contrib.seq2seq.TrainingHelper
tf.contrib.seq2seq.TrainingHelper
class tf.contrib.seq2seq.TrainingHelper
Defined in tensorflow/contrib/seq2seq/python/ops/helper.py
.
See the guide: Seq2seq Library (contrib) > Dynamic Decoding
A helper for use during training. Only reads inputs.
Returned sample_ids are the argmax of the RNN output logits.
Properties
batch_size
Methods
__init__
__init__( inputs, sequence_length, time_major=False, name=None )
Initializer.
Args:
-
inputs
: A (structure of) input tensors. -
sequence_length
: An int32 vector tensor. -
time_major
: Python bool. Whether the tensors ininputs
are time major. IfFalse
(default), they are assumed to be batch major. -
name
: Name scope for any created operations.
Raises:
-
ValueError
: ifsequence_length
is not a 1D tensor.
initialize
initialize(name=None)
next_inputs
next_inputs( time, outputs, state, name=None, **unused_kwargs )
next_inputs_fn for TrainingHelper.
sample
sample( time, outputs, name=None, **unused_kwargs )
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/contrib/seq2seq/TrainingHelper