Normal initialization

Fills the input Tensor with values drawn from the normal distribution

Usage

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
#> -1.9065  0.1094 -1.9814 -0.4104  0.2956
#>  0.4850 -0.6129 -1.8040 -1.0332  0.8786
#> -0.7913  0.1575  0.1857 -1.1765 -1.1846
#> [ CPUFloatType{3,5} ]