Update app.py

app.py

@@ -1,6 +1,5 @@
 import streamlit as st
 from transformers import AutoProcessor, VisionEncoderDecoderModel
-import requests
 from PIL import Image
 import torch
 
@@ -23,12 +22,15 @@ if uploaded_file is not None:
     image = Image.open(uploaded_file).convert("RGB")
     st.image(image, caption="Uploaded Image", use_column_width=True)
 
-    # Preprocessing image
+    # Preprocess the image
     pixel_values = processor(images=image, return_tensors="pt").pixel_values
 
-    # Generate caption
+    # Generate caption (inference)
     generated_ids = model.generate(pixel_values)
+
+    # Decode the generated caption
     generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
+    # Display the generated caption
     st.write("Generated Caption: ")
     st.success(generated_text)