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
#> -0.1030  0.2154  0.0579 -0.5820 -0.1927
#> -0.5100 -0.2952  0.0129 -0.4188  0.7129
#> -0.7241 -0.5141 -0.5110  0.1936  0.1371
#> [ CPUFloatType{3,5} ]