search

megvii-research / mdistiller

The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf
808 stars 123 forks source link

Validation Splits #45

Closed m-parchami closed 1 year ago

m-parchami commented 1 year ago

Hi,

Thanks for the great repo!

I was wondering if for CIFAR-100 and Imagenet there's also a "validation" (as a heldout subset of training set) is being created somewhere in the code? Because as I looked for it, it seems that we only have a train_dataset and test_dataset.

All the best. Thanks again for the code :)

Zzzzz1 commented 1 year ago

The test_dataset in the repo is actually the validation set that we use 😂.