Update app.py

app.py

@@ -8,51 +8,37 @@ from tensorflow.keras.applications.xception import preprocess_input as xcp_pre
 from tensorflow.keras.applications.efficientnet import preprocess_input as eff_pre
 from huggingface_hub import hf_hub_download
 
-# Download and load models
-xcp_path = hf_hub_download(repo_id="Zeyadd-Mostaffa/deepfake-image-detector", filename="xception_model.h5")
-eff_path = hf_hub_download(repo_id="Zeyadd-Mostaffa/deepfake-image-detector", filename="efficientnet_model.h5")
+# Load models from Hugging Face Hub
+xcp_path = hf_hub_download(repo_id="Zeyadd-Mostaffa/deepfake-image-detector_final", filename="xception_model.h5")
+eff_path = hf_hub_download(repo_id="Zeyadd-Mostaffa/deepfake-image-detector_final", filename="efficientnet_model.h5")
 xcp_model = load_model(xcp_path)
 eff_model = load_model(eff_path)
 
-def predict(image_path):
-    # Read the image from file path
+def predict(image_path):  # receives file path (not array)
     image = cv2.imread(image_path)
-
-    # Check if loading failed
     if image is None:
-        raise ValueError("Failed to load image. Make sure the input is an image file.")
+        return "Invalid image"
 
-    # Convert BGR to RGB (OpenCV loads images in BGR)
     image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
 
-    # Resize for each model
     xcp_img = cv2.resize(image, (299, 299))
     eff_img = cv2.resize(image, (224, 224))
 
-    # Preprocess
     xcp_tensor = xcp_pre(xcp_img.astype(np.float32))[np.newaxis, ...]
     eff_tensor = eff_pre(eff_img.astype(np.float32))[np.newaxis, ...]
 
-    # Predict
     xcp_pred = xcp_model.predict(xcp_tensor, verbose=0).flatten()[0]
     eff_pred = eff_model.predict(eff_tensor, verbose=0).flatten()[0]
-    avg_pred = (xcp_pred + eff_pred) / 2
 
+    avg_pred = (xcp_pred + eff_pred) / 2
     label = "Real" if avg_pred > 0.5 else "Fake"
-
-    return {"result": {
-    "label": label,
-    "average": round(avg_pred, 3),
-    "xception": round(xcp_pred, 3),
-    "efficientnet": round(eff_pred, 3)
-        }}
-
+    return label
 
 iface = gr.Interface(
     fn=predict,
-    inputs=gr.Image(type="filepath"),
-    outputs=gr.Label(),  # just returns a string like "Real"
+    inputs=gr.Image(type="filepath", label="image_path"),  # <- This must match backend call
+    outputs="text",
+    allow_flagging="never"
 )
 
-
-iface.launch()
+iface.launch()