You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
I use the SAmodule and FPmodule in my network, I try setting all random seeds for torch, numpy and random. However, the results are still not deterministic. Then I check the model, I find that with the same input, the SAmodule will give different outputs. Is there some way to make the SAmodule deterministic?
I think the potential reason for this is that it uses some functions implemented in C, then the random seed cannot be controlled. Do you have some idea on this?
The text was updated successfully, but these errors were encountered:
I found out the atomicAdd() function in the .cu file is not fixed in order when called, resulting in a numerical error in the sum of floating points as a result of gradient calculations.
I also found that many networks are based on this package, and how do they deal with this non-determinism?
If determinism is not guaranteed, ablation experiments can be cumbersome.
Thank you!
Hi,
I use the SAmodule and FPmodule in my network, I try setting all random seeds for torch, numpy and random. However, the results are still not deterministic. Then I check the model, I find that with the same input, the SAmodule will give different outputs. Is there some way to make the SAmodule deterministic?
I think the potential reason for this is that it uses some functions implemented in C, then the random seed cannot be controlled. Do you have some idea on this?
The text was updated successfully, but these errors were encountered: