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
#> -0.4078  0.1394 -0.8101  0.6184 -0.4003
#>  0.1397  0.2521  0.7627  0.0858  0.0319
#> -0.5982 -0.5775 -0.7312  0.6636  0.7201
#> [ CPUFloatType{3,5} ]