first commit

app.py

@@ -0,0 +1,168 @@
+import gradio as gr
+import cv2
+import tempfile
+from ultralytics import YOLOv10
+import pandas as pd
+
+df = pd.read_csv('image_class.csv')
+df = df[['name', 'class']]
+df.drop_duplicates(inplace=True)
+# print(df)
+
+def yolov10_inference(image, video, image_size, conf_threshold, iou_threshold):
+    model = YOLOv10('./drug_yolov10.pt')
+    # model = YOLOv10('./pills_yolov10.pt')
+    if image:
+        results = model.predict(source=image, imgsz=image_size, conf=conf_threshold, iou=iou_threshold)
+        annotated_image = results[0].plot()
+        # Print the detected objects' information (class, coordinates, and probability)
+        box = results[0].boxes
+        cls = [int(c) for c in box.cls.tolist()]
+        cnf = [round(f,2) for f in box.conf.tolist()]
+        name = [df[df['class']==n]['name'].item() for n in cls]
+        # print(cls)
+        # print(name)
+        # print(list(zip(cls, cnf)))
+        # print("Object type:", box.cls)
+        # print("Coordinates:", box.xyxy)
+        # print("Probability:", box.conf)
+        # print('box.class data tyupe', type(box.cls.tolist()))
+        return annotated_image[:, :, ::-1], None, list(zip(cls,cnf)), name
+    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, iou=iou_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, image_size, conf_threshold, iou_threshold):
+    annotated_image, _, output_class, output_name = yolov10_inference(image, None, image_size, conf_threshold, iou_threshold)
+    return annotated_image, None, output_class, output_name
+
+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",
+                )
+                image_size = gr.Slider(
+                    label="Image Size",
+                    minimum=0,
+                    maximum=1280,
+                    step=10,
+                    value=640,
+                )
+                conf_threshold = gr.Slider(
+                    label="Confidence Threshold",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.05,
+                    value=0.25,
+                )
+                iou_threshold = gr.Slider(
+                    label="IOU Threshold",
+                    minimum=0,
+                    maximum=1,
+                    step=0.1,
+                    value=0.6,
+                )
+                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)
+                output_name = gr.Textbox(label='Predicted Drug Name')
+                output_name.change(outputs=output_name)
+                output_class = gr.Textbox(label='Predicted Class')
+                output_class.change(outputs=output_class)
+
+        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, image_size, conf_threshold, iou_threshold, input_type):
+            if input_type == "Image":
+                return yolov10_inference(image, None, image_size, conf_threshold, iou_threshold)
+            else:
+                return yolov10_inference(None, video, image_size, conf_threshold, iou_threshold)
+
+
+        yolov10_infer.click(
+            fn=run_inference,
+            inputs=[image, video, image_size, conf_threshold, iou_threshold, input_type],
+            outputs=[output_image, output_video, output_class, output_name],
+        )
+
+        gr.Examples(
+            examples = [
+            ['./RXBASE-600_00071-1014-68_NLMIMAGE10_5715ABFD.jpg', 280, 0.2, 0.6],
+            ['./RXNAV-600_13668-0095-90_RXNAVIMAGE10_D145E8EF.jpg', 640, 0.2, 0.7],
+            ['./RXBASE-600_00074-7126-13_NLMIMAGE10_C003606B.jpg', 640, 0.2, 0.8],
+            ],
+            fn=yolov10_inference_for_examples,
+            inputs=[
+                image,
+                image_size,
+                conf_threshold,
+                iou_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()

drug_yolov10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d953e3db8e56519197a3e6d74d2b078226f7f1cf1de07064631003acb4a493f3
+size 33211887

requirements.txt

@@ -0,0 +1,4 @@
+gradio==4.32.1
+opencv_python==4.8.1.78
+opencv_python_headless==4.8.0.74
+git+https://github.com/THU-MIG/yolov10