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
#> -0.1311 -0.1925 -0.3381 -1.1570 -0.5451
#> -0.3186  1.2327 -0.5938  1.5985  0.0717
#>  1.3069  1.2172 -1.4623  0.8643  0.1981
#> [ CPUFloatType{3,5} ]