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
#>  0.6788 -0.6565 -0.4852 -0.3612  0.2842
#> -0.8653  0.3376 -0.5767  0.8286  0.7516
#> -0.1803  0.8656 -0.1408  0.4207 -0.0728
#> [ CPUFloatType{3,5} ]