mindspore.ops.batch_to_space_nd

mindspore.ops.batch_to_space_nd(input_x, block_shape, crops)

Divides batch dimension with blocks and interleaves these blocks back into spatial dimensions.

This operation will divide batch dimension N into blocks with block_shape, the output tensor's N dimension is the corresponding number of blocks after division. The output tensor's $w_1,...,w_M$ dimension is the product of original $w_1,...,w_M$ dimension and block_shape with given amount to crop from dimension, respectively.

If the input shape is $(n,c_1,...c_k,w_1,...,w_M)$, the output shape is $(n^{\prime },c_1,...c_k,w_1^{\prime },...,w_M^{\prime })$, where

$$\begin{array}{r}\begin{array}{l}\\ n^{\prime }=n//(block\mathrm{\_}shape[0]\ast ...\ast block\mathrm{\_}shape[M-1])\\ w_i^{\prime }=w_i\ast block\mathrm{\_}shape[i-1]-crops[i-1][0]-crops[i-1][1]\end{array}\end{array}$$

Parameters

• input_x (Tensor) – The input tensor. It must be greater or equal to 2-D tensor(equal to 4-D tensor on Ascend), batch dimension must be divisible by product of block_shape.

• block_shape (Union[list(int), tuple(int), int]) – The block shape of dividing block with all value greater than or equal to 1. If block_shape is a tuple or list, the length of block_shape is M corresponding to the number of spatial dimensions. If block_shape is an int, the block size of M dimensions are the same, equal to block_shape. In this case of Ascend, M must be 2.

• crops (Union[list(int), tuple(int)]) – The crops values for spatial dimensions, containing M subtraction list. Each contains 2 integer values. All values must be >= 0. crops[i] specifies the crops values for spatial dimension i, which corresponds to input dimension i + offset,where offset = N-M, and N is the number of input dimensions. It is required that $input\mathrm{\_}shape[i+offset]\ast block\mathrm{\_}shape[i]>crops[i][0]+crops[i][1]$

Returns

Tensor

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> block_shape = [2, 2]
>>> crops = [[0, 0], [0, 0]]
>>> input_x = mindspore.tensor([[[[1]]], [[[2]]], [[[3]]], [[[4]]]], mindspore.float32)
>>> output = mindspore.ops.batch_to_space_nd(input_x, block_shape, crops)
>>> print(output)
[[[[1.  2.]
   [3.  4.]]]]