Create app.py

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+import torch
+import cv2
+import numpy as np
+
+# Load YOLOv5 model
+def load_model():
+    return torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
+
+model = load_model()
+
+# YOLOv5 object detection function
+def yolo_object_detection(frame):
+    # Convert Gradio's RGB frame to BGR for OpenCV processing
+    img_bgr = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
+
+    # Perform YOLOv5 inference
+    results = model(img_bgr)
+    detections = results.pandas().xyxy[0]
+
+    # Draw bounding boxes and labels
+    for _, row in detections.iterrows():
+        x1, y1, x2, y2 = int(row['xmin']), int(row['ymin']), int(row['xmax']), int(row['ymax'])
+        label = f"{row['name']} {row['confidence']:.2f}"
+        cv2.rectangle(img_bgr, (x1, y1), (x2, y2), (255, 0, 0), 2)
+        cv2.putText(img_bgr, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (36, 255, 12), 2)
+
+    # Convert back to RGB for Gradio display
+    img_rgb = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)
+    return img_rgb
+
+# Gradio interface for real-time object detection
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            # Video input from webcam
+            input_img = gr.Image(sources=["webcam"], type="numpy", label="Webcam Input")
+        with gr.Column():
+            # Output with detected objects
+            output_img = gr.Image(streaming=True, label="YOLOv5 Object Detection Output")
+        
+        # Stream YOLOv5 object detection
+        input_img.stream(yolo_object_detection, inputs=[input_img], outputs=[output_img],
+                         time_limit=30, stream_every=0.1, concurrency_limit=30)
+
+# Launch the app
+demo.launch()