nn_init_trunc_normal_ function

Truncated normal initialization

Truncated normal initialization

Fills the input Tensor with values drawn from a truncated normal distribution.

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) }
  • Maintainer: Daniel Falbel
  • License: MIT + file LICENSE
  • Last published: 2025-02-14