Giters

fuankarion / active-speakers-context

Code for the Active Speakers in Context Paper (CVPR2020)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Training Time

rahulranjan29 opened this issue · comments

commented

Hi, Thanks for the open source code, I was wondering what time did it take to train the ASC model? Also, Can you please upload the model weight if possible . Thanks!

commented

Hi, the model itself is rather lightweight and both stages (STE & ASC) can be trained on single day with one TitanX GPU (including feature forward).
I just realized the weights are missing, I'll be working on that this week.

commented

Hi, Thanks for the update :)