search

kuc2477 / pytorch-ewc

Unofficial PyTorch implementation of DeepMind's PNAS 2017 paper "Overcoming Catastrophic Forgetting"
MIT License
260 stars 44 forks source link

log-likelihood of regression problem #6

Open tytcc opened 4 years ago

tytcc commented 4 years ago

As the code, we can get negative log-likelihood by F.log_softmax. How can I get the log-likelihood of regression problem??

20huaibei commented 2 years ago

As the code, we can get negative log-likelihood by F.log_softmax. How can I get the log-likelihood of regression problem??

Excuse me, I have encountered the same problem recently, I would like to ask if you have solved this problem

Cat-Guijun commented 4 months ago

Hi,have you solved this problem?