search

SHI-Labs / Compact-Transformers

Escaping the Big Data Paradigm with Compact Transformers, 2021 (Train your Vision Transformers in 30 mins on CIFAR-10 with a single GPU!)
https://arxiv.org/abs/2104.05704
Apache License 2.0
495 stars 77 forks source link

validation set #59

Closed ireneb612 closed 2 years ago

ireneb612 commented 2 years ago

Hi! I started training your model on my data, and after some reserach I did not manage to understand how the validation set should be made in terms of directories! I know it's timm library, but I was wondering if you could help me.

My training data il like this: -/train/0/class1/ .....jpeg class2/ ..... class3/.... class4/....

How and where should I position my validation folder?

alihassanijr commented 2 years ago

Hello,

The default is val/, but it can be overridden using the --val-split argument.