Keras LSTM training. How to shape my input data?

Question

I have a dataset of 3000 observations. Each observation consists of 3 timeseries of length 200 samples. As the output I have 5 class labels.

So I build train as test sets as follows:

test_split = round(num_samples * 3 / 4)
X_train = X_all[:test_split, :, :] # Start upto just before test_split
y_train = y_all[:test_split]
X_test = X_all[test_split:, :, :] # From test_split to end
y_test = y_all[test_split:]

# Print shapes and class labels
print(X_train.shape)
print(y_train.shape)


> (2250, 200, 3)
> (22250, 5)

I build my network using Keras functional API:

from keras.models import  Model
from keras.layers import Dense, Activation, Input, Dropout, concatenate
from keras.layers.recurrent import LSTM
from keras.constraints import maxnorm
from keras.optimizers import SGD
from keras.callbacks import EarlyStopping

series_len = 200
num_RNN_neurons = 64
ch1 = Input(shape=(series_len, 1), name='ch1')
ch2 = Input(shape=(series_len, 1), name='ch2')
ch3 = Input(shape=(series_len, 1), name='ch3')

ch1_layer = LSTM(num_RNN_neurons, return_sequences=False)(ch1)
ch2_layer = LSTM(num_RNN_neurons, return_sequences=False)(ch2)
ch3_layer = LSTM(num_RNN_neurons, return_sequences=False)(ch3)


visible = concatenate([
    ch1_layer,
    ch2_layer,
    ch3_layer])


hidden1 = Dense(30, activation='linear', name='weighted_average_channels')(visible)
output = Dense(num_classes, activation='softmax')(hidden1)

model = Model(inputs= [ch1, ch2, ch3], outputs=output)

# Compile model
model.compile(loss='categorical_crossentropy', optimizer=SGD(), metrics=['accuracy'])
monitor = EarlyStopping(monitor='val_loss', min_delta=1e-4, patience=5, verbose=1, mode='auto')

Then, I try to fit the model:

# Fit the model
model.fit(X_train, y_train, 
          epochs=epochs, 
          batch_size=batch_size,
          validation_data=(X_test, y_test),
          callbacks=[monitor],
          verbose=1)

and I get the following error:

ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 3 array(s), but instead got the following list of 1 arrays...

How should I reshape my data, to solve the issue?

Answer 1

You magically assume a single input with 3 time series X_train will split into 4 channels and be assigned to different inputs. Well this doesn't happen and that is what the error is complaining about. You have 1 input:

ch123_in = Input(shape=(series_len, 3), name='ch123')
latent = LSTM(num_RNN_neurons)(ch123_in)
hidden1 = Dense(30, activation='linear', name='weighted_average_channels')(latent)

By merging the series together into single LSTM, the model might pickup relations across time series as well. Now your target shape has to be y_train.shape == (2250, 5), the first dimension must match X_train.shape[0].

Another point is you have Dense layer with linear activation, that is almost useless as it doesn't provide any non-linearity. You might want to use a non-linear activation function like relu.