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
#> -0.2343 -0.0310 0.2535 0.4247 0.8364
#> 0.3203 -0.2105 0.4293 -0.7477 0.3314
#> -0.7936 -0.4682 0.2620 -0.1625 -0.2366
#> [ CPUFloatType{3,5} ]