use burn::tensor::activation::softmax;
use burn::tensor::backend::Backend;
use burn::tensor::{Bool, Int, Tensor};
pub(super) fn gumbel_softmax<B: Backend>(logits: Tensor<B, 3>) -> Tensor<B, 3> {
let device = logits.device();
let u = Tensor::<B, 3>::random(
logits.dims(),
burn::tensor::Distribution::Uniform(1e-20, 1.0),
&device,
);
let neg_log_u = -u.log();
let gumbel = -neg_log_u.log();
softmax(logits + gumbel, 2)
}
pub(super) fn blend_with_current<B: Backend>(
probs: Tensor<B, 3>,
assignments: Tensor<B, 2, Int>,
var_masks: Tensor<B, 2, Bool>,
) -> Tensor<B, 3> {
let [batch_size, number_vars, domain_size] = probs.dims();
let device = probs.device();
let arange: Tensor<B, 3, Int> = Tensor::<B, 1, Int>::arange(0..domain_size as i64, &device)
.reshape([1, 1, domain_size])
.repeat_dim(0, batch_size)
.repeat_dim(1, number_vars);
let assign_3d: Tensor<B, 3, Int> = assignments
.reshape([batch_size, number_vars, 1])
.repeat_dim(2, domain_size);
let one_hot: Tensor<B, 3> = assign_3d.equal(arange).float();
let mask_3d: Tensor<B, 3, Bool> = var_masks
.reshape([batch_size, number_vars, 1])
.repeat_dim(2, domain_size);
one_hot.mask_where(mask_3d, probs)
}