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
#>  1.0943  1.1567  0.0258 -0.7832 -0.5538
#> -0.5531 -1.3476 -0.8076 -0.2420  1.1353
#>  1.1322  0.3360 -1.4991 -0.0343 -0.2399
#> [ CPUFloatType{3,5} ]