Update app.py

app.py

@@ -2,38 +2,44 @@ import os
 from transformers import BlipProcessor, BlipForConditionalGeneration
 import gradio as gr
 
-# Load the token from the environment
-HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
+# Load the Hugging Face token from the environment using the secret name
+HUGGINGFACE_TOKEN = os.getenv("Image_classification")
 
-# Load the model and processor with the token
+# Load the processor and model with the token
 processor = BlipProcessor.from_pretrained(
-    "quadranttechnologies/Imageclassification",
+    "quadranttechnologies/qhub-blip-image-captioning-finetuned", 
     use_auth_token=HUGGINGFACE_TOKEN
 )
 model = BlipForConditionalGeneration.from_pretrained(
-    "quadranttechnologies/Imageclassification",
+    "quadranttechnologies/qhub-blip-image-captioning-finetuned", 
     use_auth_token=HUGGINGFACE_TOKEN
 )
 
-# Define your Gradio interface and logic as before
+# Function to generate captions for uploaded images
 def generate_caption(image):
     try:
+        # Prepare the image inputs for the model
         inputs = processor(image, return_tensors="pt")
+
+        # Generate the caption
         outputs = model.generate(**inputs)
         caption = processor.decode(outputs[0], skip_special_tokens=True)
         return caption
     except Exception as e:
         return f"Error generating caption: {e}"
 
+# Set up the Gradio interface
 interface = gr.Interface(
     fn=generate_caption,
-    inputs=gr.Image(type="pil"),
-    outputs="text",
+    inputs=gr.Image(type="pil"),  # Accepts image uploads
+    outputs="text",               # Displays generated captions as text
     title="Image Captioning Model",
-    description="Upload an image to receive a caption generated by the model."
+    description="Upload an image to generate a caption using the fine-tuned BLIP model."
 )
 
+# Launch the Gradio app
 if __name__ == "__main__":
     interface.launch(share=True)
 
 
+