augmentation and regularization used in MLP-Mixer

[Ga-Lee]

Hello! Thank you for your work!
In the paper of MLP-Mixer, when training mixer-B/16 on imagenet1k from scratch, it is said extra regularization is applied to gain the the accuracy of 76% , I want to know what detailed augmentation and regularization strategy is used for the experiment? Is there any config file can be found?
Thank you for your help! : )

[akolesnikoff]

Hi!

I've just submitted the MLP-Mixer code, as well as the configuration that achieves 76% top-1 ImageNet with MLP-Mixer-B/16 model: https://github.com/google-research/big_vision/blob/main/big_vision/configs/mlp_mixer_i1k.py. Let me know if you have any further questions.

[Ga-Lee]

Hi!

I've just submitted the MLP-Mixer code, as well as the configuration that achieves 76% top-1 ImageNet with MLP-Mixer-B/16 model: https://github.com/google-research/big_vision/blob/main/big_vision/configs/mlp_mixer_i1k.py. Let me know if you have any further questions.

Got it !
Thank you for your reply!