search

GenjiB / AVSiam

Siamese Vision Transformers are Scalable Audio-visual Learners
7 stars 1 forks source link

Missing Modules #2

Open ThaddaeusWiedemer opened 4 weeks ago

ThaddaeusWiedemer commented 4 weeks ago

Hi,

Unfortunately, I'm unable to reproduce your results since it seems many necessary modules are not part of the repo (e.g., models.cav_mae, models.yb_tome). Also, no guidance is given on how and from where to install these modules and what versions to use.

Could you please provide a working, self-contained version of your code or point me to the correct version of these modules so I can reproduce your work and cite you?

Thanks!

GenjiB commented 3 weeks ago

@ThaddaeusWiedemer Thanks for pointing this out. This version is a bit messy. Give me a few days to fix this.