How to add multiple object ability in RAM model?

[machanic]

This source code only have ability to trace and classify only one object in image.
according to arXiv:1412.7755 .
If a image has multi-label, for example, more than one mnist digits were place on the image.
after read a paper arxiv:1402.7755v2,
I thought the paper written: the multi-target learning is just a sequential learning of one-target learning for many times which is equal to the objects number in one image.
and sum the loss up to back-prop.
When I modify the code to do it, I failed! The RAM model seemed only want to find the first objects it discovered and don't care the rest of the objects.