unique(): + n = (det[:, -1] == c).sum() # detections per class + s += '%g %ss, ' % (n, names[int(c)]) # add to string + + xywh_bboxs = [] + confs = [] + oids = [] + # Write results + for *xyxy, conf, cls in det: + # to deep sort format + x_c, y_c, bbox_w, bbox_h = xyxy_to_xywh(*xyxy) + xywh_obj = [x_c, y_c, bbox_w, bbox_h] + xywh_bboxs.append(xywh_obj) + confs.append([conf.item()]) + oids.append(int(cls)) + + # if save_txt: # Write to file + # xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh + # with open(txt_path + '.txt', 'a') as f: + # f.write(('%g ' * 5 + '\n') % (cls, *xywh)) # label format + + xywhs = torch.Tensor(xywh_bboxs) + confss = torch.Tensor(confs) + + outputs = deepsort.update(xywhs, confss, oids, im0) + if len(outputs) > 0: + bbox_xyxy = outputs[:, :4] + identities = outputs[:, -2] + object_id = outputs[:, -1] + im0, count = draw_boxes(im0, bbox_xyxy, object_id,identities) + + # Print time (inference + NMS) + print('%sDone. (%.3fs)' % (s, t2 - t1)) + + currTime = time.time() + fps = 1 / (currTime - prevTime) + prevTime = currTime + cv2.line(im0, (20,25), (127,25), [85,45,255], 30) + cv2.putText(im0, f'FPS: {int(fps)}', (11, 35), 0, 1, [225, 255, 255], thickness=2, lineType=cv2.LINE_AA) + kpi1_text.write(f"

{'{:.1f}'.format(fps)}

", unsafe_allow_html=True) + + # # Save results (image with detections) + # if save_img: + # if dataset.mode == 'images': + # cv2.imwrite(save_path, im0) + # else: + # if vid_path != save_path: # new video + # vid_path = save_path + # if isinstance(vid_writer, cv2.VideoWriter): + # vid_writer.release() # release previous video writer + + # fourcc = 'mp4v' # output video codec + # fps = vid_cap.get(cv2.CAP_PROP_FPS) + # w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) + # h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) + # vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h)) + # vid_writer.write(im0) + + # data_deque assign inside yolor.py + + kpi2_text.write(f"

{len(data_deque)}

", unsafe_allow_html=True) + kpi3_text.write(f"

{count}

", unsafe_allow_html=True) + stframe.image(im0,channels = 'BGR',use_column_width=True) + + else: # without webcam + for path, img, im0s, vid_cap in dataset: + # print(path) + # print(img.shape) + # print(im0s.shape) + # print(vid_cap) + + + img = torch.from_numpy(img).to(device) + img = img.half() if half else img.float() # uint8 to fp16/32 + img /= 255.0 # 0 - 255 to 0.0 - 1.0 + if img.ndimension() == 3: + img = img.unsqueeze(0) + + # Inference + t1 = time_synchronized() + print(img.shape) + + pred = model(img)[0] + + # Apply NMS + pred = non_max_suppression(pred, confidence, 0.5, classes=assigned_class_id, agnostic=False) + t2 = time_synchronized() + + # Apply Classifier + if classify: + pred = apply_classifier(pred, modelc, img, im0s) + + # Process detections + for i, det in enumerate(pred): # detections per image + if webcam: # batch_size >= 1 + p, s, im0 = path[i], '%g: ' % i, im0s[i].copy() + else: + p, s, im0 = path, '', im0s + + save_path = str(Path(out) / Path(p).name) + txt_path = str(Path(out) / Path(p).stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '') + s += '%gx%g ' % img.shape[2:] # print string + gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh + if det is not None and len(det): + # Rescale boxes from img_size to im0 size + det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() + + # Print results + for c in det[:, -1].unique(): + n = (det[:, -1] == c).sum() # detections per class + s += '%g %ss, ' % (n, names[int(c)]) # add to string + + xywh_bboxs = [] + confs = [] + oids = [] + # Write results + for *xyxy, conf, cls in det: + # to deep sort format + x_c, y_c, bbox_w, bbox_h = xyxy_to_xywh(*xyxy) + xywh_obj = [x_c, y_c, bbox_w, bbox_h] + xywh_bboxs.append(xywh_obj) + confs.append([conf.item()]) + oids.append(int(cls)) + + if save_txt: # Write to file + xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh + with open(txt_path + '.txt', 'a') as f: + f.write(('%g ' * 5 + '\n') % (cls, *xywh)) # label format + + xywhs = torch.Tensor(xywh_bboxs) + confss = torch.Tensor(confs) + + outputs = deepsort.update(xywhs, confss, oids, im0) + if len(outputs) > 0: + bbox_xyxy = outputs[:, :4] + identities = outputs[:, -2] + object_id = outputs[:, -1] + im0, count = draw_boxes(im0, bbox_xyxy, object_id,identities) + + # Print time (inference + NMS) + print('%sDone. (%.3fs)' % (s, t2 - t1)) + + currTime = time.time() + fps = 1 / (currTime - prevTime) + prevTime = currTime + cv2.line(im0, (20,25), (127,25), [85,45,255], 30) + cv2.putText(im0, f'FPS: {int(fps)}', (11, 35), 0, 1, [225, 255, 255], thickness=2, lineType=cv2.LINE_AA) + kpi1_text.write(f"

{'{:.1f}'.format(fps)}

", unsafe_allow_html=True) + + # Save results (image with detections) + if save_img: + if dataset.mode == 'images': + cv2.imwrite(save_path, im0) + else: + if vid_path != save_path: # new video + vid_path = save_path + if isinstance(vid_writer, cv2.VideoWriter): + vid_writer.release() # release previous video writer + + fourcc = 'mp4v' # output video codec + fps = vid_cap.get(cv2.CAP_PROP_FPS) + w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) + h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) + vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h)) + vid_writer.write(im0) + + # data_deque assign inside yolor.py + + kpi2_text.write(f"

