mlnext.score.l2_norm#

mlnext.score.l2_norm(x: ndarray, x_hat: ndarray, *, reduce: bool = True) → ndarray[source]#

Calculates the l2-norm (euclidean distance) for x and x_hat. If reduce is False, then the l2_norm is calculated feature-wise.

Parameters:

  • x (np.ndarray) – ground truth.

  • x_hat (np.ndarray) – prediction.

Returns:

Returns the l2-norm between x and x_hat.

Return type:

np.ndarray

Example

>>> l2_norm(np.array([0.1, 0.2]), np.array([0.14, 0.2]))
np.ndarray([[0.04]])
>>> l2_norm(np.array([0.1, 0.2]), np.array([0.14, 0.2]), reduce=False)
np.ndarray([0.04, 0.0])