tf.keras.losses.MSLE

TensorFlow 1 version View source on GitHub

Computes the mean squared logarithmic error between y_true and y_pred.

tf.keras.losses.MSLE(
    y_true, y_pred
)

loss = mean(square(log(y_true + 1) - log(y_pred + 1)), axis=-1)

Usage:

y_true = np.random.randint(0, 2, size=(2, 3))
y_pred = np.random.random(size=(2, 3))
loss = tf.keras.losses.mean_squared_logarithmic_error(y_true, y_pred)
assert loss.shape == (2,)
y_true = np.maximum(y_true, 1e-7)
y_pred = np.maximum(y_pred, 1e-7)
assert np.array_equal(
    loss.numpy(),
    np.mean(
        np.square(np.log(y_true + 1.) - np.log(y_pred + 1.)), axis=-1))

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

Mean squared logarithmic error values. shape = [batch_size, d0, .. dN-1].