Experimental results of this work on 200 epochs on CIFAR and Tiny-ImageNet

[pc-cp]

Hi, thank you very much for your work showing the good properties exhibited by the use of mix in self-supervision learning. I try to reproduce your idea in BYOL, but I have some confusions: 1. In case of self-mixtures, is it better to use mix images in momentum branches or branches with gradient updates? If you have results for 200 epochs would be much appreciated. Thanks again for your work!