mindspore.nn.PixelUnshuffle

class mindspore.nn.PixelUnshuffle(downscale_factor)[source]

Applies the PixelUnshuffle operation over input which is the inverse of PixelShuffle. For more details, refer to Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network .

Typically, the input is of shape \((*, C, H \times r, W \times r)\) , and the output is of shape \((*, C \times r^2, H, W)\) , where \(r\) is a downscale factor and \(*\) is zero or more batch dimensions.

Parameters

downscale_factor (int) – factor to unshuffle the input, and is a positive integer. downscale_factor is the above-mentioned \(r\).

Inputs:
  • input (Tensor) - Tensor of shape \((*, C, H \times r, W \times r)\) . The dimension of input is larger than 2, and the length of second to last dimension or last dimension can be divisible by downscale_factor .

Outputs:
  • output (Tensor) - Tensor of shape \((*, C \times r^2, H, W)\) .

Raises
  • ValueError – If downscale_factor is not a positive integer.

  • ValueError – If the length of second to last dimension or last dimension is not divisible by downscale_factor .

  • ValueError – If the dimension of input is less than 3.

  • TypeError – If input is not a Tensor.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore as ms
>>> import numpy as np
>>> pixel_unshuffle = ms.nn.PixelUnshuffle(2)
>>> input_x = np.arange(8 * 8).reshape((1, 1, 8, 8))
>>> input_x = ms.Tensor(input_x, ms.dtype.int32)
>>> output = pixel_unshuffle(input_x)
>>> print(output.shape)
(1, 4, 4, 4)