tf.contrib.seq2seq.Helper

Interface for implementing sampling in seq2seq decoders.

Helper instances are used by BasicDecoder.

Attributes
`batch_size`	Batch size of tensor returned by `sample`. Returns a scalar int32 tensor.
`sample_ids_dtype`	DType of tensor returned by `sample`. Returns a DType.
`sample_ids_shape`	Shape of tensor returned by `sample`, excluding the batch dimension. Returns a `TensorShape`.

Attributes

batch_size

Batch size of tensor returned by sample.

Returns a scalar int32 tensor.

sample_ids_dtype

DType of tensor returned by sample.

Returns a DType.

sample_ids_shape

Shape of tensor returned by sample, excluding the batch dimension.

Returns a TensorShape.

@abc.abstractmethod
initialize(
    name=None
)

Returns (initial_finished, initial_inputs).

@abc.abstractmethod
next_inputs(
    time, outputs, state, sample_ids, name=None
)

Returns (finished, next_inputs, next_state).

@abc.abstractmethod
sample(
    time, outputs, state, name=None
)

Returns sample_ids.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2020-10-01 UTC.