Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import torch
 from PIL import Image
-from torchvision.transforms import functional as F
 from transformers import DetrImageProcessor, DetrForObjectDetection
 import cv2
 import numpy as np
@@ -32,15 +31,30 @@ def detect_objects(frame):
         frame = cv2.putText(frame, f'{model.config.id2label[label.item()]}: {round(score.item(), 3)}',
                             (int(box[0]), int(box[1]) - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2, cv2.LINE_AA)
 
-    return frame
+    return cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
 
-# Define the Gradio interface
-iface = gr.Interface(
-    fn=detect_objects,
-    inputs=gr.Video(),
-    outputs="numpy_image",
-    live=True,
-)
+# Function to capture video frames and process them
+def capture_frames():
+    cap = cv2.VideoCapture(0)  # Use 0 for default camera, you can change it if needed
 
-# Launch the Gradio app
-iface.launch()
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        # Process the frame
+        processed_frame = detect_objects(frame)
+
+        # Display the processed frame
+        cv2.imshow("Object Detection", processed_frame)
+
+        # Check for exit key (press 'q' to exit)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    # Release the camera and close all windows
+    cap.release()
+    cv2.destroyAllWindows()
+
+# Run the video capturing and processing function
+capture_frames()