add: gradio structure for user inference

app.py

@@ -0,0 +1,180 @@
+import numpy as np
+import gradio as gr
+from ultralytics import YOLO
+import tempfile
+import cv2
+
+def inference(image, video, model_id, image_size, conf_threshold):
+    if model_id == "yolov10n-obb":
+        model = YOLO("")
+    elif model_id == "yolov10s-obb":
+        model = YOLO("")
+    elif model_id == "yolov10m-obb":
+        model = YOLO("")
+    
+    if image:
+        results = model.predict(source=image, imgsz=image_size, conf=conf_threshold, device="cpu")
+        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(*'vp90'), 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 inference_for_examples(image, model_path, image_size, conf_threshold):
+    annotated_image, _ = 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-obb-obb",
+                        "yolov10s-obb-obb",
+                        "yolov10m-obb-bb",
+                    ],
+                    value="yolov10n-obb-obb",
+                )
+                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,
+                )
+                inferBtn = gr.Button(value="Detect Phone and Camera")
+
+            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 inference(image, None, model_id, image_size, conf_threshold)
+            else:
+                return inference(None, video, model_id, image_size, conf_threshold)
+
+
+        inferBtn.click(
+            fn=run_inference,
+            inputs=[image, video, model_id, image_size, conf_threshold, input_type],
+            outputs=[output_image, output_video],
+        )
+
+        gr.Examples(
+            examples=[
+                [
+                    "test_images/P0024.jpg",
+                    "yolov10n-obb",
+                    640,
+                    0.25,
+                ],
+                [
+                    "test_images/P0035.jpg",
+                    "yolov10n-obb",
+                    640,
+                    0.25,
+                ],
+                [
+                    "test_images/P00121.jpg",
+                    "yolov10n-obb",
+                    640,
+                    0.25,
+                ],
+                [
+                    "test_images/P0180.jpg",
+                    "yolov10n-obb",
+                    640,
+                    0.25,
+                ],
+                [
+                    "test_images/P0279.jpg",
+                    "yolov10n-obb",
+                    640,
+                    0.25,
+                ],
+                [
+                    "test_images/P2112.jpg",
+                    "yolov10n-obb",
+                    640,
+                    0.25,
+                ],               
+            ],
+            fn=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.Markdown(
+        """
+    # YOLOv10 - OBB (Oriented Bounding Box)
+        """
+    )
+    with gr.Row():
+        with gr.Column():
+            app()
+if __name__ == '__main__':
+    gradio_app.queue()
+    gradio_app.launch()

requirements.txt

@@ -0,0 +1,3 @@
+ultralytics==8.2.49
+opencv-python==4.10.0.84
+numpy==1.26.4