MeanAbsoluteError¶

class dragon.vm.tensorflow.keras.losses.MeanAbsoluteError(
  reduction='mean',
  name=None
)[source]¶

A criterion to compute the reduced element-wise absolute value difference.

The AbsoluteError function is defined as:

\[\text{AbsoluteError}(y_{true}, y_{pred}) = |y_{pred} - y_{true}| \]

Examples:

criterion = tf.keras.cost.MeanAbsoluteError()
y_true = tf.constant([1., 2., 3.])
y_pred = tf.constant([0., 0., 0.])
print(criterion(y_true, y_pred))  # 2.0