Function _bald_divergence

modAL/dropout.py:366–402

Calculates the bald divergence for each instance As it is explicitly formulated in: Deep Bayesian Active Learning with Image Data. (Yarin Gal, Riashat Islam, and Zoubin Ghahramani. 2017.) Args: proba: list with the predictions over th

(proba: list)

def _bald_divergence(proba: list) -> np.ndarray:
    """
        Calculates the bald divergence for each instance

        As it is explicitly formulated in: 
            Deep Bayesian Active Learning with Image Data. 
            (Yarin Gal, Riashat Islam, and Zoubin Ghahramani. 2017.)

        Args: 
            proba: list with the predictions over the dropout cycles
            mask: mask to detect the padded classes (must be of same shape as elements in proba)
        Return: 
            Returns the mean standard deviation of the dropout cycles over all classes. 
    """
    proba_stacked = np.stack(proba, axis=len(proba[0].shape))

    # entropy along dropout cycles
    accumulated_entropy = entropy_sum(proba_stacked, axis=-1)
    f_x = accumulated_entropy/len(proba)

    # score sums along dropout cycles
    accumulated_score = np.sum(proba_stacked, axis=-1)
    average_score = accumulated_score/len(proba)
    # expand dimension w/o data for entropy calculation
    average_score = np.expand_dims(average_score, axis=-1)

    # entropy over average prediction score
    g_x = entropy_sum(average_score, axis=-1)

    # entropy differences
    diff = np.subtract(g_x, f_x)

    # sum all dimensions of diff besides first dim (instances)
    shaped = np.reshape(diff, (diff.shape[0], -1))

    bald = np.sum(shaped, where=~np.isnan(shaped), axis=-1)
    return bald


def set_dropout_mode(model, dropout_layer_indexes: list, train_mode: bool):