TensorFlow 1 version | View source on GitHub |
BatchToSpace for N-D tensors of type T.
tf.batch_to_space(
input, block_shape, crops, name=None
)
This operation reshapes the "batch" dimension 0 into M + 1
dimensions of
shape block_shape + [batch]
, interleaves these blocks back into the grid
defined by the spatial dimensions [1, ..., M]
, to obtain a result with the
same rank as the input. The spatial dimensions of this intermediate result
are then optionally cropped according to crops
to produce the output. This
is the reverse of SpaceToBatch (see tf.space_to_batch
).
Args | |
---|---|
input
|
A N-D Tensor with shape input_shape = [batch] + spatial_shape +
remaining_shape , where spatial_shape has M dimensions.
|
block_shape
|
A 1-D Tensor with shape [M]. Must be one of the following
types: int32 , int64 . All values must be >= 1. For backwards
compatibility with TF 1.0, this parameter may be an int, in which case it
is converted to
numpy.array([block_shape, block_shape],
dtype=numpy.int64) .
|
crops
|
A 2-D Tensor with shape [M, 2] . Must be one of the
following types: int32 , int64 . All values must be >= 0.
crops[i] = [crop_start, crop_end] specifies the amount to crop from
input dimension i + 1 , which corresponds to spatial dimension i .
It is required that
crop_start[i] + crop_end[i] <= block_shape[i] * input_shape[i + 1] .
This operation is equivalent to the following steps:
The output tensor has shape
The output tensor has shape
(3) For the following
input of shape
The output tensor has shape
(4) For the following input of shape
The output tensor has shape
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."],[],[]]
|