Truncated normal initialization

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
#> -0.5052 -0.0522  0.4131  1.0076 -0.5338
#> -0.5901  0.1806 -1.1323  0.3089 -0.0270
#>  1.0514 -0.5927  0.2688  0.3349  1.0045
#> [ CPUFloatType{3,5} ]