tf.keras.losses.MAPE

Computes the mean absolute percentage error between y_true & y_pred.

Formula:

loss = 100 * mean(abs((y_true - y_pred) / y_true), axis=-1)

Division by zero is prevented by dividing by maximum(y_true, epsilon) where epsilon = keras.backend.epsilon() (default to 1e-7).

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

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

Example:

y_true = np.random.random(size=(2, 3))
y_pred = np.random.random(size=(2, 3))
loss = keras.losses.mean_absolute_percentage_error(y_true, y_pred)