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
#> -0.5071 -0.3531  0.1250  0.7562 -0.6302
#> -0.6892  0.6461  0.5584  0.7683 -0.3572
#> -0.5540 -0.8478 -0.5756  0.1296  0.1135
#> [ CPUFloatType{3,5} ]