tf.keras.losses.Dice

View source on GitHub

Computes the Dice loss value between y_true and y_pred.

Inherits From: Loss

tf.keras.losses.Dice(
    reduction='sum_over_batch_size', name='dice'
)

Formula:

loss = 1 - (2 * sum(y_true * y_pred)) / (sum(y_true) + sum(y_pred))

Args
y_true	tensor of true targets.
y_pred	tensor of predicted targets.

Returns
Dice loss value.

Methods

call

View source

call(
    y_true, y_pred
)

from_config

View source

@classmethod
from_config(
    config
)

get_config

View source

get_config()

__call__

View source

__call__(
    y_true, y_pred, sample_weight=None
)

Call self as a function.