tf.keras.losses.MAE
Stay organized with collections
Save and categorize content based on your preferences.
Computes the mean absolute error between labels and predictions.
tf.keras.losses.MAE(
y_true, y_pred
)
Used in the notebooks
loss = mean(abs(y_true - y_pred), axis=-1)
Args |
|---|
y_true
|
Ground truth values with shape = [batch_size, d0, .. dN].
|
y_pred
|
The predicted values with shape = [batch_size, d0, .. dN].
|
Returns |
|---|
Mean absolute error values with shape = [batch_size, d0, .. dN-1].
|
Example:
y_true = np.random.randint(0, 2, size=(2, 3))
y_pred = np.random.random(size=(2, 3))
loss = keras.losses.mean_absolute_error(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. Some content is licensed under the numpy license.
Last updated 2024-06-07 UTC.
[null,null,["Last updated 2024-06-07 UTC."],[],[],null,["# tf.keras.losses.MAE\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/losses/losses.py#L1161-L1195) |\n\nComputes the mean absolute error between labels and predictions.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.keras.losses.mae`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/MAE), [`tf.keras.metrics.MAE`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/MAE), [`tf.keras.metrics.mae`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/MAE)\n\n\u003cbr /\u003e\n\n tf.keras.losses.MAE(\n y_true, y_pred\n )\n\n### Used in the notebooks\n\n| Used in the tutorials |\n|----------------------------------------------------------------------------------------|\n| - [Intro to Autoencoders](https://www.tensorflow.org/tutorials/generative/autoencoder) |\n\n loss = mean(abs(y_true - y_pred), axis=-1)\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------|--------------------------------------------------------------|\n| `y_true` | Ground truth values with shape = `[batch_size, d0, .. dN]`. |\n| `y_pred` | The predicted values with shape = `[batch_size, d0, .. dN]`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| Mean absolute error values with shape = `[batch_size, d0, .. dN-1]`. ||\n\n\u003cbr /\u003e\n\n#### Example:\n\n y_true = np.random.randint(0, 2, size=(2, 3))\n y_pred = np.random.random(size=(2, 3))\n loss = keras.losses.mean_absolute_error(y_true, y_pred)"]]
View source on GitHub