search

jhjacobsen / invertible-resnet

Official Code for Invertible Residual Networks
MIT License
517 stars 78 forks source link

a question about using large image to run classification #16

Open Christian-lyc opened 4 years ago

Christian-lyc commented 4 years ago

Hi, thank you so much for providing the code. I want to run it in my own dataset. I just set the batch size to 1 and even use 6 layers with 896*448 image, but still out of memory. Do you know how this error happens? Are there some ways to solve it? Thank you.

jhjacobsen commented 4 years ago

Did you switch off log determinant computation?

Christian-lyc commented 4 years ago

Thank you for your reply. I think yes. I set this: ignore_logdet=True.