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
#>  0.3517  0.4739 -0.5648  0.0948 -1.2220
#> -0.4455  0.2146 -0.1595  1.1814 -0.6876
#> -0.6504  0.4804  0.4461 -0.2795 -0.8179
#> [ CPUFloatType{3,5} ]