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
#> -0.3315 -0.4208  0.5450  0.1931  0.8674
#>  0.5824 -0.0277  0.1092 -0.1530  0.1676
#>  0.1026  0.2176  0.1571 -0.4297  0.4761
#> [ CPUFloatType{3,5} ]