code

app.py

@@ -21,7 +21,7 @@ def draw_bounding_boxes(image, results, model, threshold=0.3):
 
 
 @spaces.GPU
-def yolov10_inference(image, conf_threshold):
+def inference(image, conf_threshold):
 
     inputs = image_processor(images=image, return_tensors="pt")
 
@@ -60,17 +60,31 @@ with gr.Blocks(css=css) as app:
     gr.HTML(
         """
     <h1 style='text-align: center'>
-    Near Real-Time Webcam Stream with RTDetr
+    Near Real-Time Webcam Stream with RT-DETR
     </h1>
     """)
     gr.HTML(
         """
         <h3 style='text-align: center'>
-        <a href='https://arxiv.org/abs/2304.08069' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
+        <a href='https://arxiv.org/abs/2304.08069' target='_blank'>arXiv</a> | <a href='https://github.com/lyuwenyu/RT-DETR' target='_blank'>github</a>
         </h3>
         """)
-    with gr.Row():
-        with gr.Column():
-            app()
+    with gr.Column(elem_classes=['my-column']):
+         with gr.Group(elem_classes=["my-group"]):
+            image = gr.Image(type="pil", label="Image", visible=True, sources="webcam", height=500, width=500)
+            conf_threshold = gr.Slider(
+                label="Confidence Threshold",
+                minimum=0.0,
+                maximum=1.0,
+                step=0.05,
+                value=0.85,
+            )
+            image.stream(
+                fn=inference,
+                inputs=[image, conf_threshold],
+                outputs=[image],
+                stream_every=0.2,
+                time_limit=30
+            )
 if __name__ == '__main__':
     app.launch()