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
#> 0.3225 -0.6461 0.4096 0.0415 -0.5559
#> 0.4231 -0.4908 -0.7005 -0.0313 0.2975
#> -0.2485 -0.4405 0.4623 -0.2294 0.6913
#> [ CPUFloatType{3,5} ]