Create app.py

app.py

@@ -0,0 +1,44 @@
+import gradio as gr
+from transformers import pipeline
+import torch
+import numpy as np
+from PIL import Image
+import gradio as gr
+from gradio_client import Client
+import os
+import json
+import spaces
+
+dpt_beit = pipeline(task = "depth-estimation", model="Intel/dpt-beit-base-384")
+depth_anything = pipeline(task = "depth-estimation", model="nielsr/depth-anything-small")
+@spaces.GPU
+def depth_anything_inference(image_path):
+  return depth_anything(image_path)["depth"]
+
+@spaces.GPU
+def dpt_beit_inference(image):
+  return dpt_beit(image)["depth"]
+
+def dpt_large(image_path):
+    try:
+        client = Client("https://nielsr-dpt-depth-estimation.hf.space/")
+        return Image.open(client.predict(image_path))
+    except Exception:
+        gr.Warning("The DPT-Large Space is currently unavailable. Please try again later.")
+        return ""
+    
+
+def infer(image):
+  return dpt_large(image), dpt_beit_inference(image), depth_anything_inference(image)
+
+
+iface = gr.Interface(fn=infer, 
+                     inputs=gr.Image(type="pil"), 
+                     outputs=[gr.Image(type="pil", label="DPT-Large"),
+                              gr.Image(type="pil", label="DPT with BeiT Backbone"),
+                              gr.Image(type="pil", label="Depth Anything")],
+                              
+                     title="Compare Depth Estimation Models",
+                     description="In this Space you can compare various depth estimation models",
+                     examples=[["bee.JPG"]])
+iface.launch(debug=True)