Update app.py

app.py

@@ -1,29 +1,33 @@
 import gradio as gr
 from transformers import pipeline
+import torch
+import numpy as np
+from PIL import Image
 
 
 depth_estimator = pipeline(task="depth-estimation",
                         model="Intel/dpt-hybrid-midas")
-
-def launch(input_image):
-    out = depth_estimator(input_image)
+if __name__ == "__main__":
+    
+    def launch(input_image):
+        out = depth_estimator(input_image)
 
     # resize the prediction
-    prediction = torch.nn.functional.interpolate(
-        out["predicted_depth"].unsqueeze(1),
-        size=input_image.size[::-1],
-        mode="bicubic",
-        align_corners=False,
-    )
+        prediction = torch.nn.functional.interpolate(
+            out["predicted_depth"].unsqueeze(1),
+            size=input_image.size[::-1],
+            mode="bicubic",
+            align_corners=False,
+        )
 
     # normalize the prediction
-    output = prediction.squeeze().numpy()
-    formatted = (output * 255 / np.max(output)).astype("uint8")
-    depth = Image.fromarray(formatted)
-    return depth
+        output = prediction.squeeze().numpy()
+        formatted = (output * 255 / np.max(output)).astype("uint8")
+        depth = Image.fromarray(formatted)
+        return depth
 
-iface = gr.Interface(launch,
+    iface = gr.Interface(launch,
                      inputs=gr.Image(type='pil'),
                      outputs=gr.Image(type='pil'))
 
-iface.launch()
+    iface.launch()