losses.loss.LossFunction Class Reference

Public Member Functions
	__init__ (self, reduction="mean")

Data Fields
	reduction

Detailed Description

Base class for loss functions with reduction type.

Definition at line 4 of file loss.py.

Constructor & Destructor Documentation

__init__()

losses.loss.LossFunction.__init__	(		self,
			reduction = "mean"
	)

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

Reimplemented in losses.cce.CategoricalCrossentropy, and losses.mse.MeanSquaredError.

Definition at line 8 of file loss.py.

    def __init__(self, reduction="mean"):
        """
        Initialize the Categorical Cross-Entropy loss function.
        Args:
            reduction (str): Reduction type ('mean', 'sum').
        """
        reduction_mapping = {
            "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 = reduction_mapping[reduction]

Field Documentation

reduction

losses.loss.LossFunction.reduction

Definition at line 24 of file loss.py.

---

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

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