Upload 24 files

app.py

@@ -0,0 +1,162 @@
+import gradio as gr
+import cv2
+import tempfile
+from ultralytics import YOLOv10
+
+
+def yolov10_inference(image, video, model_id, image_size, conf_threshold):
+    #model = YOLOv10.from_pretrained(f'jameslahm/{model_id}')
+    model = YOLOv10("/ddn/imu_tch1/project/yolov10/yolov10-1.0/runs/detect/train9/weights/best.pt")
+    if image:
+        results = model.predict(source=image, imgsz=image_size, conf=conf_threshold)
+        annotated_image = results[0].plot()
+        return annotated_image[:, :, ::-1], None
+    else:
+        video_path = tempfile.mktemp(suffix=".webm")
+        with open(video_path, "wb") as f:
+            with open(video, "rb") as g:
+                f.write(g.read())
+
+        cap = cv2.VideoCapture(video_path)
+        fps = cap.get(cv2.CAP_PROP_FPS)
+        frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+        output_video_path = tempfile.mktemp(suffix=".webm")
+        out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'vp80'), fps, (frame_width, frame_height))
+
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            results = model.predict(source=frame, imgsz=image_size, conf=conf_threshold)
+            annotated_frame = results[0].plot()
+            out.write(annotated_frame)
+
+        cap.release()
+        out.release()
+
+        return None, output_video_path
+
+
+def yolov10_inference_for_examples(image, model_path, image_size, conf_threshold):
+    annotated_image, _ = yolov10_inference(image, None, model_path, image_size, conf_threshold)
+    return annotated_image
+
+
+def app():
+    with gr.Blocks():
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image(type="pil", label="Image", visible=True)
+                video = gr.Video(label="Video", visible=False)
+                input_type = gr.Radio(
+                    choices=["Image", "Video"],
+                    value="Image",
+                    label="Input Type",
+                )
+                model_id = gr.Dropdown(
+                    label="Model",
+                    choices=[
+                        "yolov10n",
+                        "yolov10s",
+                        "yolov10m",
+                        "yolov10b",
+                        "yolov10l",
+                        "yolov10x",
+                    ],
+                    value="yolov10m",
+                )
+                image_size = gr.Slider(
+                    label="Image Size",
+                    minimum=320,
+                    maximum=1280,
+                    step=32,
+                    value=640,
+                )
+                conf_threshold = gr.Slider(
+                    label="Confidence Threshold",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.05,
+                    value=0.25,
+                )
+                yolov10_infer = gr.Button(value="Detect Objects")
+
+            with gr.Column():
+                output_image = gr.Image(type="numpy", label="Annotated Image", visible=True)
+                output_video = gr.Video(label="Annotated Video", visible=False)
+
+        def update_visibility(input_type):
+            image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
+            video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)
+            output_image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
+            output_video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)
+
+            return image, video, output_image, output_video
+
+        input_type.change(
+            fn=update_visibility,
+            inputs=[input_type],
+            outputs=[image, video, output_image, output_video],
+        )
+
+        def run_inference(image, video, model_id, image_size, conf_threshold, input_type):
+            if input_type == "Image":
+                return yolov10_inference(image, None, model_id, image_size, conf_threshold)
+            else:
+                return yolov10_inference(None, video, model_id, image_size, conf_threshold)
+
+
+        yolov10_infer.click(
+            fn=run_inference,
+            inputs=[image, video, model_id, image_size, conf_threshold, input_type],
+            outputs=[output_image, output_video],
+        )
+
+        gr.Examples(
+            examples=[
+                [
+                    "ultralytics/assets/bus.jpg",
+                    "yolov10s",
+                    640,
+                    0.25,
+                ],
+                [
+                    "ultralytics/assets/zidane.jpg",
+                    "yolov10s",
+                    640,
+                    0.25,
+                ],
+            ],
+            fn=yolov10_inference_for_examples,
+            inputs=[
+                image,
+                model_id,
+                image_size,
+                conf_threshold,
+            ],
+            outputs=[output_image],
+            cache_examples='lazy',
+        )
+
+gradio_app = gr.Blocks()
+with gradio_app:
+    gr.HTML(
+        """
+    <h1 style='text-align: center'>
+    YOLOv10: Real-Time End-to-End Object Detection
+    </h1>
+    """)
+    gr.HTML(
+        """
+        <h3 style='text-align: center'>
+        <a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
+        </h3>
+        """)
+    with gr.Row():
+        with gr.Column():
+            app()
+if __name__ == '__main__':
+    gradio_app.launch()

requirements.txt

@@ -0,0 +1,15 @@
+torch==2.0.1
+torchvision==0.15.2
+onnx==1.14.0
+onnxruntime==1.15.1
+pycocotools==2.0.7
+PyYAML==6.0.1
+scipy==1.13.0
+onnxsim==0.4.36
+onnxruntime-gpu==1.18.0
+gradio==4.31.5
+opencv-python==4.9.0.80
+psutil==5.9.8
+py-cpuinfo==9.0.0
+huggingface-hub==0.23.2
+safetensors==0.4.3

runs/detect/train/args.yaml

@@ -0,0 +1,107 @@
+task: detect
+mode: train
+model: yolov10n.yaml
+data: /ddn/imu_tsxm1/xm/GPT4V/lung/lung.yaml
+epochs: 2
+time: null
+patience: 100
+batch: 64
+imgsz: 640
+save: true
+save_period: -1
+val_period: 1
+cache: false
+device: null
+workers: 8
+project: null
+name: train
+exist_ok: false
+pretrained: true
+optimizer: auto
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+save_hybrid: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: false
+opset: null
+workspace: 4
+nms: false
+lr0: 0.01
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+label_smoothing: 0.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+copy_paste: 0.0
+auto_augment: randaugment
+erasing: 0.4
+crop_fraction: 1.0
+cfg: null
+tracker: botsort.yaml
+save_dir: /ddn/imu_tsxm1/xm/yolov10/runs/detect/train

runs/detect/train/results.csv

@@ -0,0 +1,3 @@
+                  epoch,           train/box_om,           train/cls_om,           train/dfl_om,           train/box_oo,           train/cls_oo,           train/dfl_oo,   metrics/precision(B),      metrics/recall(B),       metrics/mAP50(B),    metrics/mAP50-95(B),             val/box_om,             val/cls_om,             val/dfl_om,             val/box_oo,             val/cls_oo,             val/dfl_oo,                 lr/pg0,                 lr/pg1,                 lr/pg2
+                      1,                 3.8105,                 7.4064,                  3.678,                 3.5618,                 24.024,                 3.7539,                0.59641,                0.00843,                  0.007,                0.00266,                 2.7984,                 6.3662,                 3.1238,                 2.4414,                 15.635,                 3.0117,             0.00041369,             0.00041369,             0.00041369
+                      2,                 2.4872,                 3.9917,                 2.2762,                 2.1875,                 7.8443,                 2.0726,                0.58834,                 0.0806,                0.04886,                 0.0197,                 2.1791,                 3.5221,                 2.1289,                 1.8437,                 6.7368,                 1.8786,             0.00041933,             0.00041933,             0.00041933

runs/detect/train/weights/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3622e5cb1340eee66c1411b4661bbf9ab83cbd8cf1b5847b12f28382238dc6
+size 5748665

runs/detect/train/weights/last.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cc71bb27e03b564382e83179dd00b31a073c3cbc3c6cfcb0cfb652f824019f
+size 5748665