TensorFlow 2.0 RC is available Learn more

tf.contrib.seq2seq.GreedyEmbeddingHelper

View source on GitHub

Class GreedyEmbeddingHelper

A helper for use during inference.

Inherits From: Helper

Uses the argmax of the output (treated as logits) and passes the result through an embedding layer to get the next input.

__init__

View source

__init__(
    embedding,
    start_tokens,
    end_token
)

Initializer.

Args:

  • embedding: A callable that takes a vector tensor of ids (argmax ids), or the params argument for embedding_lookup. The returned tensor will be passed to the decoder input.
  • start_tokens: int32 vector shaped [batch_size], the start tokens.
  • end_token: int32 scalar, the token that marks end of decoding.

Raises:

  • ValueError: if start_tokens is not a 1D tensor or end_token is not a scalar.

Properties

batch_size

sample_ids_dtype

sample_ids_shape

Methods

initialize

View source

initialize(name=None)

next_inputs

View source

next_inputs(
    time,
    outputs,
    state,
    sample_ids,
    name=None
)

next_inputs_fn for GreedyEmbeddingHelper.

sample

View source

sample(
    time,
    outputs,
    state,
    name=None
)

sample for GreedyEmbeddingHelper.