Channel_shuffle
Source:R/gen-namespace-docs.R
, R/gen-namespace-examples.R
, R/gen-namespace.R
torch_channel_shuffle.Rd
Channel_shuffle
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,.,.) =
#> 0.6140 2.1915
#> -1.1439 -0.6537
#>
#> (1,2,.,.) =
#> 1.1468 -0.6219
#> 0.6974 0.8079
#>
#> (1,3,.,.) =
#> -1.7238 -0.3450
#> 0.2372 -0.6565
#>
#> (1,4,.,.) =
#> 1.1268 -0.0199
#> -0.6402 1.3421
#> [ CPUFloatType{1,4,2,2} ]
#> torch_tensor
#> (1,1,.,.) =
#> 0.6140 2.1915
#> -1.1439 -0.6537
#>
#> (1,2,.,.) =
#> -1.7238 -0.3450
#> 0.2372 -0.6565
#>
#> (1,3,.,.) =
#> 1.1468 -0.6219
#> 0.6974 0.8079
#>
#> (1,4,.,.) =
#> 1.1268 -0.0199
#> -0.6402 1.3421
#> [ CPUFloatType{1,4,2,2} ]