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
#>  0.1621 -0.1577 -0.4962  0.1353  0.2332
#>  0.0264  0.3153 -0.2353 -0.0800 -0.1215
#> -0.0600  1.1364  0.0075  0.2040  0.4694
#> [ CPUFloatType{3,5} ]