Permutation Invariant Training (PIT)

Module Interface

torchmetrics.PermutationInvariantTraining

alias of torchmetrics.audio._deprecated._PermutationInvariantTraining

Functional Interface

torchmetrics.functional.permutation_invariant_training(preds, target, metric_func, mode='speaker-wise', eval_func='max', **kwargs)

Wrapper for deprecated import.

>>> from torch import tensor
>>> preds = tensor([[[-0.0579,  0.3560, -0.9604], [-0.1719,  0.3205,  0.2951]]])
>>> target = tensor([[[ 1.0958, -0.1648,  0.5228], [-0.4100,  1.1942, -0.5103]]])
>>> best_metric, best_perm = _permutation_invariant_training(
...     preds, target, _scale_invariant_signal_distortion_ratio)
>>> best_metric
tensor([-5.1091])
>>> best_perm
tensor([[0, 1]])
>>> pit_permutate(preds, best_perm)
tensor([[[-0.0579,  0.3560, -0.9604],
         [-0.1719,  0.3205,  0.2951]]])

Return type

Tuple[Tensor, Tensor]