Keras: weighted binary crossentropy

Question

I tried to implement a weighted binary crossentropy with Keras, but I am not sure if the code is correct. The training output seems to be a bit confusing. After a few epochs I j

Answer 1

You can calc the weights like this and have the binary cross entropy like this which will programmatically put one_weight to 0.11 and one to 0.89:

one_weight = (1-num_of_ones)/(num_of_ones + num_of_zeros)
zero_weight = (1-num_of_zeros)/(num_of_ones + num_of_zeros)

def weighted_binary_crossentropy(zero_weight, one_weight):

    def weighted_binary_crossentropy(y_true, y_pred):

        b_ce = K.binary_crossentropy(y_true, y_pred)

        # weighted calc
        weight_vector = y_true * one_weight + (1 - y_true) * zero_weight
        weighted_b_ce = weight_vector * b_ce

        return K.mean(weighted_b_ce)

    return weighted_binary_crossentropy