Xavier normal initialization — nn_init_xavier_normal

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.

Usage

nn_init_xavier_normal_(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_normal_(w)
}
#> torch_tensor
#>  0.1267  1.1442  0.1660  0.1379 -0.0936
#> -0.0446 -0.2090  0.3507 -0.1380  0.4939
#>  0.5699 -0.0885 -0.2648 -0.4284 -0.0615
#> [ CPUFloatType{3,5} ]