Update app.py

app.py

@@ -82,13 +82,18 @@ def perform_detection(image, interpreter, labels):
             detections.append([object_name, scores[i], xmin, ymin, xmax, ymax])
     return image
 
+def resize_image(image, size=640):
+    return cv2.resize(image, (size, size))
+
 def detect_image(input_image):
     image = np.array(input_image)
-    result_image = perform_detection(image, interpreter, labels)
-    return Image.fromarray(result_image)
+    resized_image = resize_image(image)
+    result_image = perform_detection(resized_image, interpreter, labels)
+    result_image_resized = resize_image(result_image)
+    return Image.fromarray(result_image_resized)
 
 def detect_video(input_video):
-    cap = cv2.VideoCapture(input_video.name)
+    cap = cv2.VideoCapture(input_video)
     frames = []
 
     while cap.isOpened():
@@ -96,15 +101,20 @@ def detect_video(input_video):
         if not ret:
             break
 
-        result_frame = perform_detection(frame, interpreter, labels)
-        frames.append(result_frame)
+        resized_frame = resize_image(frame)
+        result_frame = perform_detection(resized_frame, interpreter, labels)
+        result_frame_resized = resize_image(result_frame)
+        frames.append(result_frame_resized)
 
     cap.release()
 
+    if not frames:
+        raise ValueError("No frames were read from the video.")
+
     height, width, layers = frames[0].shape
     size = (width, height)
-    output_video_path = "result_" + input_video.name
-    out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'DIVX'), 15, size)
+    output_video_path = "result_" + os.path.basename(input_video)
+    out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'mp4v'), 15, size)
 
     for frame in frames:
         out.write(frame)
@@ -113,26 +123,19 @@ def detect_video(input_video):
 
     return output_video_path
 
-image_input = gr.inputs.Image(type="pil", label="Upload an image")
-image_output = gr.outputs.Image(type="pil", label="Detection Result")
-
-video_input = gr.inputs.Video(type="file", label="Upload a video")
-video_output = gr.outputs.Video(label="Detection Result")
-
-app = gr.Interface(
-    fn=detect_image,
-    inputs=image_input,
-    outputs=image_output,
-    live=True,
-    description="Object Detection on Images"
-)
-
-app_video = gr.Interface(
-    fn=detect_video,
-    inputs=video_input,
-    outputs=video_output,
-    live=True,
-    description="Object Detection on Videos"
-)
-
-gr.TabbedInterface([app, app_video], ["Image Detection", "Video Detection"]).launch()
+app = gr.Blocks()
+
+with app:
+    with gr.Tab("Image Detection"):
+        gr.Markdown("Upload an image for object detection")
+        image_input = gr.Image(type="pil", label="Upload an image")
+        image_output = gr.Image(type="pil", label="Detection Result")
+        gr.Button("Submit").click(fn=detect_image, inputs=image_input, outputs=image_output)
+    
+    with gr.Tab("Video Detection"):
+        gr.Markdown("Upload a video for object detection")
+        video_input = gr.Video(label="Upload a video")
+        video_output = gr.Video(label="Detection Result")
+        gr.Button("Submit").click(fn=detect_video, inputs=video_input, outputs=video_output)
+
+app.launch()