View source on GitHub |
SpaceToBatch for N-D tensors of type T.
tf.space_to_batch(
input, block_shape, paddings, name=None
)
This operation divides "spatial" dimensions [1, ..., M]
of the input into a
grid of blocks of shape block_shape
, and interleaves these blocks with the
"batch" dimension (0) such that in the output, the spatial dimensions
[1, ..., M]
correspond to the position within the grid, and the batch
dimension combines both the position within a spatial block and the original
batch position. Prior to division into blocks, the spatial dimensions of the
input are optionally zero padded according to paddings
. See below for a
precise description.
Args | |
---|---|
input
|
A Tensor .
N-D with shape input_shape = [batch] + spatial_shape + remaining_shape ,
where spatial_shape has M dimensions.
|
block_shape
|
A Tensor . Must be one of the following types: int32 , int64 .
1-D with shape [M] , all values must be >= 1.
|
paddings
|
A Tensor . Must be one of the following types: int32 , int64 .
2-D with shape [M, 2] , all values must be >= 0.
paddings[i] = [pad_start, pad_end] specifies the padding for input dimension
i + 1 , which corresponds to spatial dimension i . It is required that
block_shape[i] divides input_shape[i + 1] + pad_start + pad_end .
This operation is equivalent to the following steps:
[batch] + [padded_shape[1] / block_shape[0], block_shape[0], ..., padded_shape[M] / block_shape[M-1], block_shape[M-1]] + remaining_shape
block_shape + [batch] + [padded_shape[1] / block_shape[0], ..., padded_shape[M] / block_shape[M-1]] + remaining_shape
[batch * prod(block_shape)] + [padded_shape[1] / block_shape[0], ..., padded_shape[M] / block_shape[M-1]] + remaining_shape Some examples: (1) For the following input of shape
The output tensor has shape
(2) For the following input of 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
Among others, this operation is useful for reducing atrous convolution into regular convolution. |
name
|
A name for the operation (optional). |
Returns | |
---|---|
A Tensor . Has the same type as input .
|