如下所示，我想在bn之后获取当前的moving_mean和moving_variance的值（不是基于fetch list），再基于该值做一些额外的操作，想问下这个怎么实现呢？

temp_y = fluid.layers.batch_norm(
            input=conv,
            act=act,
            param_attr=ParamAttr(name=bn_name + '_scale'),
            bias_attr=ParamAttr(bn_name + '_offset'),
            moving_mean_name=bn_name + '_mean',
            moving_variance_name=bn_name + '_variance')
y = some_func(moving_mean, moving_variance, temp_y)