contrib.seq2seq.ScheduledOutputTrainingHelper
tf.contrib.seq2seq.ScheduledOutputTrainingHelper
class tf.contrib.seq2seq.ScheduledOutputTrainingHelper
Defined in tensorflow/contrib/seq2seq/python/ops/helper.py
.
See the guide: Seq2seq Library (contrib) > Dynamic Decoding
A training helper that adds scheduled sampling directly to outputs.
Returns False for sample_ids where no sampling took place; True elsewhere.
Properties
batch_size
Methods
__init__
__init__( inputs, sequence_length, sampling_probability, time_major=False, seed=None, next_input_layer=None, auxiliary_inputs=None, name=None )
Initializer.
Args:
-
inputs
: A (structure) of input tensors. -
sequence_length
: An int32 vector tensor. -
sampling_probability
: A 0Dfloat32
tensor: the probability of sampling from the outputs instead of reading directly from the inputs. -
time_major
: Python bool. Whether the tensors ininputs
are time major. IfFalse
(default), they are assumed to be batch major. -
seed
: The sampling seed. -
next_input_layer
: (Optional) An instance oftf.layers.Layer
, i.e.,tf.layers.Dense
. Optional layer to apply to the RNN output to create the next input. -
auxiliary_inputs
: An optional (structure of) auxiliary input tensors with a shape that matchesinputs
in all but (potentially) the final dimension. These tensors will be concatenated to the sampled output or theinputs
when not sampling for use as the next input. -
name
: Name scope for any created operations.
Raises:
-
ValueError
: ifsampling_probability
is not a scalar or vector.
initialize
initialize(name=None)
next_inputs
next_inputs( time, outputs, state, sample_ids, name=None )
sample
sample( time, outputs, state, name=None )
© 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/ScheduledOutputTrainingHelper