tf.keras.losses.MeanAbsoluteError

Computes the mean of absolute difference between labels and predictions.

Used in the notebooks

Used in the tutorials

loss = abs(y_true - y_pred)

Standalone usage:

y_true = [[0., 1.], [0., 0.]]
y_pred = [[1., 1.], [1., 0.]]
# Using 'auto'/'sum_over_batch_size' reduction type.
mae = tf.keras.losses.MeanAbsoluteError()
mae(y_true, y_pred).numpy()
0.5
# Calling with 'sample_weight'.