Jun Zhang
Jun Zhang
After observing many epochs, I found the above issue seems to be normal training loss fluctuation.
still seems to be significant overfitting after 50 epochs...
i met the same problem , have you solve it?
> We have some experiments in suppmat (Figure 12), actually observing worse correlation with resnet. Interestingly, this is consistent with some results in neuroscience on correlating IT responses with deep...
@nn-ww Hi, how did you solve this issue? Thanks!
Thank you @nn-ww . I switch to cmake then everything works fine on a Mac OS system. @WUhailing
Yes, we apply the same processing on both datasets. On Fri, Oct 9, 2020 at 4:35 PM kraKKen wrote: > sure thank you for the reply, and Same goes for...