Update app.py

app.py

@@ -20,7 +20,7 @@ warnings.filterwarnings("ignore", category=UserWarning)
 
 # App title and description
 st.set_page_config(
-    page_title="Deepfake Image Analyser", 
+    page_title="Deepfake Analyzer", 
     layout="wide",
     page_icon="🔍"
 )
@@ -42,9 +42,9 @@ def check_gpu():
 # Sidebar components
 st.sidebar.title("Options")
 
-# Fixed values instead of sliders
-temperature = 0.7  # Fixed temperature value
-max_tokens = 500   # Fixed max tokens value
+# Fixed values for temperature and max tokens
+temperature = 0.7
+max_tokens = 500
 
 # Custom instruction text area in sidebar
 custom_instruction = st.sidebar.text_area(
@@ -542,11 +542,7 @@ def load_llm_model():
             return None, None
 
 # Analyze image function
-def analyze_image_with_llm(image, gradcam_overlay, face_box, pred_label, confidence, question, model, tokenizer, custom_instruction=""):
-    # Use fixed values for temperature and max_tokens
-    temperature = 0.7  # Fixed temperature value
-    max_tokens = 500   # Fixed max tokens value
-    
+def analyze_image_with_llm(image, gradcam_overlay, face_box, pred_label, confidence, question, model, tokenizer, temperature=0.7, max_tokens=500, custom_instruction=""):
     # Create a prompt that includes GradCAM information
     if custom_instruction.strip():
         full_prompt = f"{question}\n\nThe image has been processed with GradCAM and classified as {pred_label} with confidence {confidence:.2f}. Focus on the highlighted regions in red/yellow which show the areas the detection model found suspicious.\n\n{custom_instruction}"
@@ -761,4 +757,150 @@ def main():
                         st.session_state.current_pred_label = pred_label
                         st.session_state.current_confidence = confidence
                         
