Hi, the first example contains this line:
new_states = stacked_rnn.forward(x, prev_hiddens, dropout)
But there is no mention of stacked_rrn variable anywhere.
Also there is no mention of dynamics from line:
return [dynamics(x, new_states[-1])] + new_states[:-1]
Hi, the first example contains this line:
new_states = stacked_rnn.forward(x, prev_hiddens, dropout)
But there is no mention of stacked_rrn variable anywhere. Also there is no mention of dynamics from line:
return [dynamics(x, new_states[-1])] + new_states[:-1]