search

cdoersch / vae_tutorial

Caffe code to accompany my Tutorial on Variational Autoencoders
MIT License
500 stars 134 forks source link

Confused of loss=nan #1

Closed EnQing626 closed 8 years ago

EnQing626 commented 8 years ago

I have some trouble happening with loss=nan. I am confused why it happened by using my own data. I modify the "batch size" from 100 to 1, and then, modify the param of "Dummydata" shape dim from 100 to 1. But I don't know whether should I modify Reduction loss_weight. Is that the key factor influencing the mistake result loss=nan?

cdoersch commented 8 years ago

Sorry CJEQ, I think StackOverflow would be a better place for a question like this. I want to keep the github issues for this project focused on potential changes to the codebase that's hosted here.