onert.experimental.train.losses.loss.LossFunction Class Reference

Public Member Functions
None	__init__ (self, Literal["mean", "sum"] reduction="mean")

Detailed Description

Base class for loss functions with reduction type.

Definition at line 5 of file loss.py.

Constructor & Destructor Documentation

__init__()

None onert.experimental.train.losses.loss.LossFunction.__init__	(		self,
		Literal["mean", "sum"]	reduction = "mean"
	)

Initialize the Categorical Cross-Entropy loss function.
Args:
    reduction (str): Reduction type ('mean', 'sum').

Reimplemented in onert.experimental.train.losses.cce.CategoricalCrossentropy, and onert.experimental.train.losses.mse.MeanSquaredError.

Definition at line 9 of file loss.py.

    def __init__(self, reduction: Literal["mean", "sum"] = "mean") -> None:
        """
        Initialize the Categorical Cross-Entropy loss function.
        Args:
            reduction (str): Reduction type ('mean', 'sum').
        """
        reduction_mapping: Dict[Literal["mean", "sum"], loss_reduction] = {
            "mean": loss_reduction.SUM_OVER_BATCH_SIZE,
            "sum": loss_reduction.SUM
        }
 
        # Validate and assign the reduction type
        if reduction not in reduction_mapping:
            raise ValueError(
                f"Invalid reduction type. Choose from {list(reduction_mapping.keys())}.")
 
        self.reduction: loss_reduction = reduction_mapping[reduction]

---

The documentation for this class was generated from the following file:

• runtime/onert/api/python/onert/experimental/train/losses/loss.py