Update

app.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 import functools
-import os
 import sys
 from typing import Callable
 
@@ -12,6 +11,7 @@ import gradio as gr
 import huggingface_hub
 import numpy as np
 import PIL.Image
+import spaces
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -66,6 +66,7 @@ def crop_face(image: np.ndarray, box: tuple[int, int, int, int]) -> np.ndarray:
     return image
 
 
+@spaces.GPU
 @torch.inference_mode()
 def predict(image: np.ndarray, transform: Callable, model: nn.Module, device: torch.device) -> np.ndarray:
     indices = torch.arange(66).float().to(device)
@@ -129,7 +130,9 @@ def run(
 
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-face_detector = RetinaFacePredictor(threshold=0.8, device=device, model=RetinaFacePredictor.get_model("mobilenet0.25"))
+face_detector = RetinaFacePredictor(threshold=0.8, device="cpu", model=RetinaFacePredictor.get_model("mobilenet0.25"))
+face_detector.device = device
+face_detector.net.to(device)
 
 model_names = [
     "hopenet_alpha1",
@@ -157,7 +160,13 @@ with gr.Blocks(css="style.css") as demo:
         inputs=[image, model_name],
         outputs=result,
         fn=fn,
-        cache_examples=os.getenv("CACHE_EXAMPLES") == "1",
     )
-    run_button.click(fn=fn, inputs=[image, model_name], outputs=result, api_name="run")
-demo.queue().launch()
+    run_button.click(
+        fn=fn,
+        inputs=[image, model_name],
+        outputs=result,
+        api_name="run",
+    )
+
+if __name__ == "__main__":
+    demo.queue().launch()