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
#> -0.0967 -0.1055  0.5585  0.4458 -0.1966
#>  0.5379  0.8129 -0.5773 -0.0945 -0.6718
#>  0.1761 -0.1713  0.5464  0.6671 -0.4240
#> [ CPUFloatType{3,5} ]