quantus.functions.loss_func module

This module holds a collection of loss functions i.e., ways to measure the loss between two inputs.

quantus.functions.loss_func.mse(a: array, b: array, batched: bool = False, **kwargs) → float

Calculate Mean Squared Error between two images (or explanations).

Parameters:

a: np.ndarray

Array to calculate MSE with.

b: np.ndarray

Array to calculate MSE with.

batched: bool

True if arrays are batched. Arrays are expected to be 2D (B x F), where B is batch size and F is the number of features

kwargs: optional

Keyword arguments.

normalise_mse: boolean

Indicates whether to returned a normalised MSE calculation or not.

Returns:

float:

A floating point of MSE.