Yuandong Tian
Yuandong Tian
better just use ``` model.cuda(args.gpu) ``` to be compatible with both old and new pytorch.
Hi @karandesai-96, we don't have this plan yet. But you definitely can contribute!
No problem @karandesai-96! Looking forward to it.
@karandesai-96 do you still have interest in this direction?
Ok. you need an additional option to load the model: ``` --omit_keys Wt,Wt1,Wt2,Wt3 ``` Please try that first, if that doesn't work, let me know and I will try fixing...
@zhanghongjie101 yes. This is a known issue. I will fix it shortly.
Not sure what is the configuration of your machine? What is the command line? It is quite CPU-heavy because running games require that.
Try adding `GC.reg_callback("train", None)` before `GC.start()` in your script.
Also ELF is updated and the codebase is [here](https://github.com/pytorch/ELF).
Sorry for late reply. Did you solve your problem?