Update app.py

app.py

@@ -16,34 +16,33 @@ processor = DPTImageProcessor.from_pretrained("Intel/dpt-swinv2-tiny-256")
 color_map = cv2.applyColorMap(np.arange(256, dtype=np.uint8), cv2.COLORMAP_INFERNO)
 
 input_tensor = torch.zeros((1, 3, 128, 128), dtype=torch.float32, device=device)
-depth_map = np.zeros((128, 128), dtype=np.float32)
-depth_map_colored = np.zeros((128, 128, 3), dtype=np.uint8)
 
 def preprocess_image(image):
     return cv2.resize(image, (128, 128), interpolation=cv2.INTER_AREA).transpose(2, 0, 1).astype(np.float32) / 255.0
 
 @torch.inference_mode()
 def process_frame(image):
+    if image is None:
+        return None
     preprocessed = preprocess_image(image)
     input_tensor[0] = torch.from_numpy(preprocessed).to(device)
-
-    if torch.cuda.is_available():
-        torch.cuda.synchronize()
-
+    
     predicted_depth = model(input_tensor).predicted_depth
-    np.subtract(predicted_depth.squeeze().cpu().numpy(), predicted_depth.min().item(), out=depth_map)
-    np.divide(depth_map, depth_map.max(), out=depth_map)
-    np.multiply(depth_map, 255, out=depth_map)
-    depth_map = depth_map.astype(np.uint8)
-    cv2.applyColorMap(depth_map, color_map, dst=depth_map_colored)
+    depth_map = predicted_depth.squeeze().cpu().numpy()
+    depth_map = (depth_map - depth_map.min()) / (depth_map.max() - depth_map.min())
+    depth_map = (depth_map * 255).astype(np.uint8)
+    depth_map_colored = cv2.applyColorMap(depth_map, color_map)
     
-    return depth_map_colored
+    return cv2.cvtColor(depth_map_colored, cv2.COLOR_BGR2RGB)
 
 interface = gr.Interface(
     fn=process_frame,
     inputs=gr.Image(sources="webcam", streaming=True),
     outputs="image",
-    live=True
+    live=True,
+    batch=False,
+    max_batch_size=1,
+    update_interval=0.1  # Update every 0.1 seconds
 )
 
 interface.launch()