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.
Examples
if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_orthogonal_(w)
}
#> torch_tensor
#> 0.7584 0.3850 0.1420 -0.4675 -0.1945
#> 0.4705 -0.3533 0.2239 0.6894 -0.3583
#> -0.4029 0.2906 0.7858 -0.0225 -0.3679
#> [ CPUFloatType{3,5} ]