use streaming

app.py

@@ -4,45 +4,14 @@ import cv2
 import tempfile
 from ultralytics import YOLOv10
 
-@spaces.GPU
-def yolov10_inference(image, video, model_id, image_size, conf_threshold):
-    model = YOLOv10.from_pretrained(f'jameslahm/{model_id}')
-    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
+model = YOLOv10.from_pretrained(f'jameslahm/yolov10s')
 
 @spaces.GPU
-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 yolov10_inference(image, conf_threshold):
+    width, _ = image.size
+    results = model.predict(source=image, imgsz=width, conf=conf_threshold)
+    annotated_image = results[0].plot()
+    return annotated_image[:, :, ::-1]
 
 
 def app():
@@ -50,31 +19,6 @@ def app():
         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,
@@ -82,64 +26,18 @@ def app():
                     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],
+        image.stream(
+            fn=yolov10_inference,
+            inputs=[image, conf_threshold],
+            outputs=[image],
+            stream_every=0.1,
+            time_limit=30
         )
 
-        gr.Examples(
-            examples=[
-                [
-                    "bus.jpg",
-                    "yolov10s",
-                    640,
-                    0.25,
-                ],
-                [
-                    "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: