inital version

app.py

@@ -45,6 +45,8 @@ def delete_later(path: Union[str, os.PathLike], delay: int = 300):
 
 @spaces.GPU
 def run_with_gpu(image, prompt_depth):
+    image = image.to(DEVICE)
+    prompt_depth = prompt_depth.to(DEVICE)
     depth = model.predict(image, prompt_depth)
     depth = depth[0, 0].detach().cpu().numpy()
     return depth
@@ -121,6 +123,8 @@ def run(input_file, resolution):
 DESCRIPTION = """
 # Estimate accurate and high-resolution depth maps from your iPhone capture.
 
+Project Page: [Prompt Depth Anything](https://promptda.github.io/)
+
 ## Requirements:
 1. iPhone 12 Pro or later Pro models, iPad 2020 Pro or later Pro models
 2. Free iOS App: [Stray Scanner App](https://apps.apple.com/us/app/stray-scanner/id1557051662)
@@ -140,35 +144,24 @@ Note:
 def main(share: bool):
     with gr.Blocks(theme=gr.themes.Soft()) as demo:
         gr.Markdown(DESCRIPTION)
-        
-        
 
         with gr.Row():
-            input_file = gr.File(type="filepath", label="Upload a stray scanner app capture zip file")
+            input_file = gr.File(type="filepath", label="Stray scanner app capture zip file")
             resolution = gr.Dropdown(choices=['756x1008', '1428x1904'], value='756x1008', label="Inference resolution")
             submit_btn = gr.Button("Submit")
 
-        gr.Examples(examples=[
-                ["data/assets/example0_chair.zip", "756x1008"]
-            ],
-            inputs=[input_file, resolution],
-            # outputs=[output_rgb, output_depths, output_3d_model, output_ply, output_depth_map],
-            label="Examples",
-        ) 
-
         with gr.Row():
             with gr.Column():
                 output_rgb = gr.Image(type="numpy", label="RGB Image")
             with gr.Column():
-                output_depths = ImageSlider(label="Depth map / prompt depth", position=0.5)
+                output_depths = ImageSlider(label="Output depth / prompt depth", position=0.5)
         
         with gr.Row():
             with gr.Column():
                 output_3d_model = gr.Model3D(label="3D Viewer", display_mode='solid', clear_color=[1.0, 1.0, 1.0, 1.0])
             with gr.Column():
-                output_ply = gr.File(type="filepath", label="Download the unprojected point cloud as .ply file")
-                output_depth_map = gr.File(type="filepath", label="Download the depth map as .png file")
-        
+                output_ply = gr.File(type="filepath", label="Download the unprojected point cloud as .ply file", height=30)
+                output_depth_map = gr.File(type="filepath", label="Download the depth map as .png file", height=30)
         outputs = [
             output_rgb,
             output_depths,
@@ -176,7 +169,15 @@ def main(share: bool):
             output_ply,
             output_depth_map,
         ]
-
+        gr.Examples(examples=[
+                ["data/assets/example0_chair.zip", "756x1008"]
+            ],
+            fn=run,
+            inputs=[input_file, resolution],
+            outputs=outputs,
+            label="Examples",
+            cache_examples=True,
+        ) 
         submit_btn.click(run, 
                          inputs=[input_file, resolution], 
                          outputs=outputs)

promptda/utils/io_wrapper.py

@@ -7,14 +7,14 @@ import cv2
 
 from promptda.utils.logger import Log
 
-DEVICE = 'cuda' if torch.cuda.is_available(
-) else 'mps' if torch.backends.mps.is_available() else 'cpu'
+# DEVICE = 'cuda' if torch.cuda.is_available(
+# ) else 'mps' if torch.backends.mps.is_available() else 'cpu'
 
 
 def to_tensor_func(arr):
     if arr.ndim == 2:
         arr = arr[:, :, np.newaxis]
-    return torch.from_numpy(arr).permute(2, 0, 1).unsqueeze(0).to(DEVICE)
+    return torch.from_numpy(arr).permute(2, 0, 1).unsqueeze(0)
 
 
 def to_numpy_func(tensor):