Orthogonal initialization — nn_init_orthogonal

Fills the input Tensor with a (semi) orthogonal matrix, as described in Exact solutions to the nonlinear dynamics of learning in deep linear neural networks - Saxe, A. et al. (2013). The input tensor must have at least 2 dimensions, and for tensors with more than 2 dimensions the trailing dimensions are flattened.

Usage

nn_init_orthogonal_(tensor, gain = 1)

Arguments

tensor: an n-dimensional Tensor
gain: optional scaling factor

Examples

if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_orthogonal_(w)
}
#> torch_tensor
#>  0.7712  0.5349 -0.1864  0.2368 -0.1684
#>  0.2026 -0.2314  0.2222  0.5610  0.7357
#>  0.1214 -0.2399 -0.8528 -0.2716  0.3559
#> [ CPUFloatType{3,5} ]