Update app.py

app.py

@@ -5,33 +5,34 @@ from transformers import DPTForDepthEstimation, DPTImageProcessor
 import gradio as gr
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model = DPTForDepthEstimation.from_pretrained("Intel/dpt-swinv2-tiny-256", torch_dtype=torch.float16).to(device)
+model = DPTForDepthEstimation.from_pretrained("./", local_files_only=True, torch_dtype=torch.float16).to(device)
 processor = DPTImageProcessor.from_pretrained("Intel/dpt-swinv2-tiny-256")
 
 color_map = cv2.applyColorMap(np.arange(256, dtype=np.uint8), cv2.COLORMAP_INFERNO)
 
+@torch.inference_mode()
 def process_frame(image):
     rgb_frame = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-    resized_frame = cv2.resize(rgb_frame, (128, 128))
+    resized_frame = cv2.resize(rgb_frame, (128, 128), interpolation=cv2.INTER_AREA)
 
     inputs = processor(images=resized_frame, return_tensors="pt").to(device)
     inputs = {k: v.to(torch.float16) for k, v in inputs.items()}
 
-    with torch.no_grad():
-        outputs = model(**inputs)
-        predicted_depth = outputs.predicted_depth
-
+    predicted_depth = model(**inputs).predicted_depth
     depth_map = predicted_depth.squeeze().cpu().numpy()
-    depth_map = cv2.normalize(depth_map, None, 0, 255, cv2.NORM_MINMAX, dtype=cv2.CV_8U)
+    
+    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 cv2.cvtColor(depth_map_colored, cv2.COLOR_BGR2RGB)
+    return depth_map_colored
 
 interface = gr.Interface(
     fn=process_frame,
-    inputs=gr.Image(sources="webcam", streaming=True),
+    inputs=gr.Image(source="webcam", streaming=True),
     outputs="image",
-    live=True
+    live=True,
+    refresh_rate=0.1
 )
 
 interface.launch()