tf.contrib.seq2seq.GreedyEmbeddingHelper

Class GreedyEmbeddingHelper

Inherits From: Helper

Defined in tensorflow/contrib/seq2seq/python/ops/helper.py.

See the guide: Seq2seq Library (contrib) > Dynamic Decoding

A helper for use during inference.

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

Properties

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.

Methods

__init__

__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.

initialize

initialize(name=None)

Returns (initial_finished, initial_inputs).

next_inputs

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

next_inputs_fn for GreedyEmbeddingHelper.

sample

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

sample for GreedyEmbeddingHelper.