Trying to reproduce human Semantic Parsing in pytorch

Hello, I am a Postgraduate in Beijing University in China. I am trying to reproduce human Semantic parsing in pytorch, I have seen your code in your release code. In my code, I have reproduce the netword in human semantic parsing , which is same as yours human semantic parsing in pytorch. and I use interplot 30*30-----> 512*512 and cross_entropy to measure loss between results and ground label，when I train in LIP, its results is so bad. I have seen the LIP paper to learn the ASPP. And I have tried to load your released model parameter in LIP_iter_30000.chainermodel to pytorch. But it doesn't work, the results is so bad, I can't see any segmentation in picture. So I think maybe there is something wrong about my code. So if you are free, please tell how to train the semantic parsing.
My email: 17120413@bjtu.edu.cn .