View source on GitHub |
Base abstract class that allows the user to customize sampling.
Inherits From: Helper
tf.contrib.seq2seq.CustomHelper(
initialize_fn, sample_fn, next_inputs_fn, sample_ids_shape=None,
sample_ids_dtype=None
)
Args | |
---|---|
initialize_fn
|
callable that returns (finished, next_inputs)
for the first iteration.
|
sample_fn
|
callable that takes (time, outputs, state)
and emits tensor sample_ids .
|
next_inputs_fn
|
callable that takes (time, outputs, state, sample_ids)
and emits (finished, next_inputs, next_state) .
|
sample_ids_shape
|
Either a list of integers, or a 1-D Tensor of type
int32 , the shape of each value in the sample_ids batch. Defaults to
a scalar.
|
sample_ids_dtype
|
The dtype of the sample_ids tensor. Defaults to int32.
|
Attributes | |
---|---|
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 |
Methods
initialize
initialize(
name=None
)
Returns (initial_finished, initial_inputs)
.
next_inputs
next_inputs(
time, outputs, state, sample_ids, name=None
)
Returns (finished, next_inputs, next_state)
.
sample
sample(
time, outputs, state, name=None
)
Returns sample_ids
.