tf.keras.losses.Tversky

Computes the Tversky loss value between y_true and y_pred.

Inherits From: Loss

tf.keras.losses.Tversky(
    alpha=0.5,
    beta=0.5,
    reduction='sum_over_batch_size',
    name='tversky'
)

This loss function is weighted by the alpha and beta coefficients that penalize false positives and false negatives.

With alpha=0.5 and beta=0.5, the loss value becomes equivalent to Dice Loss.

Args
y_true	tensor of true targets.
y_pred	tensor of predicted targets.
alpha	coefficient controlling incidence of false positives.
beta	coefficient controlling incidence of false negatives.

Returns
Tversky loss value.

Reference:

• Salehi et al., 2017

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.