FSCE
FSCE copied to clipboard
Can not reproduce the split1 shot5 result
I followed the guidance of README (without any change) to pretrain a base model and then randomly initilize the novel weights, finally finetune it.But I get a best result of nap of only 58.8,there is a big gap between my result and the result given in paper.How come
And I wanna konw whether the config files shown in the repo is the same as the ones you use in your experiment
Recently, I repeat a lot of runs,finally get a better result of 60.16.
最近,我重复了很多次,终于得到了一个更好的结果,60.16。
Hi,how many GPUs did you use, thank you.