Dice Cofficient Loss

\[-2\frac{|\mathcal{M} \otimes \hat{\mathcal{M}}|}{|\mathcal{M}| - |\hat{\mathcal{M}}|}\]

[1]

Random Fourier Features-Based Deep Learning Improvement with Class Activation Interpretability for Nerve Structure Segmentation

[2]

Multi categorical Dice loss?

[3]

RFF-Nerve-UTP

class image_segmentation.losses.dice.DiceCoefficient(*args: Any, **kwargs: Any)

call(y_true, y_pred)

get_config()

class image_segmentation.losses.dice.SparseCategoricalDiceCoefficient(*args: Any, **kwargs: Any)

call(y_true, y_pred)