focal_loss_multiclass: Focal loss for two or more labels

In GenomeNet/deepG: Deep Learning for Genome Sequence Data

Focal loss for two or more labels

Description

Focal loss for two or more labels

Usage

focal_loss_multiclass(y_true, y_pred, gamma = 2.5, alpha = c(1))

Arguments

y_true	Vector of true values.
y_pred	Vector of predicted values.
gamma	Focusing parameter.
alpha	Vector of weighting factors.

Value

A function implementing focal loss.

Examples

y_true <- matrix(c(0, 1, 0, 0, 0, 1), nrow = 2, byrow = TRUE)
y_pred <- matrix(c(0.15, 0.8, 0.05,
                   0.08, 0.02, 0.9), nrow = 2, byrow = TRUE) 
fl <- focal_loss_multiclass(y_true, y_pred)
fl$numpy()

GenomeNet/deepG documentation built on Dec. 24, 2024, 12:11 p.m.