tf.contrib.seq2seq.tile_batch
Stay organized with collections
Save and categorize content based on your preferences.
Tile the batch dimension of a (possibly nested structure of) tensor(s) t.
tf.contrib.seq2seq.tile_batch(
t, multiplier, name=None
)
For each tensor t in a (possibly nested structure) of tensors,
this function takes a tensor t shaped [batch_size, s0, s1, ...]
composed of
minibatch entries t[0], ..., t[batch_size - 1]
and tiles it to have a shape
[batch_size * multiplier, s0, s1, ...]
composed of minibatch entries
t[0], t[0], ..., t[1], t[1], ...
where each minibatch entry is repeated
multiplier
times.
Args |
t
|
Tensor shaped [batch_size, ...] .
|
multiplier
|
Python int.
|
name
|
Name scope for any created operations.
|
Returns |
A (possibly nested structure of) Tensor shaped
[batch_size * multiplier, ...] .
|
Raises |
ValueError
|
if tensor(s) t do not have a statically known rank or
the rank is < 1.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.contrib.seq2seq.tile_batch\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/seq2seq/python/ops/beam_search_decoder.py#L101-L126) |\n\nTile the batch dimension of a (possibly nested structure of) tensor(s) t. \n\n tf.contrib.seq2seq.tile_batch(\n t, multiplier, name=None\n )\n\nFor each tensor t in a (possibly nested structure) of tensors,\nthis function takes a tensor t shaped `[batch_size, s0, s1, ...]` composed of\nminibatch entries `t[0], ..., t[batch_size - 1]` and tiles it to have a shape\n`[batch_size * multiplier, s0, s1, ...]` composed of minibatch entries\n`t[0], t[0], ..., t[1], t[1], ...` where each minibatch entry is repeated\n`multiplier` times.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------------|----------------------------------------|\n| `t` | `Tensor` shaped `[batch_size, ...]`. |\n| `multiplier` | Python int. |\n| `name` | Name scope for any created operations. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A (possibly nested structure of) `Tensor` shaped `[batch_size * multiplier, ...]`. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|---------------------------------------------------------------------------|\n| `ValueError` | if tensor(s) `t` do not have a statically known rank or the rank is \\\u003c 1. |\n\n\u003cbr /\u003e"]]