GridLSTMCell - LostTech.TensorFlow Documentation

Type GridLSTMCell

Namespace tensorflow.contrib.rnn

Parent RNNCell

Grid Long short-term memory unit (LSTM) recurrent network cell.

The default is based on: Nal Kalchbrenner, Ivo Danihelka and Alex Graves "Grid Long Short-Term Memory," Proc. ICLR 2016. http://arxiv.org/abs/1507.01526

When peephole connections are used, the implementation is based on: Tara N. Sainath and Bo Li "Modeling Time-Frequency Patterns with LSTM vs. Convolutional Architectures for LVCSR Tasks." submitted to INTERSPEECH, 2016.

The code uses optional peephole connections, shared_weights and cell clipping.

Methods

NewDyn

Properties

Public static methods

GridLSTMCell NewDyn(object num_units, ImplicitContainer<T> use_peepholes, ImplicitContainer<T> share_time_frequency_weights, object cell_clip, object initializer, ImplicitContainer<T> num_unit_shards, ImplicitContainer<T> forget_bias, object feature_size, object frequency_skip, object num_frequency_blocks, object start_freqindex_list, object end_freqindex_list, ImplicitContainer<T> couple_input_forget_gates, ImplicitContainer<T> state_is_tuple, object reuse)

Initialize the parameters for an LSTM cell.

Parameters

object num_units: int, The number of units in the LSTM cell
ImplicitContainer<T> use_peepholes: (optional) bool, default False. Set True to enable diagonal/peephole connections.
ImplicitContainer<T> share_time_frequency_weights: (optional) bool, default False. Set True to enable shared cell weights between time and frequency LSTMs.
object cell_clip: (optional) A float value, default None, if provided the cell state is clipped by this value prior to the cell output activation.
object initializer: (optional) The initializer to use for the weight and projection matrices, default None.
ImplicitContainer<T> num_unit_shards: (optional) int, default 1, How to split the weight matrix. If > 1, the weight matrix is stored across num_unit_shards.
ImplicitContainer<T> forget_bias: (optional) float, default 1.0, The initial bias of the forget gates, used to reduce the scale of forgetting at the beginning of the training.
object feature_size: (optional) int, default None, The size of the input feature the LSTM spans over.
object frequency_skip: (optional) int, default None, The amount the LSTM filter is shifted by in frequency.
object num_frequency_blocks: [required] A list of frequency blocks needed to cover the whole input feature splitting defined by start_freqindex_list and end_freqindex_list.
object start_freqindex_list: [optional], list of ints, default None, The starting frequency index for each frequency block.
object end_freqindex_list: [optional], list of ints, default None. The ending frequency index for each frequency block.
ImplicitContainer<T> couple_input_forget_gates: (optional) bool, default False, Whether to couple the input and forget gates, i.e. f_gate = 1.0 - i_gate, to reduce model parameters and computation cost.
ImplicitContainer<T> state_is_tuple
object 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.

Public properties

PythonFunctionContainer activity_regularizer get; set;

object activity_regularizer_dyn get; set;

bool built get; set;

object dtype get;

object dtype_dyn get;

bool dynamic get;

object dynamic_dyn get;

object graph get;

object graph_dyn get;

IList<Node> inbound_nodes get;

object inbound_nodes_dyn get;

IList<object> input get;

object input_dyn get;

object input_mask get;

object input_mask_dyn get;

IList<object> input_shape get;

object input_shape_dyn get;

object input_spec get; set;

object input_spec_dyn get; set;

IList<object> losses get;

object losses_dyn get;

IList<object> metrics get;

object metrics_dyn get;

object name get;

object name_dyn get;

object name_scope get;

object name_scope_dyn get;

IList<object> non_trainable_variables get;

object non_trainable_variables_dyn get;

IList<object> non_trainable_weights get;

object non_trainable_weights_dyn get;

IList<object> outbound_nodes get;

object outbound_nodes_dyn get;

IList<object> output get;

object output_dyn get;

object output_mask get;

object output_mask_dyn get;

object output_shape get;

object output_shape_dyn get;

object output_size get;

Integer or TensorShape: size of outputs produced by this cell.

object output_size_dyn get;

Integer or TensorShape: size of outputs produced by this cell.

object PythonObject get;

object rnncell_scope get; set;

string scope_name get;

object scope_name_dyn get;

object state_size get;

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.

object state_size_dyn get;