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
#>  0.7026 -0.4567 -0.0345 -0.1307  0.4457
#> -0.3468 -0.6615 -0.6355  0.5272  0.3231
#> -0.0437 -0.6052  0.5457 -0.1636 -0.7203
#> [ CPUFloatType{3,5} ]