|
final_dist, s_t_1, c_t_1, attn_dist, p_gen, next_coverage = self.model.decoder(y_t_1, s_t_1, |
Will there be duplicated computation with LSTM? e.g. given an input [w1, w2, w3, w4, ... , wn], all the prefixes will be decoded by LSTM. Why not using LSTM cell?
pointer_summarizer/training_ptr_gen/train.py
Line 90 in 83e6a2e
Will there be duplicated computation with LSTM? e.g. given an input [w1, w2, w3, w4, ... , wn], all the prefixes will be decoded by LSTM. Why not using LSTM cell?