{len(data_deque)}

", unsafe_allow_html=True) + kpi3_text.write(f"

{count}

", unsafe_allow_html=True) + stframe.image(im0,channels = 'BGR',use_column_width=True) + + + if save_txt or save_img: + print('Results saved to %s' % Path(out)) + if platform == 'darwin': # MacOS + os.system('open ' + save_path) + + print('Done. (%.3fs)' % (time.time() - t0)) + cv2.destroyAllWindows() + vid.release() diff --git a/yolor-demo.py b/yolor-demo.py new file mode 100644 index 0000000000000000000000000000000000000000..3356ea0df51bd1c6c610be1c420b1054bbac694b --- /dev/null +++ b/yolor-demo.py @@ -0,0 +1,138 @@ +# To run use +# $ streamlit run yolor_streamlit_demo.py + +from yolor import * + +import tempfile +import os +import platform +import shutil +import time +from pathlib import Path +import cv2 +import torch +import torch.backends.cudnn as cudnn + +from utils.google_utils import attempt_load +from utils.datasets import LoadStreams, LoadImages +from utils.general import ( + check_img_size, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, strip_optimizer) +from utils.plots import plot_one_box +from utils.torch_utils import select_device, load_classifier, time_synchronized + +from models.models import * +from utils.datasets import * +from utils.general import * + +from deep_sort_pytorch.utils.parser import get_config +from deep_sort_pytorch.deep_sort import DeepSort + +import streamlit as st + + +def main(): + + #title + st.title('Object Tracking Dashboard YOLOR') + + #side bar title + st.sidebar.title('Settings') + + st.markdown( + """ + + """, + unsafe_allow_html=True, + ) + + use_webcam = st.sidebar.checkbox('Use Webcam') + + st.sidebar.markdown('---') + confidence = st.sidebar.slider('Confidence',min_value=0.0, max_value=1.0, value = 0.25) + st.sidebar.markdown('---') + + save_img = st.sidebar.checkbox('Save Video') + enable_GPU = st.sidebar.checkbox('enable GPU') + + custom_classes = st.sidebar.checkbox('Use Custom Classes') + assigned_class_id = [] + if custom_classes: + assigned_class = st.sidebar.multiselect('Select The Custom Classes',list(names),default='person') + for each in assigned_class: + assigned_class_id.append(names.index(each)) + + video_file_buffer = st.sidebar.file_uploader("Upload a video", type=[ "mp4", "mov",'avi','asf', 'm4v' ]) + + DEMO_VIDEO = 'test.mp4' + + tfflie = tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) + + + ##We get our input video here + + if not video_file_buffer: + if use_webcam: + vid = cv2.VideoCapture(0, cv2.CAP_ARAVIS) + tfflie.name = 0 + else: + vid = cv2.VideoCapture(DEMO_VIDEO) + tfflie.name = DEMO_VIDEO + dem_vid = open(tfflie.name,'rb') + demo_bytes = dem_vid.read() + + st.sidebar.text('Input Video') + st.sidebar.video(demo_bytes) + + else: + tfflie.write(video_file_buffer.read()) + # print("No Buffer") + dem_vid = open(tfflie.name,'rb') + demo_bytes = dem_vid.read() + + st.sidebar.text('Input Video') + st.sidebar.video(demo_bytes) + + + print(tfflie.name) + # vid = cv2.VideoCapture(tfflie.name) + + stframe = st.empty() + + st.markdown("
", unsafe_allow_html=True) + kpi1, kpi2, kpi3 = st.beta_columns(3) #st.columns(3) + + # stframe.image(im0,channels = 'BGR',use_column_width=True) + + with kpi1: + st.markdown("**Frame Rate**") + kpi1_text = st.markdown("0") + + with kpi2: + st.markdown("**Tracked Objects**") + kpi2_text = st.markdown("0") + + with kpi3: + st.markdown("**Total Count**") + kpi3_text = st.markdown("0") + + st.markdown("
", unsafe_allow_html=True) + + # call yolor + load_yolor_and_process_each_frame(tfflie.name, enable_GPU, confidence, assigned_class_id, kpi1_text, kpi2_text, kpi3_text, stframe) + + st.text('Video is Processed') + +if __name__ == '__main__': + try: + main() + except SystemExit: + pass + diff --git a/yolor.py b/yolor.py new file mode 100644 index 0000000000000000000000000000000000000000..ddc815d81b11dfb26efd1c45bb23ad78ce82ec19 --- /dev/null +++ b/yolor.py @@ -0,0 +1,537 @@ +import cv2 +from numpy import random +from collections import deque +import numpy as np +import math +import torch +import torch.backends.cudnn as cudnn + +from utils.google_utils import attempt_load +from utils.datasets import LoadStreams, LoadImages +from utils.general import ( + check_img_size, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, strip_optimizer) +from utils.plots import plot_one_box +from utils.torch_utils import select_device, load_classifier, time_synchronized + +from models.models import * +from utils.datasets import * +from utils.general import * + +from deep_sort_pytorch.utils.parser import get_config +from deep_sort_pytorch.deep_sort import DeepSort + + + +def load_classes(path): + # Loads *.names file at 'path' + with open(path, 'r') as f: + names = f.read().split('\n') + return list(filter(None, names)) # filter removes empty strings (such as last line) + +global names +names = load_classes('data/coco.names') + + +colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))] +palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1) +data_deque = {} +speed_four_line_queue = {} +object_counter = {} + +# line1 = [(250,450), (1000, 450)] + +line2 = [(200,500), (1050, 500)] + + +def xyxy_to_xywh(*xyxy): + """" Calculates the relative bounding box from absolute pixel values. """ + bbox_left = min([xyxy[0].item(), xyxy[2].item()]) + bbox_top = min([xyxy[1].item(), xyxy[3].item()]) + bbox_w = abs(xyxy[0].item() - xyxy[2].item()) + bbox_h = abs(xyxy[1].item() - xyxy[3].item()) + x_c = (bbox_left + bbox_w / 2) + y_c = (bbox_top + bbox_h / 2) + w = bbox_w + h = bbox_h + return x_c, y_c, w, h + +def xyxy_to_tlwh(bbox_xyxy): + tlwh_bboxs = [] + for i, box in enumerate(bbox_xyxy): + x1, y1, x2, y2 = [int(i) for i in box] + top = x1 + left = y1 + w = int(x2 - x1) + h = int(y2 - y1) + tlwh_obj = [top, left, w, h] + tlwh_bboxs.append(tlwh_obj) + return tlwh_bboxs + +def compute_color_for_labels(label): + """ + Simple function that adds fixed color depending on the class + """ + if label == 0: #person #BGR + color = (85,45,255) + elif label == 2: # Car + color = (222,82,175) + elif label == 3: # Motobike + color = (0, 204, 255) + elif label == 5: # Bus + color = (0, 149, 255) + else: + color = [int((p * (label ** 2 - label + 1)) % 255) for p in palette] + return tuple(color) + +def draw_border(img, pt1, pt2, color, thickness, r, d): + x1,y1 = pt1 + x2,y2 = pt2 + # Top left + cv2.line(img, (x1 + r, y1), (x1 + r + d, y1), color, thickness) + cv2.line(img, (x1, y1 + r), (x1, y1 + r + d), color, thickness) + cv2.ellipse(img, (x1 + r, y1 + r), (r, r), 180, 0, 90, color, thickness) + + # Top right + cv2.line(img, (x2 - r, y1), (x2 - r - d, y1), color, thickness) + cv2.line(img, (x2, y1 + r), (x2, y1 + r + d), color, thickness) + cv2.ellipse(img, (x2 - r, y1 + r), (r, r), 270, 0, 90, color, thickness) + # Bottom left + cv2.line(img, (x1 + r, y2), (x1 + r + d, y2), color, thickness) + cv2.line(img, (x1, y2 - r), (x1, y2 - r - d), color, thickness) + cv2.ellipse(img, (x1 + r, y2 - r), (r, r), 90, 0, 90, color, thickness) + # Bottom right + cv2.line(img, (x2 - r, y2), (x2 - r - d, y2), color, thickness) + cv2.line(img, (x2, y2 - r), (x2, y2 - r - d), color, thickness) + cv2.ellipse(img, (x2 - r, y2 - r), (r, r), 0, 0, 90, color, thickness) + + cv2.rectangle(img, (x1 + r, y1), (x2 - r, y2), color, -1, cv2.LINE_AA) + cv2.rectangle(img, (x1, y1 + r), (x2, y2 - r - d), color, -1, cv2.LINE_AA) + + cv2.circle(img, (x1 +r, y1+r), 2, color, 12) + cv2.circle(img, (x2 -r, y1+r), 2, color, 12) + cv2.circle(img, (x1 +r, y2-r), 2, color, 12) + cv2.circle(img, (x2 -r, y2-r), 2, color, 12) + + return img + +def UI_box(x, img, color=None, label=None, line_thickness=None): + # Plots one bounding box on image img + tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness + color = color or [random.randint(0, 255) for _ in range(3)] + c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3])) + # cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA) + if label: + tf = max(tl - 1, 1) # font thickness + t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0] + # c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3 + + img = draw_border(img, (c1[0], c1[1] - t_size[1] -3), (c1[0] + t_size[0], c1[1]+3), color, 1, 8, 2) + + # cv2.line(img, c1, c2, color, 30) + # cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled + cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA) + +def estimateSpeed(location1, location2): + + d_pixels = math.sqrt(math.pow(location2[0] - location1[0], 2) + math.pow(location2[1] - location1[1], 2)) + ppm = 8 #Pixels per Meter + d_meters = d_pixels / ppm + time_constant = 15 * 3.6 + speed = d_meters * time_constant + return speed + +# Return true if line segments AB and CD intersect +def intersect(A,B,C,D): + return ccw(A,C,D) != ccw(B,C,D) and ccw(A,B,C) != ccw(A,B,D) + +def ccw(A,B,C): + return (C[1]-A[1]) * (B[0]-A[0]) > (B[1]-A[1]) * (C[0]-A[0]) + + + + + + +def draw_boxes(img, bbox, object_id, identities=None, offset=(0, 0)): + cv2.line(img, line2[0], line2[1], (0,200,0), 3) + + height, width, _ = img.shape + # remove tracked point from buffer if object is lost + for key in list(data_deque): + if key not in identities: + data_deque.pop(key) + + for i, box in enumerate(bbox): + x1, y1, x2, y2 = [int(i) for i in box] + x1 += offset[0] + x2 += offset[0] + y1 += offset[1] + y2 += offset[1] + + # box_area = (x2-x1) * (y2-y1) + box_height = (y2-y1) + + # code to find center of bottom edge + center = (int((x2+x1)/ 2), int((y2+y2)/2)) + + # get ID of object + id = int(identities[i]) if identities is not None else 0 + + # create new buffer for new object + if id not in data_deque: + data_deque[id] = deque(maxlen= 64) + speed_four_line_queue[id] = [] + + color = compute_color_for_labels(object_id[i]) + obj_name = names[object_id[i]] + label = '%s' % (obj_name) + + # add center to buffer + data_deque[id].appendleft(center) + + # print("id ", id) + # print("data_deque[id] ", data_deque[id]) + + if len(data_deque[id]) >= 2: + # print("data_deque[id][i-1]", data_deque[id][1], data_deque[id][0]) + + if intersect(data_deque[id][0], data_deque[id][1], line2[0], line2[1]):# or intersect(data_deque[id][0], data_deque[id][1], line1[0], line1[1]) or intersect(data_deque[id][0], data_deque[id][1], line3[0], line3[1]) or intersect(data_deque[id][0], data_deque[id][1], line4[0], line4[1]) : + + cv2.line(img, line2[0], line2[1], (0,100,0), 3) + + obj_speed = estimateSpeed(data_deque[id][1], data_deque[id][0]) + + speed_four_line_queue[id].append(obj_speed) + + if obj_name not in object_counter: + object_counter[obj_name] = 1 + else: + object_counter[obj_name] += 1 + + try: + label = label + " " + str(sum(speed_four_line_queue[id])//len(speed_four_line_queue[id])) + except : + pass + + UI_box(box, img, label=label, color=color, line_thickness=2) + + # draw trail + for i in range(1, len(data_deque[id])): + # check if on buffer value is none + if data_deque[id][i - 1] is None or data_deque[id][i] is None: + continue + + # generate dynamic thickness of trails + thickness = int(np.sqrt(64 / float(i + i)) * 1.5) + + # draw trails + cv2.line(img, data_deque[id][i - 1], data_deque[id][i], color, thickness) + + + count = 0 + for idx, (key, value) in enumerate(object_counter.items()): + # print(idx, key, value) + cnt_str = str(key) + ": " + str(value) + + cv2.line(img, (width - 150 ,25+ (idx*40)), (width,25 + (idx*40)), [85,45,255], 30) + cv2.putText(img, cnt_str, (width - 150, 35 + (idx*40)), 0, 1, [225, 255, 255], thickness=2, lineType=cv2.LINE_AA) + + count += value + + return img, count + + +def load_yolor_and_process_each_frame(vid_name, enable_GPU, confidence, assigned_class_id, kpi1_text, kpi2_text, kpi3_text, stframe): + data_deque.clear() + speed_four_line_queue.clear() + object_counter.clear() + + out, source, weights, save_txt, imgsz, cfg = \ + 'inference/output', vid_name, 'yolor_p6.pt', False, 1280, 'cfg/yolor_p6.cfg' + + #webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt') + webcam = source == 0 or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt') + + # initialize deepsort + cfg_deep = get_config() + cfg_deep.merge_from_file("deep_sort_pytorch/configs/deep_sort.yaml") + # attempt_download("deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7", repo='mikel-brostrom/Yolov5_DeepSort_Pytorch') + deepsort = DeepSort(cfg_deep.DEEPSORT.REID_CKPT, + max_dist=cfg_deep.DEEPSORT.MAX_DIST, min_confidence=cfg_deep.DEEPSORT.MIN_CONFIDENCE, + nms_max_overlap=cfg_deep.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg_deep.DEEPSORT.MAX_IOU_DISTANCE, + max_age=cfg_deep.DEEPSORT.MAX_AGE, n_init=cfg_deep.DEEPSORT.N_INIT, nn_budget=cfg_deep.DEEPSORT.NN_BUDGET, + use_cuda=True) + + # Initialize GPU + if enable_GPU: + device = select_device('gpu') + else: + device = select_device('cpu') + + if os.path.exists(out): + shutil.rmtree(out) # delete output folder + os.makedirs(out) # make new output folder + half = device.type != 'cpu' # half precision only supported on CUDA + + # Load model + model = Darknet(cfg, imgsz)#.cuda() + model.load_state_dict(torch.load(weights, map_location=device)['model']) + model.to(device).eval() + if half: + model.half() # to FP16 + + # Second-stage classifier + classify = False + if classify: + modelc = load_classifier(name='resnet101', n=2) # initialize + modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']) # load weights + modelc.to(device).eval() + + # Set Dataloader + vid_path, vid_writer = None, None + if webcam: + save_img = True + print("HEREHERER") + # cudnn.benchmark = True # set True to speed up constant image size inference + # dataset = LoadStreams(source, img_size=imgsz) + else: + save_img = True + dataset = LoadImages(source, img_size=imgsz, auto_size=64) + + + # Run inference + t0 = time.time() + img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img + _ = model(img.half() if half else img) if device.type != 'cpu' else None # run once + prevTime = 0 + count = 0 + + if webcam: # code for only webcam + + vid = cv2.VideoCapture(0) + + while vid.isOpened(): + ret, img = vid.read() + if not ret: + continue + + im0s = img.copy() + print(im0s.shape) + img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to bsx3x416x416 + print(img.shape) + + img = torch.from_numpy(img.copy()).to(device) + img = img.half() if half else img.float() # uint8 to fp16/32 + img /= 255.0 # 0 - 255 to 0.0 - 1.0 + if img.ndimension() == 3: + img = img.unsqueeze(0) + + print(img.shape) + + # Inference + t1 = time_synchronized() + pred = model(img)[0] + + # Apply NMS + pred = non_max_suppression(pred, confidence, 0.5, classes=assigned_class_id, agnostic=False) + t2 = time_synchronized() + + # Apply Classifier + if classify: + pred = apply_classifier(pred, modelc, img, im0s) + + print("HERE") + # Process detections + for i, det in enumerate(pred): # detections per image + p, s, im0 = "webcam_out.mp4", '', im0s + + # save_path = str(Path(out) / Path(p).name) + # txt_path = str(Path(out) / Path(p).stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '') + s += '%gx%g ' % img.shape[2:] # print string + gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh + if det is not None and len(det): + # Rescale boxes from img_size to im0 size + det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() + + # Print results + for c in det[:, -1].unique(): + n = (det[:, -1] == c).sum() # detections per class + s += '%g %ss, ' % (n, names[int(c)]) # add to string + + xywh_bboxs = [] + confs = [] + oids = [] + # Write results + for *xyxy, conf, cls in det: + # to deep sort format + x_c, y_c, bbox_w, bbox_h = xyxy_to_xywh(*xyxy) + xywh_obj = [x_c, y_c, bbox_w, bbox_h] + xywh_bboxs.append(xywh_obj) + confs.append([conf.item()]) + oids.append(int(cls)) + + # if save_txt: # Write to file + # xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh + # with open(txt_path + '.txt', 'a') as f: + # f.write(('%g ' * 5 + '\n') % (cls, *xywh)) # label format + + xywhs = torch.Tensor(xywh_bboxs) + confss = torch.Tensor(confs) + + outputs = deepsort.update(xywhs, confss, oids, im0) + if len(outputs) > 0: + bbox_xyxy = outputs[:, :4] + identities = outputs[:, -2] + object_id = outputs[:, -1] + im0, count = draw_boxes(im0, bbox_xyxy, object_id,identities) + + # Print time (inference + NMS) + print('%sDone. (%.3fs)' % (s, t2 - t1)) + + currTime = time.time() + fps = 1 / (currTime - prevTime) + prevTime = currTime + cv2.line(im0, (20,25), (127,25), [85,45,255], 30) + cv2.putText(im0, f'FPS: {int(fps)}', (11, 35), 0, 1, [225, 255, 255], thickness=2, lineType=cv2.LINE_AA) + kpi1_text.write(f"

