Tassilo Wald

Hello, it would be nice if you could add the hyper parameters of RandAugment N and M that were used to get the results for the Datasets.

Hello, thanks for the nice repo and the cool work :) Do you have some trained checkpoints of your models from some of the public datasets that one could use?...

Hello, thanks for providing this repo to your really nice work :) I am wondering if there is any way of getting some final checkpoints of some already trained checkpoints....

Hello, I am currently re-implementing SparK and stumbled over the masking token that gets re-introduced during `densifying`. https://github.com/keyu-tian/SparK/blob/a63e386f8e5186bc07ad7fce86e06b08f48a61ea/pretrain/spark.py#L99C1-L110C9 I was wondering if you tested how important the Mask Tokens are...