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
#> -0.7121 0.8032 -0.0018 -0.8483 0.1989
#> 0.1548 0.4414 0.3474 -0.2256 0.3213
#> -0.1098 0.7432 0.6216 0.1046 -0.7247
#> [ CPUFloatType{3,5} ]