search

2014gaokao / pedestrian-attribute-recognition-with-GCN

Pytorch implementation of pedestrian attribute recognition with graph convolutional network
78 stars 17 forks source link

about loss function #3

Open dmuqlzhang opened 5 years ago

dmuqlzhang commented 5 years ago

excuse me, I want to understand why not add label weight at Multilabelloss function? I think maybe use weighted cross entropy loss will achieve a better result？

abhigoku10 commented 2 years ago

@dmuqlzhang did u try using wce loss did u get better accuracy ?