Method _prepare_criterion

opacus/privacy_engine.py:226–244

Args: module: GradSampleModule used for training, optimizer: DPOptimizer used for training, criterion: Loss function used for training, loss_reduction: "mean" or "sum", indicates if the loss reduction (for aggregating the gradients) P

(
        self,
        *,
        module: GradSampleModule,
        optimizer: DPOptimizer,
        criterion,
        loss_reduction: str = "mean",
        **kwargs,
    )

                )

    def _prepare_criterion(
        self,
        *,
        module: GradSampleModule,
        optimizer: DPOptimizer,
        criterion,
        loss_reduction: str = "mean",
        **kwargs,
    ) -> DPLossFastGradientClipping:
        """
        Args:
            module: GradSampleModule used for training,
            optimizer: DPOptimizer used for training,
            criterion: Loss function used for training,
            loss_reduction: "mean" or "sum", indicates if the loss reduction (for aggregating the gradients)

        Prepare the DP loss class, which packages the two backward passes for fast gradient clipping.
        """
        return DPLossFastGradientClipping(module, optimizer, criterion, loss_reduction)

    def is_compatible(
        self,