You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
lstm_cell.state_size is an Integer or TensorShape, what does "for dim in lstm_cell.state_size" mean? And I don't know how "state_update_op = tf.assign(init_states[i], new_state)" works, since you assign init_states using "tf.zeros([self._max_batch_size, dim]" in L548.
The text was updated successfully, but these errors were encountered:
bilm-tf/bilm/model.py
Line 547 in 7cffee2
lstm_cell.state_size is an Integer or TensorShape, what does "for dim in lstm_cell.state_size" mean? And I don't know how "state_update_op = tf.assign(init_states[i], new_state)" works, since you assign init_states using "tf.zeros([self._max_batch_size, dim]" in L548.
The text was updated successfully, but these errors were encountered: