bi-att-flow
bi-att-flow copied to clipboard
Question: why use TensorFlow BasicLSTMCell instead of other kind of LSTM cell in TF?
Just curious, why use BasicLSTMCell
instead of other "faster" LSTM cell in TF like:
tf.contrib.rnn.LSTMBlockCellor
tf.contrib.rnn.LSTMBlockFusedCell` ?
I am not really a machine learning expert, just thought why not using a faster LSTM cell in TF. I am referring to this post online: https://returnn.readthedocs.io/en/latest/tf_lstm_benchmark.html