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
#> -0.4620 -0.0496 -0.3949  0.1246 -0.8404
#> -0.5346 -0.0448 -0.3253  0.7942 -0.5718
#> -0.5172 -0.5147  0.8381  0.2599  0.1879
#> [ CPUFloatType{3,5} ]