what is details about the experiments for cifar-100

juntang-zhuang / Adabelief-Optimizer

Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"

BSD 2-Clause "Simplified" License

1.05k stars 108 forks source link

what is details about the experiments for cifar-100 #29

Closed XieBinghui closed 3 years ago

XieBinghui commented 3 years ago

Hi, Juntang,

The work is outstanding! If convenient, would you please tell me the details about the experiments for cifar-100? Compared with cifar-10, is there only one difference that you change the output dimension of the last linear layer from 10 to 100? Or are there some other differences?

Looking forward to your reply! Thanks for your nice work again!

juntang-zhuang commented 3 years ago

last layer is the only difference, if I remember correctly.

XieBinghui commented 3 years ago

Thanks for your prompt reply!

juntang-zhuang commented 3 years ago

Happen to be coding now and saw the notification immediately, hahah!