|View source on GitHub|
DepthToSpace for tensors of type T.
Compat aliases for migration
See Migration guide for more details.
tf.compat.v1.depth_to_space( input, block_size, name=None, data_format='NHWC' )
Rearranges data from depth into blocks of spatial data.
This is the reverse transformation of SpaceToDepth. More specifically,
this op outputs a copy of the input tensor where values from the
dimension are moved in spatial blocks to the
block_size indicates the input block size and how the data is moved.
- Chunks of data of size
block_size * block_sizefrom depth are rearranged into non-overlapping blocks of size
block_size x block_size
- The width the output tensor is
input_depth * block_size, whereas the height is
input_height * block_size.
- The Y, X coordinates within each block of the output image are determined by the high order component of the input channel index.
- The depth of the input tensor must be divisible by
block_size * block_size.
data_format attr specifies the layout of the input and output tensors
with the following options:
[ batch, height, width, channels ]
[ batch, channels, height, width ]
qint8 [ batch, channels / 4, height, width, 4 ]
It is useful to consider the operation as transforming a 6-D Tensor. e.g. for data_format = NHWC, Each element in the input tensor can be specified via 6 coordinates, ordered by decreasing memory layout significance as: n,iY,iX,bY,bX,oC (where n=batch index, iX, iY means X or Y coordinates within the input image, bX, bY means coordinates within the output block, oC means output channels). The output would be the input transposed to the following layout: n,iY,bY,iX,bX,oC
This operation is useful for resizing the activations between convolutions (but keeping all da