Update app.py

app.py

@@ -22,7 +22,7 @@ def predict(image, max_length=64, num_beams=4):
     pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values
     pixel_values = pixel_values.to(device)
     with torch.no_grad():
-        text = model.generate(pixel_values.unsqueeze(0).cuda())
+        text = model.generate(pixel_values.unsqueeze(0).cpu())
         text = tokenizer.decode(text.replace('<|endoftext|>', '').split('\n')[0],'\n\n\n')
        # output_ids = model.generate(
         #    pixel_values,