ninatu / everything_at_once

Official implementation of "Everything at Once - Multi-modal Fusion Transformer for Video Retrieval". CVPR 2022
95 stars 18 forks source link

How many GPUs are used & how long is it for training #4

Closed Qichen98fly closed 2 years ago

Qichen98fly commented 2 years ago

What gpus and how many gpus do you use for training? How long does it take?

ninatu commented 2 years ago

Hi! Training our model on the HowTo100M dataset takes approximately 2 days on four Nvidia V100 32GB GPUs. Finetuning on the YouCook2 and the MSR-VTT takes less than 30 minutes.