tf.keras.losses.Dice | TensorFlow v2.16.1 (original) (raw)

tf.keras.losses.Dice

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'
)

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.

call(
    y_true, y_pred
)

@classmethod from_config( config )

get_config()

__call__(
    y_true, y_pred, sample_weight=None
)

Call self as a function.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-06-07 UTC.