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
#> -0.5348  0.3593 -0.3155 -0.8486  0.0068
#> -0.1175  0.1275  0.4085 -1.4018 -0.3685
#> -0.6050  0.8337 -0.4382  0.5691  0.5143
#> [ CPUFloatType{3,5} ]