TFLiteLSTMCell - LostTech.TensorFlow Documentation

Type TFLiteLSTMCell

Namespace tensorflow.lite.experimental.nn

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

This is used only for TfLite, it provides hints and it also makes the variables in the desired for the tflite ops (transposed and seaparated).

The default non-peephole implementation is based on:

https://pdfs.semanticscholar.org/1154/0131eae85b2e11d53df7f1360eeb6476e7f4.pdf

Felix Gers, Jurgen Schmidhuber, and Fred Cummins. "Learning to forget: Continual prediction with LSTM." IET, 850-855, 1999.

The peephole implementation is based on:

https://research.google.com/pubs/archive/43905.pdf

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 tf.contrib.rnn.LSTMBlockCell and tf.contrib.rnn.LSTMBlockFusedCell for better performance on CPU.

Methods

NewDyn

Properties

Public static methods

TFLiteLSTMCell NewDyn(object num_units, ImplicitContainer<T> use_peepholes, object cell_clip, object initializer, object num_proj, object proj_clip, object num_unit_shards, object num_proj_shards, ImplicitContainer<T> forget_bias, ImplicitContainer<T> state_is_tuple, object activation, object reuse, object name, object dtype)

Initialize the parameters for an LSTM cell.

Parameters

object num_units: int, The number of units in the LSTM cell.
ImplicitContainer<T> use_peepholes: bool, set True to enable diagonal/peephole connections.
object cell_clip: (optional) A float value, 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.
object num_proj: (optional) int, The output dimensionality for the projection matrices. If None, no projection is performed.
object proj_clip: (optional) A float value. If `num_proj > 0` and `proj_clip` is provided, then the projected values are clipped elementwise to within `[-proj_clip, proj_clip]`.
object num_unit_shards: Deprecated, will be removed by Jan. 2017. Use a variable_scope partitioner instead.
object num_proj_shards: Deprecated, will be removed by Jan. 2017. Use a variable_scope partitioner instead.
ImplicitContainer<T> forget_bias: Biases of the forget gate are initialized by default to 1 in order to reduce the scale of forgetting at the beginning of the training. Must set it manually to `0.0` when restoring from CudnnLSTM trained checkpoints.
ImplicitContainer<T> state_is_tuple: If True, accepted and returned states are 2-tuples of the `c_state` and `m_state`. If False, they are concatenated along the column axis. This latter behavior will soon be deprecated.
object activation: Activation function of the inner states. Default: `tanh`.
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.
object 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.
object dtype: Default dtype of the layer (default of `None` means use the type of the first input). Required when `build` is called before `call`. When restoring from CudnnLSTM-trained checkpoints, use `CudnnCompatibleLSTMCell` instead.

Public properties

PythonFunctionContainer activity_regularizer get; set;

object activity_regularizer_dyn get; set;

bool built get; set;

object cell_bias get; set;

object cell_to_cell_w get; set;

object cell_to_forget_w get; set;

object cell_to_input_w get; set;

object cell_to_output_w get; set;

object dtype get;

object dtype_dyn get;

bool dynamic get;

object dynamic_dyn get;

object forget_bias get; set;

object graph get;

object graph_dyn get;

IList<Node> inbound_nodes get;

object inbound_nodes_dyn get;

IList<object> input get;

object input_bias get; set;

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;

object input_to_cell_w get; set;

object input_to_forget_w get; set;

object input_to_input_w get; set;

object input_to_output_w 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_bias get; set;

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;