dandelin / ViLT

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Regarding pretraining time

juhongm999 opened this issue · comments

First of all, thanks for great work.
Can you tell us how long the pretraining took on your machine with 64 V100s ?
Thank you in advance

Hi, @juhongm999

I've shared 100k tensorboard log here -> #12 (comment)

You can check the training time there 😃

Thank you for quick reply!