TengdaHan/TemporalAlignNet

About pre-training hardware

tomchen-ctj opened this issue · 2 comments

Hi,

Thank you for your solid work and code releases.
May I ask how many GPUs are used in the basic TAN pre-training? (Sorry if I missed that description in your paper)

Thanks!

Hi, the basic TAN pre-training is on frozen visual features, so it requires fewer GPUs.
I mostly use only one GPU (but with 48gb gpu-memory) for one experiment.

I see, thank you!