mindspore.ops.SpaceToDepth

class mindspore.ops.SpaceToDepth(block_size)

Rearrange blocks of spatial data into depth.

The output tensor's height dimension is $height/block\mathrm{\_}size$.

The output tensor's weight dimension is $weight/block\mathrm{\_}size$.

The depth of output tensor is $block\mathrm{\_}size\ast block\mathrm{\_}size\ast input\mathrm{\_}depth$.

The input tensor's height and width must be divisible by block_size. The data format is "NCHW".

Parameters

block_size (int) – The block size used to divide spatial data. It must be >= 2.

Inputs:

• x (Tensor) - The target tensor. The data type is Number. It must be a 4-D tensor.

Outputs:

Tensor, the same data type as x. It must be a 4-D tensor. Tensor of shape $(N,(C_{in}\ast \text{block\_size}\ast 2),H_{in}/\text{block\_size},W_{in}/\text{block\_size})$.

Raises

• TypeError – If block_size is not an int.

• ValueError – If block_size is less than 2.

• ValueError – If length of shape of x is not equal to 4.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.random.rand(1,3,2,2), mindspore.float32)
>>> block_size = 2
>>> space_to_depth = ops.SpaceToDepth(block_size)
>>> output = space_to_depth(x)
>>> print(output.shape)
(1, 12, 1, 1)