[Python] Tensorflow deployment

My Model


model = Sequential()
model.add(Bidirectional(LSTM(128, return_sequences=True), input_shape=(X.shape[1], X.shape[2])))
model.add(Dropout(0.2))
model.add(Bidirectional(LSTM(50)))
model.add(Dropout(0.2))
model.add(Dense(1)) # Output: 1 nilai (Close price)

model.compile(optimizer='adam', loss='mse', metrics=['mean_absolute_error'])



When I load model

def load_model_and_scalers():
model = load_model("bilstm_model_3.h5",
# custom_objects={"mae": MeanAbsoluteError()}
)
scaler_input = load("scaler_input_3.pkl")
scaler_close = load("scaler_close_3.pkl")
st.text(model.summary())
return model, scaler_input, scaler_close


My Error

TypeError: Could not locate function 'mse'. Make sure custom classes are decorated with `@keras.saving.register_keras_serializable()`. Full object config: {'module': 'keras.metrics', 'class_name': 'function', 'config': 'mse', 'registered_name': 'mse'}
WARNING:tensorflow:From D:\Dokumen\UMJ\Skripsi\Asli\myenv\lib\site-packages\keras\src\backend\common\global_state.py:82: The name tf.reset_default_graph is deprecated. Please use tf.compat.v1.reset_default_graph instead.


Why my code error? because I load model mse default

Continue reading...