getting the shape for the input_shape parameter LSTM

Question

Is there a way to get the shape automatically for the input_shape parameter in LSTM, then to set that shape to the input_shape parameter. I want to be able to have the Recurrent Neural Network to set the input shape automatically, depending on the shape of the data. Thanks.

    dataset_train = pd.read_csv(dataset_path)
    
    training_set = dataset_train.iloc[:, :].values

    from sklearn.preprocessing import MinMaxScaler
    sc = MinMaxScaler(feature_range=(0, 1))
    training_set_scaled = sc.fit_transform(x)

    
    print(len(training_set_scaled))
    print(len(dataset_train))

    X_train = []
    y_train = []
    for i in range(past_days, len(training_set_scaled) - future_days + 1):
        X_train.append(training_set_scaled[i - past_days:i, 0])
        y_train.append(training_set_scaled[i + future_days - 1:i + future_days, 0])
    X_train, y_train = np.array(X_train), np.array(y_train)

    
    ## Building and Training the RNN

    from tensorflow.keras.models import Sequential
    from tensorflow.keras.layers import Dense
    from tensorflow.keras.layers import LSTM
    from tensorflow.keras.layers import Dropout

    ### Initialising the RNN


    regressor = Sequential()

    ### Adding the first LSTM layer and some Dropout regularisation

    regressor.add(LSTM(units=50, input_shape= (?) , return_sequences=True))
    regressor.add(Dropout(0.2))

    ### Adding a second LSTM layer and some Dropout regularisation

    regressor.add(LSTM(units=50, return_sequences=True))
    regressor.add(Dropout(0.2))

    ### Adding a third LSTM layer and some Dropout regularisation

    regressor.add(LSTM(units=50, return_sequences=True))
    regressor.add(Dropout(0.2))

    ### Adding a fourth LSTM layer and some Dropout regularisation

    regressor.add(LSTM(units=50))
    regressor.add(Dropout(0.2))

    ### Adding the output layer

    regressor.add(Dense(units=1))

    ### Compiling the RNN

    regressor.compile(optimizer='adam', loss='mean_squared_error')

Answer 1

If you know what data you're going to be training/testing the model on, this shouldn't be a challenge. You just have to pick one data point from your dataset. If your data is in NumPy/Tensor/Pandas, you can get it's shape using x.shape() . You don't have to worry about the batch size, this is something that Keras will automatically pick on.

Answer 2

I generally use input_shape=X_train.shape[1:] . That is assuming your input shape is correct, and can pass through the neural net.