o ¡¿¯iF ã@s@ddlZddlmZddlmZddlmZGdd„deƒZdS)éN)Ú AbsEnhLoss)ÚAbsLossWrapper)Ú PITSolvercs4eZdZ  ddef‡fdd„ Zifdd„Z‡ZS) ÚMultiLayerPITSolverçð?TÚ criterioncs.tƒ ¡||_||_||_t|||ƒ|_dS)a%Multi-Layer Permutation Invariant Training Solver. Compute the PIT loss given inferences of multiple layers and a single reference. It also support single inference and single reference in evaluation stage. Args: criterion (AbsEnhLoss): an instance of AbsEnhLoss weight (float): weight (between 0 and 1) of current loss for multi-task learning. independent_perm (bool): If True, PIT will be performed in forward to find the best permutation; If False, the permutation from the last LossWrapper output will be inherited. Note: You should be careful about the ordering of loss wrappers defined in the yaml config, if this argument is False. N)ÚsuperÚ__init__rÚweightÚindependent_permrÚsolver)Úselfrr r ©Ú __class__©úc/home/ubuntu/.local/lib/python3.10/site-packages/espnet2/enh/loss/wrappers/multilayer_pit_solver.pyr s zMultiLayerPITSolver.__init__c Cs”d}t |d¡rt|ƒt|ƒkr| |||¡\}}}|}n't|ƒD]\}}| |||¡\}}}|||ddt|ƒ}q"|t|ƒ}|||fS)aÐPermutation invariant training solver. Args: ref (List[torch.Tensor]): [(batch, ...), ...] x n_spk infs (Union[List[torch.Tensor], List[List[torch.Tensor]]]): [(batch, ...), ...] Returns: loss: (torch.Tensor): minimum loss with the best permutation stats: dict, for collecting training status others: dict, in this PIT solver, permutation order will be returned grér)ÚtorchÚ is_tensorÚlenr Ú enumerate) r ÚrefÚinfsÚothersÚlossesÚlossÚstatsÚidxÚinfrrrÚforward%s   zMultiLayerPITSolver.forward)rT)Ú__name__Ú __module__Ú __qualname__rr rÚ __classcell__rrrrrsüþr)rÚ$espnet2.enh.loss.criterions.abs_lossrÚ%espnet2.enh.loss.wrappers.abs_wrapperrÚ$espnet2.enh.loss.wrappers.pit_solverrrrrrrÚs