{'{:.1f}'.format(fps)}

", unsafe_allow_html=True) + + # # Save results (image with detections) + # if save_img: + # if dataset.mode == 'images': + # cv2.imwrite(save_path, im0) + # else: + # if vid_path != save_path: # new video + # vid_path = save_path + # if isinstance(vid_writer, cv2.VideoWriter): + # vid_writer.release() # release previous video writer + + # fourcc = 'mp4v' # output video codec + # fps = vid_cap.get(cv2.CAP_PROP_FPS) + # w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) + # h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) + # vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h)) + # vid_writer.write(im0) + + # data_deque assign inside yolor.py + + kpi2_text.write(f"

{len(data_deque)}

", unsafe_allow_html=True) + kpi3_text.write(f"

{count}

", unsafe_allow_html=True) + stframe.image(im0,channels = 'BGR',use_column_width=True) + + else: # without webcam + for path, img, im0s, vid_cap in dataset: + # print(path) + # print(img.shape) + # print(im0s.shape) + # print(vid_cap) + + + img = torch.from_numpy(img).to(device) + img = img.half() if half else img.float() # uint8 to fp16/32 + img /= 255.0 # 0 - 255 to 0.0 - 1.0 + if img.ndimension() == 3: + img = img.unsqueeze(0) + + # Inference + t1 = time_synchronized() + print(img.shape) + + pred = model(img)[0] + + # Apply NMS + pred = non_max_suppression(pred, confidence, 0.5, classes=assigned_class_id, agnostic=False) + t2 = time_synchronized() + + # Apply Classifier + if classify: + pred = apply_classifier(pred, modelc, img, im0s) + + # Process detections + for i, det in enumerate(pred): # detections per image + if webcam: # batch_size >= 1 + p, s, im0 = path[i], '%g: ' % i, im0s[i].copy() + else: + p, s, im0 = path, '', im0s + + save_path = str(Path(out) / Path(p).name) + txt_path = str(Path(out) / Path(p).stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '') + s += '%gx%g ' % img.shape[2:] # print string + gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh + if det is not None and len(det): + # Rescale boxes from img_size to im0 size + det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() + + # Print results + for c in det[:, -1].unique(): + n = (det[:, -1] == c).sum() # detections per class + s += '%g %ss, ' % (n, names[int(c)]) # add to string + + xywh_bboxs = [] + confs = [] + oids = [] + # Write results + for *xyxy, conf, cls in det: + # to deep sort format + x_c, y_c, bbox_w, bbox_h = xyxy_to_xywh(*xyxy) + xywh_obj = [x_c, y_c, bbox_w, bbox_h] + xywh_bboxs.append(xywh_obj) + confs.append([conf.item()]) + oids.append(int(cls)) + + if save_txt: # Write to file + xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh + with open(txt_path + '.txt', 'a') as f: + f.write(('%g ' * 5 + '\n') % (cls, *xywh)) # label format + + xywhs = torch.Tensor(xywh_bboxs) + confss = torch.Tensor(confs) + + outputs = deepsort.update(xywhs, confss, oids, im0) + if len(outputs) > 0: + bbox_xyxy = outputs[:, :4] + identities = outputs[:, -2] + object_id = outputs[:, -1] + im0, count = draw_boxes(im0, bbox_xyxy, object_id,identities) + + # Print time (inference + NMS) + print('%sDone. (%.3fs)' % (s, t2 - t1)) + + currTime = time.time() + fps = 1 / (currTime - prevTime) + prevTime = currTime + cv2.line(im0, (20,25), (127,25), [85,45,255], 30) + cv2.putText(im0, f'FPS: {int(fps)}', (11, 35), 0, 1, [225, 255, 255], thickness=2, lineType=cv2.LINE_AA) + kpi1_text.write(f"

{'{:.1f}'.format(fps)}

", unsafe_allow_html=True) + + # Save results (image with detections) + if save_img: + if dataset.mode == 'images': + cv2.imwrite(save_path, im0) + else: + if vid_path != save_path: # new video + vid_path = save_path + if isinstance(vid_writer, cv2.VideoWriter): + vid_writer.release() # release previous video writer + + fourcc = 'mp4v' # output video codec + fps = vid_cap.get(cv2.CAP_PROP_FPS) + w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) + h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) + vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h)) + vid_writer.write(im0) + + # data_deque assign inside yolor.py + + kpi2_text.write(f"

{len(data_deque)}

", unsafe_allow_html=True) + kpi3_text.write(f"

