Initial state for bidirectional GRU

1

Hi all,

The the usage of initial states for bidirectional GRU/LSTM/RNN seems ambiguous to me in the official documentation.

h_0 (num_layers * num_directions, batch, hidden_size): tensor containing the initial hidden state for each element in the batch.

Can I assume that [:num_layers, batch, hidden_size] of the initial state are for the forward GRU and the rest of the initial state are for the backward GRU?

Thanks!