Is pytorch0.4 compatible with pytorch0.3?

1

I have a lot of code than can be run in the environment of 0.3, but when I directly use them in 0.4. Every time I backward, the usage of memory in GPU will increase. I try to use item instead of data[0], and directly use tensor not Variable, and for training no_grad feature should not be use. So is there any other possibilities?

Thanks!!!

2

Your changes sound good. Is the memory increasing until you get an OOM error?
If so, could you post a small runnable code snippet?