Spaces:
Runtime error
Runtime error
File size: 14,028 Bytes
5b93456 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 |
import torch
import torch.nn as nn
from torchvision.ops import nms
import numpy as np
class DecodeBox():
def __init__(self, anchors, num_classes, input_shape, anchors_mask = [[6,7,8], [3,4,5], [0,1,2]]):
super(DecodeBox, self).__init__()
self.anchors = anchors
self.num_classes = num_classes
self.bbox_attrs = 5 + num_classes
self.input_shape = input_shape
self.anchors_mask = anchors_mask
def decode_box(self, inputs):
outputs = []
for i, input in enumerate(inputs):
batch_size = input.size(0)
input_height = input.size(2)
input_width = input.size(3)
stride_h = self.input_shape[0] / input_height
stride_w = self.input_shape[1] / input_width
scaled_anchors = [(anchor_width / stride_w, anchor_height / stride_h) for anchor_width, anchor_height in self.anchors[self.anchors_mask[i]]]
prediction = input.view(batch_size, len(self.anchors_mask[i]),
self.bbox_attrs, input_height, input_width).permute(0, 1, 3, 4, 2).contiguous()
x = torch.sigmoid(prediction[..., 0])
y = torch.sigmoid(prediction[..., 1])
w = prediction[..., 2]
h = prediction[..., 3]
conf = torch.sigmoid(prediction[..., 4])
pred_cls = torch.sigmoid(prediction[..., 5:])
FloatTensor = torch.cuda.FloatTensor if x.is_cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if x.is_cuda else torch.LongTensor
grid_x = torch.linspace(0, input_width - 1, input_width).repeat(input_height, 1).repeat(
batch_size * len(self.anchors_mask[i]), 1, 1).view(x.shape).type(FloatTensor)
grid_y = torch.linspace(0, input_height - 1, input_height).repeat(input_width, 1).t().repeat(
batch_size * len(self.anchors_mask[i]), 1, 1).view(y.shape).type(FloatTensor)
anchor_w = FloatTensor(scaled_anchors).index_select(1, LongTensor([0]))
anchor_h = FloatTensor(scaled_anchors).index_select(1, LongTensor([1]))
anchor_w = anchor_w.repeat(batch_size, 1).repeat(1, 1, input_height * input_width).view(w.shape)
anchor_h = anchor_h.repeat(batch_size, 1).repeat(1, 1, input_height * input_width).view(h.shape)
pred_boxes = FloatTensor(prediction[..., :4].shape)
pred_boxes[..., 0] = x.data + grid_x
pred_boxes[..., 1] = y.data + grid_y
pred_boxes[..., 2] = torch.exp(w.data) * anchor_w
pred_boxes[..., 3] = torch.exp(h.data) * anchor_h
_scale = torch.Tensor([input_width, input_height, input_width, input_height]).type(FloatTensor)
output = torch.cat((pred_boxes.view(batch_size, -1, 4) / _scale,
conf.view(batch_size, -1, 1), pred_cls.view(batch_size, -1, self.num_classes)), -1)
outputs.append(output.data)
return outputs
def yolo_correct_boxes(self, box_xy, box_wh, input_shape, image_shape, letterbox_image):
box_yx = box_xy[..., ::-1]
box_hw = box_wh[..., ::-1]
input_shape = np.array(input_shape)
image_shape = np.array(image_shape)
if letterbox_image:
new_shape = np.round(image_shape * np.min(input_shape/image_shape))
offset = (input_shape - new_shape)/2./input_shape
scale = input_shape/new_shape
box_yx = (box_yx - offset) * scale
box_hw *= scale
box_mins = box_yx - (box_hw / 2.)
box_maxes = box_yx + (box_hw / 2.)
