Normal initialization

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
#> -1.4652 -0.3194  0.5178 -0.9953 -0.4607
#> -1.3006 -1.4896 -0.7139  0.9247 -0.3508
#>  0.3609 -1.5614 -2.3035 -0.3111 -0.0605
#> [ CPUFloatType{3,5} ]