Update app.py

app.py

@@ -19,24 +19,37 @@ def load_and_preprocess_image(img, target_size=(256, 256)):
 
 # Step 4: Function to make predictions
 def predict_image(img):
-    img_array = load_and_preprocess_image(img)
-    prediction = model.predict(img_array)
-
-    # Determine output shape and extract confidence
-    if prediction.shape[-1] == 1:
-        prob_real = prediction[0][0]
-    elif prediction.shape[-1] == 2:
-        prob_real = prediction[0][1]  # Assuming second index = "real"
-    else:
-        return "Model output shape not recognized.", "Cannot compute prediction."
-
-    real_confidence = prob_real * 100
-    fake_confidence = (1 - prob_real) * 100
-    result_label = "Real" if real_confidence > fake_confidence else "Fake"
-
-    result_text = f"The model predicts this image is '{result_label}' with {max(real_confidence, fake_confidence):.2f}% confidence."
-    explanation = f"Real Confidence: {real_confidence:.2f}% | Fake Confidence: {fake_confidence:.2f}%"
-    return result_text, explanation
+    print("Image received.")  # Confirm function is triggered
+
+    try:
+        img_array = load_and_preprocess_image(img)
+        print("Image shape:", img_array.shape)
+
+        prediction = model.predict(img_array)
+        print("Raw prediction:", prediction)
+
+        # Determine output shape
+        if prediction.shape[-1] == 1:
+            prob_real = prediction[0][0]
+        elif prediction.shape[-1] == 2:
+            prob_real = prediction[0][1]  # assumes index 1 = "real"
+        else:
+            print("Unexpected model output shape.")
+            return "Error: Unrecognized output shape.", ""
+
+        real_confidence = prob_real * 100
+        fake_confidence = (1 - prob_real) * 100
+        result_label = "Real" if real_confidence > fake_confidence else "Fake"
+
+        result_text = f"The model predicts this image is '{result_label}' with {max(real_confidence, fake_confidence):.2f}% confidence."
+        explanation = f"Real Confidence: {real_confidence:.2f}% | Fake Confidence: {fake_confidence:.2f}%"
+
+        print("Prediction result:", result_text)
+        return result_text, explanation
+
+    except Exception as e:
+        print("Error during prediction:", str(e))
+        return "An error occurred during prediction.", str(e)
 
 # Step 5: Define the Gradio interface
 interface = gr.Interface(