Update app.py

app.py

@@ -46,22 +46,35 @@ transform = transforms.Compose([
 
 def predict(input_data):
     try:
-        # Check if the input is a URL or image (Gradio will pass either based on user input)
+        print(f"Input data received: {input_data}, Type: {type(input_data)}")
+        
+        # Check if the input is a URL or image
         if isinstance(input_data, str):  # If it's a string, assume it's a URL
-            response = requests.get(input_data)
-            if response.status_code == 200:
+            try:
+                response = requests.get(input_data)
+                response.raise_for_status()  # Raise error for HTTP issues
                 img = Image.open(BytesIO(response.content))
-            else:
-                return json.dumps({"error": "Unable to fetch image from the URL."})
+                print("Image fetched successfully from URL.")
+            except Exception as e:
+                print(f"Error fetching image from URL: {e}")
+                return json.dumps({"error": f"Failed to fetch image from URL: {e}"})
         else:  # If it's not a string, assume it's an image file
             img = input_data
 
-        # Check if the input is a PIL Image type
+        # Validate the image
         if not isinstance(img, Image.Image):
+            print("Invalid image format received.")
             return json.dumps({"error": "Invalid image format received. Please provide a valid image."})
+        else:
+            print(f"Image successfully loaded: {img}")
 
         # Apply transformations to the image
         img = transform(img).unsqueeze(0)
+        print(f"Transformed image tensor shape: {img.shape}")
+
+        # Ensure model is loaded
+        if model is None:
+            return json.dumps({"error": "Model not loaded. Ensure the model file is available and correctly loaded."})
 
         # Move the image to the correct device
         img = img.to(torch.device("cuda" if torch.cuda.is_available() else "cpu"))
@@ -70,6 +83,7 @@ def predict(input_data):
         with torch.no_grad():
             outputs = model(img)
             predicted_class = torch.argmax(outputs, dim=1).item()
+            print(f"Model prediction outputs: {outputs}, Predicted class: {predicted_class}")
 
         # Return the result based on the predicted class
         if predicted_class == 0:
@@ -80,9 +94,11 @@ def predict(input_data):
             return json.dumps({"error": "Unexpected class prediction."})
 
     except Exception as e:
+        print(f"Error processing image: {e}")
         return json.dumps({"error": f"Error processing image: {e}"})
 
 
+
 # Create the Gradio interface with both local file upload and URL input
 iface = gr.Interface(
     fn=predict,