Liu Jiashuo

icon indicating a website link https://ljsthu.github.io icon indicating an email [email protected]

icon company Tsinghua University icon location Beijing icon location Ph.D. Candidate @THU-TAI | Remote @namkoong-lab | VSR @Stanford MS&E

Results 3 comments of Liu Jiashuo

Loss became 'nan' after 10000~20000 epochs

Thanks for your reply. I am training the network on the kanji dataset, and I found the results are not acceptable even after 20000 epochs. Have you ever met this...

Loss became 'nan' after 10000~20000 epochs

I ran your code and the author's code on kanji dataset, but I found that the KL loss in your code was increasing while it was decreasing in the author's...

Loss became 'nan' after 10000~20000 epochs

It was increasing from the beginning. I think you did a good job and the code is quite clear. I think the way you calculated the kl loss was right...