Update app.py

app.py

@@ -1,59 +1,46 @@
+from huggingface_hub import hf_hub_download
+from ultralytics import YOLOv10
 import gradio as gr
-import numpy as np
-from fastrtc import WebRTC
-import time
-
-# WebRTC configuration with public STUN servers
-rtc_configuration = {
-    "iceServers": [
-        {"urls": "stun:stun.l.google.com:19302"},
-        {"urls": "stun:stun1.l.google.com:19302"}
-    ]
-}
-
-# Video processing function (example: flip video vertically)
-def flip_vertically(image):
-    return np.flip(image, axis=0)
-
-# Server-side function to process video stream
-def process_stream(webrtc_input):
-    while True:
-        # Get the next frame from the WebRTC input
-        frame = next(webrtc_input, None)
-        if frame is not None:
-            # Process the frame (e.g., flip vertically)
-            processed_frame = flip_vertically(frame)
-            yield processed_frame
-        # Control frame rate (e.g., process every 0.1 seconds)
-        time.sleep(0.1)
-
-# Gradio app setup
-with gr.Blocks() as demo:
-    gr.HTML("<h1 style='text-align: center'>Real-Time Webcam Stream with FastRTC</h1>")
-    
-    # WebRTC component for video streaming
-    webrtc_input = WebRTC(
-        label="Webcam Stream",
-        mode="send",
-        modality="video",
-        rtc_configuration=rtc_configuration,
-    )
-    
-    # Output component to display processed video
-    webrtc_output = WebRTC(
-        label="Processed Stream",
-        mode="receive",
-        modality="video",
-        rtc_configuration=rtc_configuration,
-    )
-    
-    # Connect input to output through the processing function
-    demo.load(
-        fn=process_stream,
-        inputs=[webrtc_input],
-        outputs=[webrtc_output],
-        queue=True,
+from gradio_webrtc import WebRTC
+
+model_file = hf_hub_download(
+    repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
+)
+
+model = YOLOv10(model_file)
+
+def detection(image, conf_threshold=0.3):
+    image = cv2.resize(image, (model.input_width, model.input_height))
+    new_image = model.detect_objects(image, conf_threshold)
+    return new_image
+
+
+
+css = """.my-group {max-width: 600px !important; max-height: 600px !important;}
+         .my-column {display: flex !important; justify-content: center !important; align-items: center !important;}"""
+
+with gr.Blocks(css=css) as demo:
+    gr.HTML(
+        """
+        <h1 style='text-align: center'>
+        YOLOv10 Webcam Stream (Powered by WebRTC ⚡️)
+        </h1>
+        """
     )
+    with gr.Column(elem_classes=["my-column"]):
+        with gr.Group(elem_classes=["my-group"]):
+            image = WebRTC(label="Stream", rtc_configuration=rtc_configuration)
+            conf_threshold = gr.Slider(
+                label="Confidence Threshold",
+                minimum=0.0,
+                maximum=1.0,
+                step=0.05,
+                value=0.30,
+            )
+
+        image.stream(
+            fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
+        )
 
-# Launch the app
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()