{count}

", unsafe_allow_html=True) + stframe.image(im0,channels = 'BGR',use_column_width=True) + + + if save_txt or save_img: + print('Results saved to %s' % Path(out)) + if platform == 'darwin': # MacOS + os.system('open ' + save_path) + + print('Done. (%.3fs)' % (time.time() - t0)) + cv2.destroyAllWindows() + vid.release() \ No newline at end of file diff --git a/yolov7-demo.py b/yolov7-demo.py new file mode 100644 index 0000000000000000000000000000000000000000..a79aca90df243ebaef1c223acd0553992df5531c --- /dev/null +++ b/yolov7-demo.py @@ -0,0 +1,123 @@ +# To run use +# $ streamlit run yolor_streamlit_demo.py + +from yolo_v7 import names, load_yolov7_and_process_each_frame + +import tempfile +import cv2 + + +from models.models import * +from utils.datasets import * +from utils.general import * + +import streamlit as st + + +def main(): + + #title + st.title('Object Tracking Dashboard YOLOv7') + + #side bar title + st.sidebar.title('Settings') + + st.markdown( + """ + + """, + unsafe_allow_html=True, + ) + + use_webcam = st.sidebar.checkbox('Use Webcam') + + st.sidebar.markdown('---') + confidence = st.sidebar.slider('Confidence',min_value=0.0, max_value=1.0, value = 0.25) + st.sidebar.markdown('---') + + save_img = st.sidebar.checkbox('Save Video') + enable_GPU = st.sidebar.checkbox('enable GPU') + + custom_classes = st.sidebar.checkbox('Use Custom Classes') + assigned_class_id = [] + if custom_classes: + assigned_class = st.sidebar.multiselect('Select The Custom Classes',list(names),default='person') + for each in assigned_class: + assigned_class_id.append(names.index(each)) + + video_file_buffer = st.sidebar.file_uploader("Upload a video", type=[ "mp4", "mov",'avi','asf', 'm4v' ]) + + DEMO_VIDEO = 'test.mp4' + + tfflie = tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) + + + ##We get our input video here + + if not video_file_buffer: + if use_webcam: + vid = cv2.VideoCapture(0, cv2.CAP_ARAVIS) + tfflie.name = 0 + else: + vid = cv2.VideoCapture(DEMO_VIDEO) + tfflie.name = DEMO_VIDEO + dem_vid = open(tfflie.name,'rb') + demo_bytes = dem_vid.read() + + st.sidebar.text('Input Video') + st.sidebar.video(demo_bytes) + + else: + tfflie.write(video_file_buffer.read()) + # print("No Buffer") + dem_vid = open(tfflie.name,'rb') + demo_bytes = dem_vid.read() + + st.sidebar.text('Input Video') + st.sidebar.video(demo_bytes) + + + print(tfflie.name) + # vid = cv2.VideoCapture(tfflie.name) + + stframe = st.empty() + + st.markdown("
", unsafe_allow_html=True) + kpi1, kpi2, kpi3 = st.columns(3) #st.beta_columns(3) #st.columns(3) + + # stframe.image(im0,channels = 'BGR',use_column_width=True) + + with kpi1: + st.markdown("**Frame Rate**") + kpi1_text = st.markdown("0") + + with kpi2: + st.markdown("**Tracked Objects**") + kpi2_text = st.markdown("0") + + with kpi3: + st.markdown("**Total Count**") + kpi3_text = st.markdown("0") + + st.markdown("
", unsafe_allow_html=True) + # call yolor + # load_yolor_and_process_each_frame(tfflie.name, enable_GPU, confidence, assigned_class_id, kpi1_text, kpi2_text, kpi3_text, stframe) + load_yolov7_and_process_each_frame('yolov7', tfflie.name, enable_GPU, save_img, confidence, assigned_class_id, kpi1_text, kpi2_text, kpi3_text, stframe) + + st.text('Video is Processed') + +if __name__ == '__main__': + try: + main() + except SystemExit: + pass + + diff --git a/yolov7-tiny-demo.py b/yolov7-tiny-demo.py new file mode 100644 index 0000000000000000000000000000000000000000..e83d0d03fd6bb07e5419670e1f8519ff06e6fd05 --- /dev/null +++ b/yolov7-tiny-demo.py @@ -0,0 +1,121 @@ +# To run use +# $ streamlit run yolor_streamlit_demo.py + +from yolo_v7 import names, load_yolov7_and_process_each_frame + +import tempfile +import cv2 + +from models.models import * +from utils.datasets import * +from utils.general import * +import streamlit as st + + +def main(): + + #title + st.title('Object Tracking Dashboard YOLOv7-tiny') + + #side bar title + st.sidebar.title('Settings') + + st.markdown( + """ + + """, + unsafe_allow_html=True, + ) + + use_webcam = st.sidebar.checkbox('Use Webcam') + + st.sidebar.markdown('---') + confidence = st.sidebar.slider('Confidence',min_value=0.0, max_value=1.0, value = 0.25) + st.sidebar.markdown('---') + + save_img = st.sidebar.checkbox('Save Video') + enable_GPU = st.sidebar.checkbox('enable GPU') + + custom_classes = st.sidebar.checkbox('Use Custom Classes') + assigned_class_id = [] + if custom_classes: + assigned_class = st.sidebar.multiselect('Select The Custom Classes',list(names),default='person') + for each in assigned_class: + assigned_class_id.append(names.index(each)) + + video_file_buffer = st.sidebar.file_uploader("Upload a video", type=[ "mp4", "mov",'avi','asf', 'm4v' ]) + + DEMO_VIDEO = 'test.mp4' + + tfflie = tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) + + + ##We get our input video here + + if not video_file_buffer: + if use_webcam: + vid = cv2.VideoCapture(0, cv2.CAP_ARAVIS) + tfflie.name = 0 + else: + vid = cv2.VideoCapture(DEMO_VIDEO) + tfflie.name = DEMO_VIDEO + dem_vid = open(tfflie.name,'rb') + demo_bytes = dem_vid.read() + + st.sidebar.text('Input Video') + st.sidebar.video(demo_bytes) + + else: + tfflie.write(video_file_buffer.read()) + # print("No Buffer") + dem_vid = open(tfflie.name,'rb') + demo_bytes = dem_vid.read() + + st.sidebar.text('Input Video') + st.sidebar.video(demo_bytes) + + + print(tfflie.name) + # vid = cv2.VideoCapture(tfflie.name) + + stframe = st.empty() + + st.markdown("
