Fills the input Tensor
with values according to the method
described in Understanding the difficulty of training deep feedforward neural networks
- Glorot, X. & Bengio, Y. (2010), using a normal
distribution.
Examples
if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_xavier_normal_(w)
}
#> torch_tensor
#> 0.1424 1.1235 0.4007 0.2574 -0.1097
#> -0.6556 -0.6592 -0.9366 0.3650 0.0776
#> -0.2478 -0.4547 0.3113 0.2522 0.3727
#> [ CPUFloatType{3,5} ]