Update app.py

app.py

@@ -2,9 +2,6 @@ import streamlit as st
 import torch
 from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
 from PIL import Image
-from transformers import AutoProcessor, AutoModelForImageTextToText
-
-
 
 # Load the model and processor
 model_id = "brucewayne0459/paligemma_derm"
@@ -38,7 +35,7 @@ st.markdown(
 
 # Streamlit app title and instructions
 st.title("Skin Condition Identifier")
-st.write("Upload an image and provide a text prompt to identify the skin condition.")
+st.write("Upload an image and provide a custom prompt to identify the skin condition.")
 
 # Column layout for input and display
 col1, col2 = st.columns([3, 2])
@@ -46,51 +43,41 @@ col1, col2 = st.columns([3, 2])
 with col1:
     # File uploader for image
     uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
-    prompt = "Identify the skin condition?"
-    
-    # Text input for prompt
-    input_text = st.text_input("Enter your prompt:", prompt)
-    
+    prompt = st.text_input("Enter your prompt:", "Identify the skin condition?")
+
 with col2:
-    # Display uploaded image (if any)
     if uploaded_file:
+        # Open and resize the uploaded image
         input_image = Image.open(uploaded_file).convert("RGB")
-        
-        # Resize image for display (300x300 pixels)
         resized_image = input_image.resize((300, 300))
-        
-        # Display the resized image
         st.image(resized_image, caption="Uploaded Image (300x300)", use_container_width=True)
 
-    # Process and display the result when the button is clicked
-    if uploaded_file and st.button("Analyze"):
-        if not input_text.strip():
-            st.error("Please provide a valid prompt!")
-        else:
+        # Resize image for processing (512x512 pixels)
+        max_size = (512, 512)
+        processed_image = input_image.resize(max_size)
+
+        # Predict automatically when the image is uploaded or the prompt changes
+        with st.spinner("Processing..."):
             try:
-                # Resize image for processing (512x512 pixels)
-                max_size = (512, 512)
-                input_image = input_image.resize(max_size)
-    
                 # Prepare inputs
-                with st.spinner("Processing..."):
-                    inputs = processor(
-                        text=input_text,
-                        images=input_image,
-                        return_tensors="pt",
-                        padding="longest"
-                    ).to(device)
-    
-                    # Generate output with default max_new_tokens
-                    default_max_tokens = 50  # Set a default value for max tokens
-                    with torch.no_grad():
-                        outputs = model.generate(**inputs, max_new_tokens=default_max_tokens)
-                    
-                    # Decode output
-                    decoded_output = processor.decode(outputs[0], skip_special_tokens=True)
-    
+                inputs = processor(
+                    text=prompt,
+                    images=processed_image,
+                    return_tensors="pt",
+                    padding="longest"
+                ).to(device)
+
+                # Generate output
+                default_max_tokens = 50  # Set a default value for max tokens
+                with torch.no_grad():
+                    outputs = model.generate(**inputs, max_new_tokens=default_max_tokens)
+
+                # Decode output
+                decoded_output = processor.decode(outputs[0], skip_special_tokens=True)
+
                 # Display result
                 st.success("Analysis Complete!")
                 st.write("**Model Output:**", decoded_output)
+
             except Exception as e:
                 st.error(f"Error: {str(e)}")