Reproduce resnet 18 + relabel about relabel_imagenet HOT 5 OPEN

@John1231983
Thanks for having interests in our paper.
Indeed, our results 72.5% accuracy is obtained without CutMix regularization.
We got a slightly better result (72.8%) with the CutMix trick.
It seems that there is a difference in the number of GPUs, we used 4 but 2 for yours, which makes the minibatch size twice than ours.

from relabel_imagenet.

We used 2 gpus but bsx2 for each gpu. We also evaluate on x2 batch size and 8 gpu but best accuracy is 72.1. Any suggestion?

from relabel_imagenet.

@John1231983
We have run it twice on 4 GPUs and the results were
* Prec@1 72.546 Prec@5 90.478
* Prec@1 72.614 Prec@5 90.432.
Could you run it on 4 GPU setting?

from relabel_imagenet.

Could you maybe provide the config file of this experiment? I´m struggling to reproduce results aswell.

from relabel_imagenet.

@schallko we used the config file for resnet50 training.
Change the architecture to resnet18 at https://github.com/naver-ai/relabel_imagenet/blob/main/configs/relabel_train_resnet50.yaml#L2

from relabel_imagenet.