-                        st.success("✅ Initial detection and GradCAM visualization complete!")
+                        st.success("✅ Initial detection and GradCAM visualization complete!")
+                else:
+                    st.warning("⚠️ Please load the CLIP model first to perform initial detection.")
+            except Exception as e:
+                st.error(f"Error processing image: {str(e)}")
+                import traceback
+                st.error(traceback.format_exc())  # This will show the full error traceback
+    
+    # Image Analysis Summary section - AFTER Stage 2
+    if hasattr(st.session_state, 'current_image') and (hasattr(st.session_state, 'image_caption') or hasattr(st.session_state, 'gradcam_caption')):
+        with st.expander("Image Analysis Summary", expanded=True):
+            st.subheader("Generated Descriptions and Analysis")
+            
+            # Display image, captions, and results in organized layout with proper formatting
+            col1, col2 = st.columns([1, 2])
+            
+            with col1:
+                # Display original image and overlay side by side with controlled size
+                st.image(st.session_state.current_image, caption="Original Image", width=300)
+                if hasattr(st.session_state, 'current_overlay'):
+                    st.image(st.session_state.current_overlay, caption="GradCAM Overlay", width=300)
+            
+            with col2:
+                # Detection result
+                if hasattr(st.session_state, 'current_pred_label'):
+                    st.markdown("### Detection Result")
+                    st.markdown(f"**Classification:** {st.session_state.current_pred_label} (Confidence: {st.session_state.current_confidence:.2%})")
+                    st.markdown("---")
+                
+                # Image description
+                if hasattr(st.session_state, 'image_caption'):
+                    st.markdown("### Image Description")
+                    st.markdown(st.session_state.image_caption)
+                    st.markdown("---")
+                
+                # GradCAM analysis
+                if hasattr(st.session_state, 'gradcam_caption'):
+                    st.markdown("### GradCAM Analysis")
+                    st.markdown(st.session_state.gradcam_caption)
+    
+    # LLM Analysis section - AFTER Image Analysis Summary
+    with st.expander("Stage 3: Detailed Analysis with Vision LLM", expanded=False):
+        if hasattr(st.session_state, 'current_image') and st.session_state.llm_model_loaded:
+            st.subheader("Detailed Deepfake Analysis")
+            
+            # Display chat history
+            for i, (question, answer) in enumerate(st.session_state.chat_history):
+                st.markdown(f"**Question {i+1}:** {question}")
+                st.markdown(f"**Answer:** {answer}")
+                st.markdown("---")
+            
+            # Include both captions in the prompt if available
+            caption_text = ""
+            if hasattr(st.session_state, 'image_caption'):
+                caption_text += f"\n\nImage Description:\n{st.session_state.image_caption}"
+                
+            if hasattr(st.session_state, 'gradcam_caption'):
+                caption_text += f"\n\nGradCAM Analysis:\n{st.session_state.gradcam_caption}"
+            
+            # Default question with option to customize
+            default_question = f"This image has been classified as {st.session_state.current_pred_label}. Analyze the key features that led to this classification, focusing on the highlighted areas in the GradCAM visualization. Provide both a technical explanation for experts and a simple explanation for non-technical users."
+            
+            # User input for new question
+            new_question = st.text_area("Ask a question about the image:", value=default_question if not st.session_state.chat_history else "", height=100)
+            
+            # Analyze button and Clear Chat button in the same row
+            col1, col2 = st.columns([3, 1])
+            with col1:
+                analyze_button = st.button("🔍 Send Question", type="primary")
+            with col2:
+                clear_button = st.button("🗑️ Clear Chat History")
+            
+            if clear_button:
+                st.session_state.chat_history = []
+                st.experimental_rerun()
+                
+            if analyze_button and new_question:
+                try:
+                    # Add caption info if it's the first question
+                    if not st.session_state.chat_history:
+                        full_question = new_question + caption_text
+                    else:
+                        full_question = new_question
+                    
+                    result = analyze_image_with_llm(
+                        st.session_state.current_image,
+                        st.session_state.current_overlay,
+                        st.session_state.current_face_box,
+                        st.session_state.current_pred_label,
+                        st.session_state.current_confidence,
+                        full_question,
+                        st.session_state.llm_model,
+                        st.session_state.tokenizer,
+                        temperature=temperature,
+                        max_tokens=max_tokens,
+                        custom_instruction=custom_instruction
+                    )
+                    
+                    # Add to chat history
+                    st.session_state.chat_history.append((new_question, result))
+                    
+                    # Display the latest result too
+                    st.success("✅ Analysis complete!")
+                    
+                    # Check if the result contains both technical and non-technical explanations
+                    if "Technical" in result and "Non-Technical" in result:
+                        try:
+                            # Split the result into technical and non-technical sections
+                            parts = result.split("Non-Technical")
+                            technical = parts[0]
+                            non_technical = "Non-Technical" + parts[1]
+                            
+                            # Display in two columns
+                            tech_col, simple_col = st.columns(2)
+                            with tech_col:
+                                st.subheader("Technical Analysis")
+                                st.markdown(technical)
+                            
+                            with simple_col:
+                                st.subheader("Simple Explanation")
+                                st.markdown(non_technical)
+                        except Exception as e:
+                            # Fallback if splitting fails
+                            st.subheader("Analysis Result")
+                            st.markdown(result)
+                    else:
+                        # Just display the whole result
+                        st.subheader("Analysis Result")
+                        st.markdown(result)
+                    
+                    # Rerun to update the chat history display
+                    st.experimental_rerun()
+                    
+                except Exception as e:
+                    st.error(f"Error during LLM analysis: {str(e)}")
+                    
+        elif not hasattr(st.session_state, 'current_image'):
+            st.warning("⚠️ Please upload an image and complete the initial detection first.")
+        else:
+            st.warning("⚠️ Please load the Vision LLM to perform detailed analysis.")
+    
+    # Footer
+    st.markdown("---")
+    st.caption("Advanced Deepfake Image Analyzer with Structured BLIP Captioning")
+
+if __name__ == "__main__":
+    main()