boxes = np.concatenate([box_mins[..., 0:1], box_mins[..., 1:2], box_maxes[..., 0:1], box_maxes[..., 1:2]], axis=-1)
boxes *= np.concatenate([image_shape, image_shape], axis=-1)
return boxes
def non_max_suppression(self, prediction, num_classes, input_shape, image_shape, letterbox_image, conf_thres=0.5, nms_thres=0.4):
box_corner = prediction.new(prediction.shape)
box_corner[:, :, 0] = prediction[:, :, 0] - prediction[:, :, 2] / 2
box_corner[:, :, 1] = prediction[:, :, 1] - prediction[:, :, 3] / 2
box_corner[:, :, 2] = prediction[:, :, 0] + prediction[:, :, 2] / 2
box_corner[:, :, 3] = prediction[:, :, 1] + prediction[:, :, 3] / 2
prediction[:, :, :4] = box_corner[:, :, :4]
output = [None for _ in range(len(prediction))]
for i, image_pred in enumerate(prediction):
class_conf, class_pred = torch.max(image_pred[:, 5:5 + num_classes], 1, keepdim=True)
conf_mask = (image_pred[:, 4] * class_conf[:, 0] >= conf_thres).squeeze()
image_pred = image_pred[conf_mask]
class_conf = class_conf[conf_mask]
class_pred = class_pred[conf_mask]
if not image_pred.size(0):
continue
detections = torch.cat((image_pred[:, :5], class_conf.float(), class_pred.float()), 1)
unique_labels = detections[:, -1].cpu().unique()
if prediction.is_cuda:
unique_labels = unique_labels.cuda()
detections = detections.cuda()
for c in unique_labels:
detections_class = detections[detections[:, -1] == c]
keep = nms(
detections_class[:, :4],
detections_class[:, 4] * detections_class[:, 5],
nms_thres
)
max_detections = detections_class[keep]
output[i] = max_detections if output[i] is None else torch.cat((output[i], max_detections))
if output[i] is not None:
output[i] = output[i].cpu().numpy()
box_xy, box_wh = (output[i][:, 0:2] + output[i][:, 2:4])/2, output[i][:, 2:4] - output[i][:, 0:2]
output[i][:, :4] = self.yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape, letterbox_image)
return output
class DecodeBoxNP():
def __init__(self, anchors, num_classes, input_shape, anchors_mask = [[6,7,8], [3,4,5], [0,1,2]]):
super(DecodeBoxNP, self).__init__()
self.anchors = anchors
self.num_classes = num_classes
self.bbox_attrs = 5 + num_classes
self.input_shape = input_shape
self.anchors_mask = anchors_mask
def sigmoid(self, x):
return 1 / (1 + np.exp(-x))
def decode_box(self, inputs):
outputs = []
for i, input in enumerate(inputs):
batch_size = np.shape(input)[0]
input_height = np.shape(input)[2]
input_width = np.shape(input)[3]
stride_h = self.input_shape[0] / input_height
stride_w = self.input_shape[1] / input_width
scaled_anchors = [(anchor_width / stride_w, anchor_height / stride_h) for anchor_width, anchor_height in self.anchors[self.anchors_mask[i]]]
prediction = np.transpose(np.reshape(input, (batch_size, len(self.anchors_mask[i]), self.bbox_attrs, input_height, input_width)), (0, 1, 3, 4, 2))
x = self.sigmoid(prediction[..., 0])
y = self.sigmoid(prediction[..., 1])
w = prediction[..., 2]
h = prediction[..., 3]
conf = self.sigmoid(prediction[..., 4])
pred_cls = self.sigmoid(prediction[..., 5:])
grid_x = np.repeat(np.expand_dims(np.repeat(np.expand_dims(np.linspace(0, input_width - 1, input_width), 0), input_height, axis=0), 0), batch_size * len(self.anchors_mask[i]), axis=0)
grid_x = np.reshape(grid_x, np.shape(x))
grid_y = np.repeat(np.expand_dims(np.repeat(np.expand_dims(np.linspace(0, input_height - 1, input_height), 0), input_width, axis=0).T, 0), batch_size * len(self.anchors_mask[i]), axis=0)
grid_y = np.reshape(grid_y, np.shape(y))
anchor_w = np.repeat(np.expand_dims(np.repeat(np.expand_dims(np.array(scaled_anchors)[:, 0], 0), batch_size, axis=0), -1), input_height * input_width, axis=-1)
anchor_h = np.repeat(np.expand_dims(np.repeat(np.expand_dims(np.array(scaled_anchors)[:, 1], 0), batch_size, axis=0), -1), input_height * input_width, axis=-1)
anchor_w = np.reshape(anchor_w, np.shape(w))
