search

kenziyuliu / DGNN-PyTorch

Unofficial PyTorch implementation of the CVPR'19 paper "Skeleton-Based Action Recognition with Directed Graph Neural Networks".
Other
235 stars 59 forks source link

请问您为什么你的关节预处理的结果 跟2sagcn的差别很大 不一样为什么 #17

Closed dangao250 closed 4 years ago

dangao250 commented 4 years ago

May I ask why your joint pretreatment results are very different from 2sagcn? Why?

kenziyuliu commented 4 years ago

Hi there, most preprocessing files are copied directly from 2s-AGCN, including the joint data preprocessing logic. You can verify this by running diff on the files in data_gen/ to those in https://github.com/lshiwjx/2s-AGCN/tree/master/data_gen.