datasets/ClassPrioritySampler.py [433:439]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        balanced_weights *= self.num_samples / balanced_weights.sum() * \
                            self.balance_scale
        return balanced_weights

    def __iter__(self):
        for _ in range(self.num_samples):
            w = random.random() * self.ptree.total
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



datasets/MixedPrioritizedSampler.py [310:316]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        balanced_weights *= self.num_samples / balanced_weights.sum() * \
                            self.balance_scale
        return balanced_weights

    def __iter__(self):
        for _ in range(self.num_samples):
            w = random.random() * self.ptree.total
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -