Create app.py (#1)

- Create app.py (2bc270afa1baf158b6fe898121ccb36294638e9e)

app.py

@@ -0,0 +1,96 @@
+# Import necessary libraries
+import gradio as gr  # Gradio for creating the web interface
+import cv2  # OpenCV for image processing
+from huggingface_hub import hf_hub_download  # Download models from Hugging Face Hub
+from gradio_webrtc import WebRTC  # WebRTC integration for streaming webcam feeds in Gradio
+from twilio.rest import Client  # Twilio client for managing ICE servers for WebRTC
+import os  # OS module for environment variable access
+from inference import YOLOv10  # Custom YOLOv10 inference class
+
+# Download YOLOv10 model file from Hugging Face Hub
+model_file = hf_hub_download(
+    repo_id="onnx-community/yolov10n",  # Repository containing the YOLOv10 model
+    filename="onnx/model.onnx"  # Model file to download
+)
+
+# Initialize the YOLOv10 model
+model = YOLOv10(model_file)
+
+# Retrieve Twilio account credentials from environment variables
+account_sid = os.environ.get("TWILIO_ACCOUNT_SID")  # Twilio Account SID
+auth_token = os.environ.get("TWILIO_AUTH_TOKEN")  # Twilio Auth Token
+
+# Check if Twilio credentials are available
+if account_sid and auth_token:
+    # Initialize Twilio client with credentials
+    client = Client(account_sid, auth_token)
+
+    # Create a Twilio token for ICE server configuration
+    token = client.tokens.create()
+
+    # Configure WebRTC to use Twilio ICE servers for better connection reliability
+    rtc_configuration = {
+        "iceServers": token.ice_servers,  # Use Twilio ICE servers
+        "iceTransportPolicy": "relay",  # Relay policy to improve NAT traversal
+    }
+else:
+    # Use default WebRTC configuration if Twilio credentials are not available
+    rtc_configuration = None
+
+# Function to perform object detection
+def detection(image, conf_threshold=0.3):
+    # Resize the input image to match the model's expected dimensions
+    image = cv2.resize(image, (model.input_width, model.input_height))
+    # Perform object detection and return the processed image
+    new_image = model.detect_objects(image, conf_threshold)
+    return cv2.resize(new_image, (500, 500))  # Resize output image for display
+
+# Define custom CSS for Gradio interface layout
+css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
+                      .my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
+
+# Create a Gradio interface with custom blocks
+with gr.Blocks(css=css) as demo:
+    # Add a title to the Gradio interface
+    gr.HTML(
+        """
+    <h1 style='text-align: center'>
+    YOLOv10 Webcam Stream
+    </h1>
+    """
+    )
+    # Add links to the arXiv paper and GitHub repository for YOLOv10
+    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>
+        """
+    )
+    # Define a column layout for the interface
+    with gr.Column(elem_classes=["my-column"]):
+        with gr.Group(elem_classes=["my-group"]):
+            # Add a WebRTC component for webcam streaming
+            image = WebRTC(label="Stream", rtc_configuration=rtc_configuration)
+            # Add a slider to adjust the confidence threshold for object detection
+            conf_threshold = gr.Slider(
+                label="Confidence Threshold",  # Label for the slider
+                minimum=0.0,  # Minimum slider value
+                maximum=1.0,  # Maximum slider value
+                step=0.05,  # Step size for slider
+                value=0.30,  # Default slider value
+            )
+
+        # Stream webcam frames through the detection function
+        image.stream(
+            fn=detection,  # Detection function to process frames
+            inputs=[image, conf_threshold],  # Inputs: webcam stream and confidence threshold
+            outputs=[image],  # Outputs: processed frames
+            time_limit=10  # Limit each detection to 10 seconds
+        )
+
+# Launch the Gradio app when the script is run directly
+if __name__ == "__main__":
+    demo.launch()
+
+