Channel_shuffle

Usage

torch_channel_shuffle(self, groups)

Arguments

self: (Tensor) the input tensor
groups: (int) number of groups to divide channels in and rearrange.

Divide the channels in a tensor of shape

math:(*, C , H, W) :

Divide the channels in a tensor of shape $(*, C, H, W)$ into g groups and rearrange them as $(*, C \frac{g}{,} g, H, W)$ , while keeping the original tensor shape.

Examples

if (torch_is_installed()) {

input <- torch_randn(c(1, 4, 2, 2))
print(input)
output <- torch_channel_shuffle(input, 2)
print(output)
}
#> torch_tensor
#> (1,1,.,.) = 
#>   1.2647 -0.6131
#>  -0.9159  0.5732
#> 
#> (1,2,.,.) = 
#>   1.0948 -0.7870
#>  -1.8078 -0.0688
#> 
#> (1,3,.,.) = 
#>  -0.4148 -0.2391
#>  -0.6839 -1.0318
#> 
#> (1,4,.,.) = 
#>  -0.0844 -0.1575
#>   0.1586 -0.1377
#> [ CPUFloatType{1,4,2,2} ]
#> torch_tensor
#> (1,1,.,.) = 
#>   1.2647 -0.6131
#>  -0.9159  0.5732
#> 
#> (1,2,.,.) = 
#>  -0.4148 -0.2391
#>  -0.6839 -1.0318
#> 
#> (1,3,.,.) = 
#>   1.0948 -0.7870
#>  -1.8078 -0.0688
#> 
#> (1,4,.,.) = 
#>  -0.0844 -0.1575
#>   0.1586 -0.1377
#> [ CPUFloatType{1,4,2,2} ]