LostTech.TensorFlow : API Documentation

Type Decoder

Namespace tensorflow.contrib.seq2seq

Parent PythonObjectContainer

Interfaces IDecoder

An RNN Decoder abstract interface object.

Concepts used by this interface: - `inputs`: (structure of) tensors and TensorArrays that is passed as input to the RNNCell composing the decoder, at each time step. - `state`: (structure of) tensors and TensorArrays that is passed to the RNNCell instance as the state. - `finished`: boolean tensor telling whether each sequence in the batch is finished. - `outputs`: Instance of BasicDecoderOutput. Result of the decoding, at each time step.

Properties

Public properties

object batch_size get;

The batch size of input values.

object batch_size_dyn get;

The batch size of input values.

object output_dtype get;

A (possibly nested tuple of...) dtype[s].

object output_dtype_dyn get;

A (possibly nested tuple of...) dtype[s].

object output_size get;

A (possibly nested tuple of...) integer[s] or `TensorShape` object[s].

object output_size_dyn get;

A (possibly nested tuple of...) integer[s] or `TensorShape` object[s].

object PythonObject get;

bool tracks_own_finished get;

Describes whether the Decoder keeps track of finished states.

Most decoders will emit a true/false `finished` value independently at each time step. In this case, the `dynamic_decode` function keeps track of which batch entries are already finished, and performs a logical OR to insert new batches to the finished set.

Some decoders, however, shuffle batches / beams between time steps and `dynamic_decode` will mix up the finished state across these entries because it does not track the reshuffle across time steps. In this case, it is up to the decoder to declare that it will keep track of its own finished state by setting this property to `True`.

object tracks_own_finished_dyn get;

Describes whether the Decoder keeps track of finished states.

Most decoders will emit a true/false `finished` value independently at each time step. In this case, the `dynamic_decode` function keeps track of which batch entries are already finished, and performs a logical OR to insert new batches to the finished set.

Some decoders, however, shuffle batches / beams between time steps and `dynamic_decode` will mix up the finished state across these entries because it does not track the reshuffle across time steps. In this case, it is up to the decoder to declare that it will keep track of its own finished state by setting this property to `True`.