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,.,.) = 
#>  0.01 *
#>   7.3356 -174.6643
#>   -58.0814 -94.0913
#> 
#> (1,2,.,.) = 
#>  -1.9080 -0.0760
#>  -0.3699  1.2992
#> 
#> (1,3,.,.) = 
#>  -0.1018 -0.3375
#>   0.4146  1.3945
#> 
#> (1,4,.,.) = 
#>   0.4264  0.7439
#>   0.2286 -0.2788
#> [ CPUFloatType{1,4,2,2} ]
#> torch_tensor
#> (1,1,.,.) = 
#>  0.01 *
#>   7.3356 -174.6643
#>   -58.0814 -94.0913
#> 
#> (1,2,.,.) = 
#>  -0.1018 -0.3375
#>   0.4146  1.3945
#> 
#> (1,3,.,.) = 
#>  -1.9080 -0.0760
#>  -0.3699  1.2992
#> 
#> (1,4,.,.) = 
#>   0.4264  0.7439
#>   0.2286 -0.2788
#> [ CPUFloatType{1,4,2,2} ]