|View source on GitHub|
Long short-term memory unit (LSTM) recurrent network cell. (deprecated)
tf.compat.v1.lite.experimental.nn.TFLiteLSTMCell( num_units, use_peepholes=False, cell_clip=None, initializer=None, num_proj=None, proj_clip=None, num_unit_shards=None, num_proj_shards=None, forget_bias=1.0, state_is_tuple=True, activation=None, reuse=None, name=None, dtype=None )
This is used only for TfLite, it provides hints and it also makes the variables in the desired for the tflite ops (transposed and separated).
The default non-peephole implementation is based on:
Felix Gers, Jurgen Schmidhuber, and Fred Cummins. "Learning to forget: Continual prediction with LSTM." IET, 850-855, 1999.
The peephole implementation is based on:
Hasim Sak, Andrew Senior, and Francoise Beaufays. "Long short-term memory recurrent neural network architectures for large scale acoustic modeling." INTERSPEECH, 2014.
The class uses optional peep-hole connections, optional cell clipping, and an optional projection layer.
Note that this cell is not optimized for performance. Please use
tf.contrib.cudnn_rnn.CudnnLSTM for better performance on GPU, or