anchor_h = np.reshape(anchor_h, np.shape(h))
pred_boxes = np.zeros(np.shape(prediction[..., :4]))
pred_boxes[..., 0] = x + grid_x
pred_boxes[..., 1] = y + grid_y
pred_boxes[..., 2] = np.exp(w) * anchor_w
pred_boxes[..., 3] = np.exp(h) * anchor_h
_scale = np.array([input_width, input_height, input_width, input_height])
output = np.concatenate([np.reshape(pred_boxes, (batch_size, -1, 4)) / _scale,
np.reshape(conf, (batch_size, -1, 1)), np.reshape(pred_cls, (batch_size, -1, self.num_classes))], -1)
outputs.append(output)
return outputs
def bbox_iou(self, box1, box2, x1y1x2y2=True):
"""
计算IOU
"""
if not x1y1x2y2:
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
else:
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]
inter_rect_x1 = np.maximum(b1_x1, b2_x1)
inter_rect_y1 = np.maximum(b1_y1, b2_y1)
inter_rect_x2 = np.minimum(b1_x2, b2_x2)
inter_rect_y2 = np.minimum(b1_y2, b2_y2)
inter_area = np.maximum(inter_rect_x2 - inter_rect_x1, 0) * \
np.maximum(inter_rect_y2 - inter_rect_y1, 0)
b1_area = (b1_x2 - b1_x1) * (b1_y2 - b1_y1)
b2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1)
iou = inter_area / np.maximum(b1_area + b2_area - inter_area, 1e-6)
return iou
def yolo_correct_boxes(self, box_xy, box_wh, input_shape, image_shape, letterbox_image):
box_yx = box_xy[..., ::-1]
box_hw = box_wh[..., ::-1]
input_shape = np.array(input_shape)
image_shape = np.array(image_shape)
if letterbox_image:
new_shape = np.round(image_shape * np.min(input_shape/image_shape))
offset = (input_shape - new_shape)/2./input_shape
scale = input_shape/new_shape
box_yx = (box_yx - offset) * scale
box_hw *= scale
box_mins = box_yx - (box_hw / 2.)
box_maxes = box_yx + (box_hw / 2.)
boxes = np.concatenate([box_mins[..., 0:1], box_mins[..., 1:2], box_maxes[..., 0:1], box_maxes[..., 1:2]], axis=-1)
boxes *= np.concatenate([image_shape, image_shape], axis=-1)
return boxes
def non_max_suppression(self, prediction, num_classes, input_shape, image_shape, letterbox_image, conf_thres=0.5, nms_thres=0.4):
box_corner = np.zeros_like(prediction)
box_corner[:, :, 0] = prediction[:, :, 0] - prediction[:, :, 2] / 2
box_corner[:, :, 1] = prediction[:, :, 1] - prediction[:, :, 3] / 2
box_corner[:, :, 2] = prediction[:, :, 0] + prediction[:, :, 2] / 2
box_corner[:, :, 3] = prediction[:, :, 1] + prediction[:, :, 3] / 2
prediction[:, :, :4] = box_corner[:, :, :4]
output = [None for _ in range(len(prediction))]
for i, image_pred in enumerate(prediction):
class_conf = np.max(image_pred[:, 5:5 + num_classes], 1, keepdims=True)
class_pred = np.expand_dims(np.argmax(image_pred[:, 5:5 + num_classes], 1), -1)
conf_mask = np.squeeze((image_pred[:, 4] * class_conf[:, 0] >= conf_thres))
image_pred = image_pred[conf_mask]
class_conf = class_conf[conf_mask]
class_pred = class_pred[conf_mask]
if not np.shape(image_pred)[0]:
continue
detections = np.concatenate((image_pred[:, :5], class_conf, class_pred), 1)
unique_labels = np.unique(detections[:, -1])
for c in unique_labels:
detections_class = detections[detections[:, -1] == c]
conf_sort_index = np.argsort(detections_class[:, 4] * detections_class[:, 5])[::-1]
detections_class = detections_class[conf_sort_index]
max_detections = []
while np.shape(detections_class)[0]:
max_detections.append(detections_class[0:1])
if len(detections_class) == 1:
break
ious = self.bbox_iou(max_detections[-1], detections_class[1:])
detections_class = detections_class[1:][ious < nms_thres]
max_detections = np.concatenate(max_detections, 0)
output[i] = max_detections if output[i] is None else np.concatenate((output[i], max_detections))
if output[i] is not None:
output[i] = output[i]
box_xy, box_wh = (output[i][:, 0:2] + output[i][:, 2:4])/2, output[i][:, 2:4] - output[i][:, 0:2]
output[i][:, :4] = self.yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape, letterbox_image)
return output
|