", unsafe_allow_html=True) + kpi1, kpi2, kpi3 = st.beta_columns(3) #st.columns(3) + + # stframe.image(im0,channels = 'BGR',use_column_width=True) + + with kpi1: + st.markdown("**Frame Rate**") + kpi1_text = st.markdown("0") + + with kpi2: + st.markdown("**Tracked Objects**") + kpi2_text = st.markdown("0") + + with kpi3: + st.markdown("**Total Count**") + kpi3_text = st.markdown("0") + + st.markdown("
", unsafe_allow_html=True) + # call yolor + # load_yolor_and_process_each_frame(tfflie.name, enable_GPU, confidence, assigned_class_id, kpi1_text, kpi2_text, kpi3_text, stframe) + load_yolov7_and_process_each_frame('yolov7-tiny', tfflie.name, enable_GPU, save_img, confidence, assigned_class_id, kpi1_text, kpi2_text, kpi3_text, stframe) + + st.text('Video is Processed') + +if __name__ == '__main__': + try: + main() + except SystemExit: + pass + + diff --git a/yolov7/__pycache__/yolov7_detector.cpython-310.pyc b/yolov7/__pycache__/yolov7_detector.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fd96bf1a4ea69b24dd1b458283800cf15b92624e Binary files /dev/null and b/yolov7/__pycache__/yolov7_detector.cpython-310.pyc differ diff --git a/yolov7/__pycache__/yolov7_detector.cpython-39.pyc b/yolov7/__pycache__/yolov7_detector.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fd117cd7fc66a6a997761f84424ed1ccab2746f2 Binary files /dev/null and b/yolov7/__pycache__/yolov7_detector.cpython-39.pyc differ diff --git a/yolov7/__pycache__/yolov7_utils.cpython-310.pyc b/yolov7/__pycache__/yolov7_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2f1b09c84b705c41d7a702038516336aa2eb1000 Binary files /dev/null and b/yolov7/__pycache__/yolov7_utils.cpython-310.pyc differ diff --git a/yolov7/__pycache__/yolov7_utils.cpython-39.pyc b/yolov7/__pycache__/yolov7_utils.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6848cc1b0d3899f0128eb0e7c37ab1269b374e65 Binary files /dev/null and b/yolov7/__pycache__/yolov7_utils.cpython-39.pyc differ diff --git a/yolov7/weights/yolov7-tiny.onnx b/yolov7/weights/yolov7-tiny.onnx new file mode 100644 index 0000000000000000000000000000000000000000..905449ffa500f2db89b9906dc3a8bc58ad6e9973 --- /dev/null +++ b/yolov7/weights/yolov7-tiny.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa7a5f728412a4027dde73b6476f511e7b704febdb7b054ce9f88697a67afe2 +size 24983020 diff --git a/yolov7/weights/yolov7.onnx b/yolov7/weights/yolov7.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d8bc498325a3205e453af763e8a1f43e25631659 --- /dev/null +++ b/yolov7/weights/yolov7.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c656e50e3724e02d4385ca6ce58e5827657a0fc730f2d34c2dfff01b737228 +size 147735961 diff --git a/yolov7/yolov7_detector.py b/yolov7/yolov7_detector.py new file mode 100644 index 0000000000000000000000000000000000000000..78ffe71d61e12cb4dde8523ed7b488ce3021f21a --- /dev/null +++ b/yolov7/yolov7_detector.py @@ -0,0 +1,57 @@ +from .yolov7_utils import prepare_input, process_output +import onnxruntime +import os + + +class YOLOv7Detector: + def __init__(self, + weights=os.path.join(os.path.dirname( + os.path.abspath(__file__)), './weights/yolov7.onnx'), + use_cuda=True, use_onnx=True) -> None: + + if use_onnx: + if use_cuda: + providers = [ + 'CUDAExecutionProvider', + 'CPUExecutionProvider' + ] + else: + providers = ['CPUExecutionProvider'] + + self.model = onnxruntime.InferenceSession(weights, providers=providers) + + self.class_names= ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', + 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', + 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', + 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', + 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', + 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', + 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', + 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', + 'hair drier', 'toothbrush'] + + # else: + # self.model = torch + self.device = 'cuda' if use_cuda else 'cpu' + + def detect(self, image: list, + conf_thres: float = 0.25, + iou_thres: float = 0.45, + classes: list = None, + agnostic_nms: bool = False, + input_shape=(640, 640), + max_det: int = 1000) -> list: + + image0 = image.copy() + input_tensor = prepare_input(image, input_shape) + input_name = self.model.get_inputs()[0].name + + outputs = self.model.run([self.model.get_outputs()[0].name], { + input_name: input_tensor}) + dets = process_output( + outputs, image0.shape[:2], input_shape, conf_thres, iou_thres, classes=classes) + image_info = { + 'width': image0.shape[1], + 'height': image0.shape[0], + } + return dets, image_info diff --git a/yolov7/yolov7_utils.py b/yolov7/yolov7_utils.py new file mode 100644 index 0000000000000000000000000000000000000000..20d4eb288b65748caa72f5bdf4f5c575fd859f33 --- /dev/null +++ b/yolov7/yolov7_utils.py @@ -0,0 +1,192 @@ +import cv2 +import numpy as np + + +def prepare_input(image, input_shape): + input_height, input_width = input_shape + input_img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) + + # Resize input image + input_img = cv2.resize(input_img, (input_width, input_height)) + # Scale input pixel values to 0 to 1 + input_img = input_img / 255.0 + input_img = input_img.transpose(2, 0, 1) + input_tensor = input_img[np.newaxis, :, :, :].astype(np.float32) + + return input_tensor + +def process_output(output, ori_shape, input_shape, conf_threshold, iou_threshold, classes=[]): + predictions = output[0] + # predictions = np.squeeze(output[0]) + # print(predictions.shape) + # print([p[5] for p in predictions]) + # exit() + # Filter out object confidence scores