tf.contrib.seq2seq.TrainingHelper

View source on GitHub

A helper for use during training. Only reads inputs.

Inherits From: Helper

Returned sample_ids are the argmax of the RNN output logits.

inputs A (structure of) input tensors.
sequence_length An int32 vector tensor.
time_major Python bool. Whether the tensors in inputs are time major. If False (default), they are assumed to be batch major.
name Name scope for any created operations.

ValueError if sequence_length is not a 1D tensor.

batch_size Batch size of tensor returned by sample.

Returns a scalar int32 tensor.

inputs

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.

sequence_length

Methods

initialize

View source

Returns (initial_finished, initial_inputs).

next_inputs

View source

next_inputs_fn for TrainingHelper.

sample

View source

Returns sample_ids.