Dice Cofficient Metric

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

[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.metrics.dice.DiceCoefficientMetric(*args: Any, **kwargs: Any)

compute(y_true, y_pred)

get_config()

result()

update_state(y_true, y_pred, sample_weight=None)

class image_segmentation.metrics.dice.SparseCategoricalDiceCoefficientMetric(*args: Any, **kwargs: Any)

update_state(y_true, y_pred, sample_weight=None)