Truncated normal initialization — nn_init_trunc_normal_ • torch

Fills the input Tensor with values drawn from a truncated normal distribution.

Usage

nn_init_trunc_normal_(tensor, mean = 0, std = 1, a = -2, b = 2)

Arguments

tensor: an n-dimensional Tensor
mean: the mean of the normal distribution
std: the standard deviation of the normal distribution
a: the minimum cutoff value
b: the maximum cutoff value

Examples

if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_trunc_normal_(w)
}
#> torch_tensor
#>  0.9654  0.4623 -0.9739 -1.2712  0.1685
#>  0.7285  0.1402 -1.0576 -0.8360  0.7709
#> -0.5137 -0.5875  0.7684  0.2338 -0.8943
#> [ CPUFloatType{3,5} ]