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
#>  1.8168 -0.6190  1.3776 -0.6168  0.0281
#> -1.3362  1.0592 -0.3194 -0.1106  0.8847
#> -0.0672 -1.4283  0.8746  0.2834 -1.7215
#> [ CPUFloatType{3,5} ]