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
#> -0.7121  0.8032 -0.0018 -0.8483  0.1989
#>  0.1548  0.4414  0.3474 -0.2256  0.3213
#> -0.1098  0.7432  0.6216  0.1046 -0.7247
#> [ CPUFloatType{3,5} ]