What can I use instead of tf.contrib.rnn.LayerNormBasicLSTM in TensorFlow 2.x?
Question
The tf.contrib.rnn.LayerNormBasicLSTM is deprecated in TensorFlow 2.x. What is equivalent to this code or what can I use instead of it in TensorFlow 2.x?
1 answers
solution1
0 ACCPTED 2021-02-10 11:39:37
In Tensorflow 2.x, you can use
tf.compat.v1.nn.rnn_cell.LSTMCell
For better performance, alternative is
tf.keras.layers.LSTMCell
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.
Related Question
Tensorflow 2.x - tf.contrib.layers.variance_scaling_initializer()
what exactly does 'tf.contrib.rnn.DropoutWrapper'' in tensorflow do? ( three citical questions)
Can tensorflow 2.x be run on the latest Python?
tf.contrib.layers.fully_connected() in Tensorflow 2?
tf.contrib does not exist in tensorflow 2.0 Should I download my version of tensorflow?
What is the equivalent of PyTorch's BoolTensor in Tensorflow 2.x?
Unable to import tensorflow 2.x, python 3.6
Upgrade Tensorflow 1.x code to Tensorflow 2.x code
Tensorflow : Understanding tf.contrib.seq2seq.BasicDecoder
What is cuDNN implementation of rnn cells in Tensorflow
Related Tags