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
Hello,
I have used
self.intra_rnn = keras.layers.Bidirectional(keras.layers.CuDNNLSTM(units=self.numUnits//2, return_sequences=True))
and
self.inter_rnn = keras.layers.CuDNNLSTM(units=self.numUnits, return_sequences=True)
during the training process, which significantly increases the training speed.
However, is it possible to use LSTM using inference to run on cpu?
If so, what would be the LSTM parameters? Using the below may give different result compared to CuDNNLSTM?
keras.layers.LSTM(units=self.numUnits//2, return_sequences=True,implementation = 2,recurrent_activation = 'hard_sigmoid')
The text was updated successfully, but these errors were encountered:
In TenosrFlow 2.X the requirements to use the cuDNN implementation are:
activation == tanh
recurrent_activation == sigmoid
recurrent_dropout == 0
unroll is False
use_bias is True
Inputs are not masked or strictly right padded.
implementation == 2,
I haven't compared the code of LSTM in tf1 with tf2. Maybe they are a little different. If you use the above parameters, be careful of the alignment when loading the weights.
Hello,
I have used
self.intra_rnn = keras.layers.Bidirectional(keras.layers.CuDNNLSTM(units=self.numUnits//2, return_sequences=True))
and
self.inter_rnn = keras.layers.CuDNNLSTM(units=self.numUnits, return_sequences=True)
during the training process, which significantly increases the training speed.
However, is it possible to use LSTM using inference to run on cpu?
If so, what would be the LSTM parameters? Using the below may give different result compared to CuDNNLSTM?
keras.layers.LSTM(units=self.numUnits//2, return_sequences=True,implementation = 2,recurrent_activation = 'hard_sigmoid')
The text was updated successfully, but these errors were encountered: