tf.keras.losses.MAE

View source on GitHub

Computes the mean absolute error between labels and predictions.

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, tf.losses.MAE, tf.losses.mae, tf.losses.mean_absolute_error, tf.metrics.MAE, tf.metrics.mae, tf.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.keras.losses.MAE(
    y_true, y_pred
)

loss = mean(abs(y_true - y_pred), axis=-1)

Standalone usage:

y_true = np.random.randint(0, 2, size=(2, 3))
y_pred = np.random.random(size=(2, 3))
loss = tf.keras.losses.mean_absolute_error(y_true, y_pred)
assert loss.shape == (2,)
assert np.array_equal(
    loss.numpy(), np.mean(np.abs(y_true - y_pred), axis=-1))

Args
y_true	Ground truth values. shape = [batch_size, d0, .. dN].
y_pred	The predicted values. shape = [batch_size, d0, .. dN].

Returns
Mean absolute error values. shape = [batch_size, d0, .. dN-1].