Giters

MartinXM / GAP

official implementation for Language Supervised Training for Skeleton-based Action Recognition

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About NW-UCLA

SunPengP opened this issue · comments

commented

Hello, when i tried to use CTR-GCN to train NW-UCLA, i got 95.5 accurancy , 1% lower than the result CTR-GCN given.
Did you meet the same problem in your experiments.

commented

You may need to tune the weights of different modals.

commented

Hello, when i tried to use CTR-GCN to train NW-UCLA, i got 95.5 accurancy , 1% lower than the result CTR-GCN given. Did you meet the same problem in your experiments.

You may need to tune the weights of different modals.

Thank you for your reply. Is this how you handled your experiment