Update app.py

app.py

@@ -1,8 +1,8 @@
 import gradio as gr
-import cv2
 import torch
 from PIL import Image
 from transformers import DetrImageProcessor, DetrForObjectDetection
+import cv2
 import numpy as np
 
 # Load the pre-trained DETR model
@@ -33,55 +33,11 @@ def image_object_detection(image_pil):
 
     return image_np
 
-# Function for live object detection from the camera
-def live_object_detection():
-    # Open a connection to the camera (replace with your own camera setup)
-    cap = cv2.VideoCapture(0)
-
-    while True:
-        # Capture frame-by-frame
-        ret, frame = cap.read()
-
-        # Convert the frame to PIL Image
-        frame_pil = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
-
-        # Process the frame with the DETR model
-        inputs = processor(images=frame_pil, return_tensors="pt")
-        outputs = model(**inputs)
-
-        # convert outputs (bounding boxes and class logits) to COCO API
-        # let's only keep detections with score > 0.9
-        target_sizes = torch.tensor([frame_pil.size[::-1]])
-        results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
-
-        # Draw bounding boxes on the frame
-        for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
-            box = [int(round(i)) for i in box.tolist()]
-            cv2.rectangle(frame, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
-            label_text = f"{model.config.id2label[label.item()]}: {round(score.item(), 3)}"
-            cv2.putText(frame, label_text, (box[0], box[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
-
-        # Display the resulting frame
-        cv2.imshow('Object Detection', frame)
-
-        # Break the loop when 'q' key is pressed
-        if cv2.waitKey(1) & 0xFF == ord('q'):
-            break
-
-    # Release the camera and close all windows
-    cap.release()
-    cv2.destroyAllWindows()
-
 # Define the Gradio interface
 iface = gr.Interface(
-    fn=[image_object_detection, live_object_detection],
-    inputs=[
-        gr.Image(type="pil", label="Upload an image for object detection") # Remove this line
-    ],
-    outputs=[
-        "image",
-        "image",
-    ],
+    fn=image_object_detection,
+    inputs=gr.Image(type="pil", label="Upload an image for object detection"),
+    outputs="image",
     live=True,
 )