Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 from transformers import CLIPModel, CLIPProcessor
 from PIL import Image
-import requests
 
 # Step 1: Load Fine-Tuned Model from Hugging Face Model Hub
 model_name = "quadranttechnologies/retail-content-safety-clip-finetuned"
@@ -68,7 +67,6 @@ def classify_image(image):
         }
 
     except Exception as e:
-        # Log and return detailed error messages
         print(f"Error during classification: {e}")
         return {"Error": str(e)}
 
@@ -76,27 +74,13 @@ def classify_image(image):
 iface = gr.Interface(
     fn=classify_image,
     inputs=gr.Image(type="pil"),
-    outputs=gr.Label(label="Output"),  # Display probabilities as progress bars
+    outputs=gr.Textbox(label="Output (Debug Mode)"),  # Use Textbox to display errors if any occur
     title="Content Safety Classification",
     description="Upload an image to classify it as 'safe' or 'unsafe' with corresponding probabilities.",
 )
 
-# Step 4: Test Before Launch
+# Step 4: Launch Gradio Interface
 if __name__ == "__main__":
-    print("Testing model locally with a sample image...")
-    try:
-        # Test with a sample image
-        url = "https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png"
-        test_image = Image.open(requests.get(url, stream=True).raw)
-
-        # Run the classification function
-        print("Running local test...")
-        result = classify_image(test_image)
-        print(f"Local Test Result: {result}")
-    except Exception as e:
-        print(f"Error during local test: {e}")
-
-    # Launch Gradio Interface
     print("Launching the Gradio interface...")
     iface.launch()
 
@@ -128,5 +112,6 @@ if __name__ == "__main__":
 
 
 
+