Sherrylife

Results 4 comments of Sherrylife

Questions on experimental results (Table 1)

Hi, @vaseline555 , I agree with your results. And I also want to ask can your reproduced the same result using Fedfomo method under the same pathological non=IID setting with...

Memory problem of Lisa finetuning

> It seems that each time new layers are activated, the memory consumption may increase, and layers activated again will not increase the memory consumption. I also found this phenomenon...

Run time statistics

Hi, @benisalla , I am sorry that I can't find the snippet of code I have tried since it has been a long time. I remember the code in this...

n_jobs > 1 takes much more time.

I also observe the same phenomenon.