Xavier uniform initialization — nn_init_xavier_uniform

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.

Usage

nn_init_xavier_uniform_(tensor, gain = 1)

Arguments

tensor: an n-dimensional Tensor
gain: an optional scaling factor

Examples

if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_xavier_uniform_(w)
}
#> torch_tensor
#>  0.8506  0.5229  0.6085 -0.7187 -0.1505
#>  0.0939  0.6773 -0.1960  0.0014  0.3092
#>  0.7826 -0.2240  0.6648 -0.8478  0.6025
#> [ CPUFloatType{3,5} ]