Deep Learning By Example

Training the model

Now, let's kick off the training process by providing the inputs and outputs to the built model and then use the optimizer to train the network. Don't forget that we need to use the previous state while making predictions for the current state. Thus, we need to pass the output state back to the network so that it can be used during the prediction of the next input.

Let's provide initial values for our hyperparameters (you can tune them afterwards depending on the dataset you are using to train this architecture):

batch_size = 100        # Sequences per batchnum_steps = 100         # Number of sequence steps per batchlstm_size = 512         # Size of hidden layers in LSTMsnum_layers = 2          # Number of LSTM layerslearning_rate = 0.001 # Learning rate ...