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 uniform
distribution.
Examples
if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_xavier_uniform_(w)
}
#> torch_tensor
#> -0.0967 -0.1055 0.5585 0.4458 -0.1966
#> 0.5379 0.8129 -0.5773 -0.0945 -0.6718
#> 0.1761 -0.1713 0.5464 0.6671 -0.4240
#> [ CPUFloatType{3,5} ]