tf.contrib.rnn.IndyLSTMCell

Basic IndyLSTM recurrent network cell.

Inherits From: LayerRNNCell

tf.contrib.rnn.IndyLSTMCell(
    num_units, forget_bias=1.0, activation=None, reuse=None,
    kernel_initializer=None, bias_initializer=None, name=None, dtype=None
)

Based on IndRNNs (https://arxiv.org/abs/1803.04831) and similar to BasicLSTMCell, yet with the $U_f$, $U_i$, $U_o$ and $U_c$ matrices in the regular LSTM equations replaced by diagonal matrices, i.e. a Hadamard product with a single vector:

$$f_t = \sigma_g\left(W_f x_t + u_f \circ h_{t-1} + b_f\right)$$

$$i_t = \sigma_g\left(W_i x_t + u_i \circ h_{t-1} + b_i\right)$$

$$o_t = \sigma_g\left(W_o x_t + u_o \circ h_{t-1} + b_o\right)$$

$$c_t = f_t \circ c_{t-1} + i_t \circ \sigma_c\left(W_c x_t + u_c \circ h_{t-1} + b_c\right)$$

where $\circ$ denotes the Hadamard operator. This means that each IndyLSTM node sees only its own state $h$ and $c$, as opposed to seeing all states in the same layer.

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.

It does not allow cell clipping, a projection layer, and does not use peep-hole connections: it is the basic baseline.

For a detailed analysis of IndyLSTMs, see https://arxiv.org/abs/1903.08023

Args
num_units	int, The number of units in the LSTM cell.
forget_bias	float, The bias added to forget gates (see above). Must set to 0.0 manually when restoring from CudnnLSTM-trained checkpoints.
activation	Activation function of the inner states. Default: tanh.
reuse	(optional) Python 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.
kernel_initializer	(optional) The initializer to use for the weight matrix applied to the inputs.
bias_initializer	(optional) The initializer to use for the bias.
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.
dtype	Default dtype of the layer (default of None means use the type of the first input). Required when build is called before call.

Attributes
graph	DEPRECATED FUNCTION Warning: THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Stop using this property because tf.layers layers no longer track their graph.
output_size	Integer or TensorShape: size of outputs produced by this cell.
scope_name
state_size	size(s) of state(s) used by this cell. It can be represented by an Integer, a TensorShape or a tuple of Integers or TensorShapes.

Methods

get_initial_state

View source

get_initial_state(
    inputs=None, batch_size=None, dtype=None
)

zero_state

View source

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, 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, s] for each s in state_size.