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
#> 0.6287 -0.5792 -0.1305 -0.1029 0.0325
#> 0.6539 0.0275 -0.2274 0.5379 -0.0562
#> -0.2081 -0.2833 0.1389 0.3959 -0.8699
#> [ CPUFloatType{3,5} ]