|View source on GitHub|
Basic LSTM recurrent network cell.
The implementation is based on: http://arxiv.org/abs/1409.2329.
forget_bias (default: 1) to the biases of the forget gate in order to
reduce the scale of forgetting in the beginning of the training.
rnn_cell_impl.LSTMCell, this is a monolithic op and should be much
faster. The weight and bias matrices should be compatible as long as the
variable scope matches.
__init__( num_units, forget_bias=1.0, cell_clip=None, use_peephole=False, dtype=None, reuse=None, name='lstm_cell' )
Initialize the basic LSTM cell.
num_units: int, The number of units in the LSTM cell.
forget_bias: float, The bias added to forget gates (see above).
cell_clip: An optional
float. Defaults to
use_peephole: Whether to use peephole connections or not.
dtype: the variable dtype of this layer. Default to tf.float32.
reuse: (optional) boolean describing whether to reuse variables in an existing scope. If not
True, and the existing scope already has the given variables, an error is raised.
name: String, the name of the layer. Layers with the same name will share weights, but to avoid mistakes we require reuse=True in such cases. By default this is "lstm_cell", for variable-name compatibility with
When restoring from CudnnLSTM-trained checkpoints, must use CudnnCompatibleLSTMBlockCell instead.
get_initial_state( inputs=None, batch_size=None, dtype=None )
zero_state( batch_size, dtype )
Return zero-filled state tensor(s).
batch_size: int, float, or unit Tensor representing the batch size.
dtype: the data type to use for the state.
state_size is an int or TensorShape, then the return value is a
N-D tensor of shape
[batch_size, state_size] filled with zeros.
state_size is a nested list or tuple, then the return value is
a nested list or tuple (of the same structure) of
2-D tensors with
[batch_size, s] for each s in