Fills the input Tensor with values drawn from a truncated normal distribution.
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
#> 0.0660 0.4092 -1.8134 1.5285 0.3146
#> 0.3924 1.3526 -0.4359 1.4549 0.8951
#> 0.5148 -0.7059 1.1601 -0.2954 0.4129
#> [ CPUFloatType{3,5} ]