BatchToSpace for ND tensors of type T.
tf.compat.v2.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 below for a precise description.
Args  

input  A Tensor . ND 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 . 1D with shape [M] , 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 Tensor . Must be one of the following types: int32 , int64 . 2D with shape [M, 2] , 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:

name  A name for the operation (optional). 
Returns  

A Tensor . Has the same type as input . 
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/compat/v2/batch_to_space