tf.contrib.rnn.LSTMBlockCell

class tf.contrib.rnn.LSTMBlockCell

See the guide: RNN and Cells (contrib) > Core RNN Cell wrappers (RNNCells that wrap other RNNCells)

Basic LSTM recurrent network cell.

The implementation is based on: http://arxiv.org/abs/1409.2329.

We add 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.

Unlike core_rnn_cell.LSTMCell, this is a monolithic op and should be much faster. The weight and bias matrixes should be compatible as long as the variable scope matches.

Properties

output_size

state_size

Methods

__init__(num_units, forget_bias=1.0, use_peephole=False)

Initialize the basic LSTM cell.

Args:

• num_units: int, The number of units in the LSTM cell.
• forget_bias: float, The bias added to forget gates (see above).
• use_peephole: Whether to use peephole connections or not.

zero_state(batch_size, dtype)

Return zero-filled state tensor(s).

Args:

• batch_size: int, float, or unit Tensor representing the batch size.
• dtype: the data type to use for the state.

Returns:

If state_size is an int or TensorShape, then the return value is a N-D tensor of shape [batch_size x state_size] filled with zeros.

If 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 the shapes [batch_size x s] for each s in state_size.

Defined in tensorflow/contrib/rnn/python/ops/lstm_ops.py.