Update app.py

app.py

@@ -427,12 +427,13 @@ def generate_gradcam_caption(image, processor, model, max_length=60):
     Generate a detailed analysis of GradCAM visualization using the fine-tuned BLIP model
     """
     try:
-        # Check for available GPU
+        # Process image first
+        inputs = processor(image, return_tensors="pt")
+        
+        # Check for available GPU and move model and inputs
         device = "cuda" if torch.cuda.is_available() else "cpu"
         model = model.to(device)
-        
-        # Process image with BLIP
-        inputs = processor(image, return_tensors="pt").to(device)
+        inputs = {k: v.to(device) if hasattr(v, 'to') else v for k, v in inputs.items()}
         
         # Generate caption
         with torch.no_grad():