SJShin-AI

memory leakage problem when loss.backward()

14

Hi. How can i solve memory leakage problem on loss.backward? Actually my code is a bit complex, which makes it hard to provide whole. The main memory burden comes from...

Simultaneous computation of per-sample gradient and per-batch gradient

1

Hi. Thanks for providing functorch, one of most effective lib. Actually i am working on my code which needs an access into both per-sample gradient in mini-batch and per-batch gradient,...

Further explanation about the degraded performance of baselines than random sampling.

8

First of all, thank you so much for providing such a good github repository. I ran the code myself, and the code is very reproducible and helpful to concatenate my...