The code of Sec. V(E) - Githubissues

Chiaraplizz / ST-TR

Spatial Temporal Transformer Network for Skeleton-Based Activity Recognition

MIT License

294 stars 57 forks source link

The code of Sec. V(E) #19

Closed 1iuhongzhe closed 3 years ago

1iuhongzhe commented 3 years ago

I want to use spatial TR as an augmentation to improve my code, and i have seen the paper(Sec. V(E)), but i cant find the precise location. Could you help me to find where it is? Thanks a lot.

Chiaraplizz commented 3 years ago

Hi,

Sorry for my delay in the response. If you set only_temporal_attention: False (for T-TR) or only_attention: False (for S-TR) in the configuration file it automatically concatenates features obtained both from self-attention and from standard convolution.

Chiara