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
#> 0.3316 -0.3799 0.7870 0.4199 0.2380
#> -0.5967 0.3578 0.7614 0.7000 0.4116
#> -0.5598 0.2516 0.2989 -0.4461 0.3115
#> [ CPUFloatType{3,5} ]