Training strategy on Imagenet

[Ga-Lee]

Hello! Thank you for your wonderful job!
it is said that as-mlp uses the same training strategy in Swin Transformer, I want to know to what extend the work use the same strategy ? For example, does as-mlp use Mixup、Cutmix?
I saw there exists codes for mixup in function build_loader which requires config.AUG.MIXUP, but I didn't find config.AUG in the config file for models.
I want to know the detailed training setting for your models, may you do the favor for me?

[dongzelian]

@Ga-Lee Thanks so much!
(1) does as-mlp use Mixup、Cutmix? Yes.
(2) where is config.AUG? The config.AUG.MIXUP is here:

AS-MLP/config.py

Line 119 in da82a96

_C.AUG.MIXUP = 0.8

(3) detailed training setting. You can refer to https://github.com/svip-lab/AS-MLP/blob/main/data/build.py, https://github.com/svip-lab/AS-MLP/blob/main/config.py, and Sec. A.2 in Swin Transformer paper (https://arxiv.org/pdf/2103.14030.pdf).

[Ga-Lee]

@dongzelian
Thank you for your kindness and reply!
no more questions, and I will close the issue. : )