parameters of bidirectional LSTM

Question

I am new to LSTMs and also bidirectional lstms. I am trying to implement a model described in a scientific article. It says that the bilstm model has a layer size of 200 and number of hidden layers is 2. I think for the hidden layers I have to add 2 bilstm layers top of each other. But I can not understand what author means by layer size. Is this same as units parameter for keras.layers.lstm?

Answer 1

Yes, the 'layer size' is the hidden dimension within the LSTM—the size of the hidden state. The Keras toolkit calls that units in keras.layers.lstm.