Normal initialization — nn_init_normal_ • torch

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
#> -2.8220 -0.9944  0.8991  0.8899 -0.4855
#> -0.5401  2.6521 -0.5640  1.9080 -1.2019
#>  1.4732 -0.1343  2.0501 -0.5470  0.7292
#> [ CPUFloatType{3,5} ]