below threshold + # obj_conf = predictions[:, 4] + obj_conf = predictions[:, 6] + # predictions = predictions[obj_conf > conf_threshold] + # obj_conf = obj_conf[obj_conf > conf_threshold] + + # print(obj_conf[0]) + + # Multiply class confidence with bounding box confidence + # predictions[:, 5] *= obj_conf[:, np.newaxis] + # predictions[:, 6] *= obj_conf + + # Get the scores + # scores = np.max(predictions[:, 5:], axis=1) + scores = predictions[:, 6] + + # Filter out the objects with a low score + predictions = predictions[obj_conf > conf_threshold] + scores = scores[scores > conf_threshold] + + if len(scores) == 0: + return [], [], [] + + # Get the class with the highest confidence + # class_ids = np.argmax(predictions[:, 5:], axis=1) + class_ids = predictions[:, 5].astype(np.uint16) + # Extract boxes from predictions + boxes = predictions[:, 1:5] + + # Scale boxes to original image dimensions + boxes = rescale_boxes(boxes, ori_shape, input_shape) + + # Convert boxes to xyxy format + # boxes = xywh2xyxy(boxes) + + # Apply non-maxima suppression to suppress weak, overlapping bounding boxes + indices = nms(boxes, scores, iou_threshold) + + dets = [] + for i in indices: + if len(classes) > 0: + if class_ids[i] in classes: + dets.append([*boxes[i], scores[i], class_ids[i]]) + else: + dets.append([*boxes[i], scores[i], class_ids[i]]) + + # return boxes[indices], scores[indices], class_ids[indices] + return np.array(dets) + + +def rescale_boxes(boxes, ori_shape, input_shape): + + input_height, input_width = input_shape + img_height, img_width = ori_shape + # Rescale boxes to original image dimensions + input_shape = np.array([input_width, input_height, input_width, input_height]) + boxes = np.divide(boxes, input_shape, dtype=np.float32) + boxes *= np.array([img_width, img_height, img_width, img_height]) + return boxes + +class_names = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', + 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', + 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', + 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', + 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', + 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', + 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', + 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', + 'scissors', 'teddy bear', 'hair drier', 'toothbrush'] + +# Create a list of colors for each class where each color is a tuple of 3 integer values +rng = np.random.default_rng(3) +colors = rng.uniform(0, 255, size=(len(class_names), 3)) + +def nms(boxes, scores, iou_threshold): + # Sort by score + sorted_indices = np.argsort(scores)[::-1] + + keep_boxes = [] + while sorted_indices.size > 0: + # Pick the last box + box_id = sorted_indices[0] + keep_boxes.append(box_id) + + # Compute IoU of the picked box with the rest + ious = compute_iou(boxes[box_id, :], boxes[sorted_indices[1:], :]) + + # Remove boxes with IoU over the threshold + keep_indices = np.where(ious < iou_threshold)[0] + + # print(keep_indices.shape, sorted_indices.shape) + sorted_indices = sorted_indices[keep_indices + 1] + + return keep_boxes + + +def compute_iou(box, boxes): + # Compute xmin, ymin, xmax, ymax for both boxes + xmin = np.maximum(box[0], boxes[:, 0]) + ymin = np.maximum(box[1], boxes[:, 1]) + xmax = np.minimum(box[2], boxes[:, 2]) + ymax = np.minimum(box[3], boxes[:, 3]) + + # Compute intersection area + intersection_area = np.maximum(0, xmax - xmin) * np.maximum(0, ymax - ymin) + + # Compute union area + box_area = (box[2] - box[0]) * (box[3] - box[1]) + boxes_area = (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1]) + union_area = box_area + boxes_area - intersection_area + + # Compute IoU + iou = intersection_area / union_area + + return iou + + +def xywh2xyxy(x): + # Convert bounding box (x, y, w, h) to bounding box (x1, y1, x2, y2) + y = np.copy(x) + y[..., 0] = x[..., 0] - x[..., 2] / 2 + y[..., 1] = x[..., 1] - x[..., 3] / 2 + y[..., 2] = x[..., 0] + x[..., 2] / 2 + y[..., 3] = x[..., 1] + x[..., 3] / 2 + return y + +def draw_detections(image, boxes, scores, class_ids, mask_alpha=0.3): + mask_img = image.copy() + det_img = image.copy() + + img_height, img_width = image.shape[:2] + size = min([img_height, img_width]) * 0.0006 + text_thickness = int(min([img_height, img_width]) * 0.001) + # Draw bounding boxes and labels of detections + for box, score, class_id in zip(boxes, scores, class_ids): + color = colors[class_id] + + x1, y1, x2, y2 = box.astype(int) + + # Draw rectangle + cv2.rectangle(det_img, (x1, y1), (x2, y2), color, 2) + + # Draw fill rectangle in mask image + cv2.rectangle(mask_img, (x1, y1), (x2, y2), color, -1) + + label = class_names[class_id] + caption = f'{label} {int(score * 100)}%' + (tw, th), _ = cv2.getTextSize(text=caption, fontFace=cv2.FONT_HERSHEY_SIMPLEX, + fontScale=size, thickness=text_thickness) + th = int(th * 1.2) + + cv2.rectangle(det_img, (x1, y1), + (x1 + tw, y1 - th), color, -1) + cv2.rectangle(mask_img, (x1, y1), + (x1 + tw, y1 - th), color, -1) + cv2.putText(det_img, caption, (x1, y1), + cv2.FONT_HERSHEY_SIMPLEX, size, (255, 255, 255), text_thickness, cv2.LINE_AA) + + cv2.putText(mask_img, caption, (x1, y1), + cv2.FONT_HERSHEY_SIMPLEX, size, (255, 255, 255), text_thickness, cv2.LINE_AA) + + cv2.imwrite('reult.png', mask_img) + exit() + + +# def draw_detections(image, boxes, scores, class_ids, draw_scores=True, mask_alpha=0.4): + +# return draw_detections(image, boxes, scores, +# class_ids, mask_alpha) \ No newline at end of file