Update app.py

app.py

@@ -24,31 +24,33 @@ def extract_face(image):
         return None
     x, y, w, h = faces[0]['box']
     x, y = max(0, x), max(0, y)
-    face = image[y:y+h, x:x+w]
-    return face
+    return image[y:y+h, x:x+w]
 
 def predict(image):
     face = extract_face(image)
     if face is None:
         return "No face detected", None
 
-    # Prepare for Xception
+    # Xception
     xcp_img = cv2.resize(face, (299, 299))
     xcp_tensor = xcp_pre(xcp_img.astype(np.float32))[np.newaxis, ...]
     xcp_pred = xcp_model.predict(xcp_tensor, verbose=0).flatten()[0]
 
-    # Prepare for EfficientNet
+    # EfficientNet
     eff_img = cv2.resize(face, (224, 224))
     eff_tensor = eff_pre(eff_img.astype(np.float32))[np.newaxis, ...]
     eff_pred = eff_model.predict(eff_tensor, verbose=0).flatten()[0]
 
-    # Ensemble average
+    # Ensemble
     avg_pred = (xcp_pred + eff_pred) / 2
-
-    # ✅ Important fix: if label "real" = 1, fake = 0, prediction > 0.5 = real
     label = "Real" if avg_pred > 0.5 else "Fake"
 
-    return label, face
+    # Log probabilities
+    print(f"Xception: {xcp_pred:.4f}, EfficientNetB4: {eff_pred:.4f}, Ensemble Avg: {avg_pred:.4f}")
+
+    # Return label with confidence
+    result = f"{label} (Avg: {avg_pred:.3f}, XCP: {xcp_pred:.3f}, EFF: {eff_pred:.3f})"
+    return result, face
 
 interface = gr.Interface(
     fn=predict,