keras-layer-normalization-rnn icon indicating copy to clipboard operation
keras-layer-normalization-rnn copied to clipboard

Published 20 hours ago • verified publisher icon Binbose

train timecost per epoch

Open rcx986635 opened this issue 5 years ago • 0 comments

@Binbose, firstly,thank u for your sharing project. I try the GRU_LN, with layer_to_normalize=("input_gate", "input_recurrent", "recurrent_gate" , "recurrent_recurrent") and normalize_seperately=False, but I found that the training timecost takes twice as before per epoch. Is there any solutions for this? Looking forward to your reply.

rcx986635 avatar Jan 15 '20 06:01 rcx986635