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
#> 0.0861 0.2105 0.0386 0.0478 -0.7859
#> -0.5292 0.0143 -0.1561 -0.4400 0.7440
#> 0.1636 -0.0215 0.7972 0.1964 0.3584
#> [ CPUFloatType{3,5} ]