Normal initialization

Source: R/nn-init.R

Fills the input Tensor with values drawn from the normal distribution

nn_init_normal_(tensor, mean = 0, std = 1)

Arguments

tensor

an n-dimensional Tensor
mean

the mean of the normal distribution
std

the standard deviation of the normal distribution

Examples

if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_normal_(w)

}

#> torch_tensor
#> -0.6194  0.7818 -0.2960  1.7736 -0.1287
#> -0.9586  0.2466  0.1270 -0.3057  0.5785
#>  1.3467  1.3532  1.3662  0.7040  1.4877
#> [ CPUFloatType{3,5} ]