Update app.py

app.py

@@ -1,50 +1,54 @@
-import gradio as gr
-import tempfile
+import streamlit as st
 import cv2
+import os
+import tempfile
+import numpy as np
 from prediction import Prediction
+from PIL import Image
 
-# Initialize the predictor
-predictor = Prediction()
+st.set_page_config(page_title="Deepfake Detection", layout="wide")
+st.title("🔍 Deepfake Video Detector with Grad-CAM Overlay")
 
-# Define your inference function
-def detect_deepfake(video_file, sequence_length=None):
-    try:
-        # Save the uploaded video to a temporary file
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as temp_video:
-            temp_video.write(video_file.read())
-            temp_video_path = temp_video.name
+st.markdown(
+    "Upload a video file below to analyze it for deepfakes. The model will detect faces, "
+    "analyze the content, and display the result with a Grad-CAM overlay for interpretability."
+)
 
-        # Run prediction
-        prediction_str, explanation_image, details = predictor.predict(
-            temp_video_path, sequence_length
-        )
+# File uploader
+uploaded_file = st.file_uploader("📤 Upload a video file (e.g., MP4, AVI)", type=["mp4", "avi", "mov"])
 
-        # Return prediction and image
-        explanation_img = None
-        if explanation_image is not None:
-            explanation_img = cv2.cvtColor(explanation_image, cv2.COLOR_BGR2RGB)
+# Prediction button
+if uploaded_file is not None:
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as tmp_file:
+        tmp_file.write(uploaded_file.read())
+        tmp_file_path = tmp_file.name
 
-        return prediction_str, explanation_img, str(details)
+    st.info("⏳ Processing video... Please wait.")
+    
+    try:
+        # Initialize prediction class
+        predictor = Prediction()
+        
+        # Make prediction
+        prediction_result, gradcam_image, classification_details = predictor.predict(tmp_file_path)
+
+        # Display prediction
+        st.subheader("🧠 Prediction Result")
+        st.success(prediction_result)
+
+        # Display detailed classification info
+        if classification_details:
+            st.subheader("📊 Classification Details")
+            st.json(classification_details)
+
+        # Display Grad-CAM visualization
+        if gradcam_image is not None:
+            st.subheader("🔥 Grad-CAM Visualization (Middle Frame)")
+            st.image(gradcam_image, channels="BGR", caption="Grad-CAM Overlay")
 
     except Exception as e:
-        return f"Error: {str(e)}", None, ""
-
-# Gradio UI
-demo = gr.Interface(
-    fn=detect_deepfake,
-    inputs=[
-        gr.File(label="Upload Video (.mp4)", file_types=[".mp4"]),
-        gr.Number(label="Sequence Length (Optional)", value=None),
-    ],
-    outputs=[
-        gr.Textbox(label="Prediction"),
-        gr.Image(label="Explanation Image"),
-        gr.Textbox(label="Details"),
-    ],
-    title="Deepdetect",
-    description="Upload a video to detect deepfakes using Face2Face, FaceSwap, FaceShifter, and NeuralTextures models.",
-    allow_flagging="never",
-)
+        st.error(f"❌ An error occurred during prediction: {e}")
 
-if __name__ == "__main__":
-    demo.launch()
+    finally:
+        # Clean up temp file
+        os.remove(tmp_file_path)