tf.keras.losses.MAE

TensorFlow 2 version

View source on GitHub

View aliases

Main aliases

tf.keras.losses.mae, tf.keras.losses.mean_absolute_error, tf.keras.metrics.MAE, tf.keras.metrics.mae, tf.keras.metrics.mean_absolute_error

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.losses.MAE, tf.compat.v1.keras.losses.mae, tf.compat.v1.keras.losses.mean_absolute_error, tf.compat.v1.keras.metrics.MAE, tf.compat.v1.keras.metrics.mae, tf.compat.v1.keras.metrics.mean_absolute_error, `tf.compat.v2.keras.losses.MAE`, `tf.compat.v2.keras.losses.mae`, `tf.compat.v2.keras.losses.mean_absolute_error`, `tf.compat.v2.keras.metrics.MAE`, `tf.compat.v2.keras.metrics.mae`, `tf.compat.v2.keras.metrics.mean_absolute_error`, `tf.compat.v2.losses.MAE`, `tf.compat.v2.losses.mae`, `tf.compat.v2.losses.mean_absolute_error`, `tf.compat.v2.metrics.MAE`, `tf.compat.v2.metrics.mae`, `tf.compat.v2.metrics.mean_absolute_error`

tf.keras.losses.MAE(
    y_true, y_pred
)

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.

Last updated 2020-10-01 UTC.