PixelUnshuffle¶

class paddle.nn. PixelUnshuffle ( downscale_factor, data_format='NCHW', name=None ) [source]

Rearranges elements in a tensor of shape $[N, C, H, W]$ to a tensor of shape $[N, r^2C, H/r, W/r]$ , or from shape $[N, H, W, C]$ to $[N, H/r, W/r, r^2C]$ , where $r$ is the downscale factor. This operation is the reversion of PixelShuffle operation. Please refer to the paper: Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network . by Shi et. al (2016) for more details.

Parameters

downscale_factor (int) – Factor to decrease spatial resolution.
data_format (str, optional) – The data format of the input and output data. An optional string of NCHW or NHWC. The default is NCHW. When it is NCHW, the data is stored in the order of [batch_size, input_channels, input_height, input_width].
name (str, optional) – Name for the operation (optional, default is None). Normally there is no need for user to set this property. For more information, please refer to Name.

Shape:

x: 4-D tensor with shape of $[N, C, H, W]$ or $[N, C, H, W]$ .
out: 4-D tensor with shape of $[N, r^2C, H/r, W/r]$ or $[N, H/r, W/r, r^2C]$ , where $r$ is downscale_factor.

Examples

import paddle
import paddle.nn as nn

x = paddle.randn([2, 1, 12, 12])
pixel_unshuffle = nn.PixelUnshuffle(3)
out = pixel_unshuffle(x)
print(out.shape)
# [2, 9, 4, 4]

forward ( x ) forward¶

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

*inputs (tuple) – unpacked tuple arguments
**kwargs (dict) – unpacked dict arguments

extra_repr ( ) extra_repr¶: Extra representation of this layer, you can have custom implementation of your own layer.

PixelUnshuffle¶

forward¶

extra_repr¶