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
Thanks a lot for the implementation, it's great to have to have all three possibilities in the same code-base to be able to benchmark those.
We have something similar in Asteroid, (PITLossWrapper)[https://github.com/mpariente/asteroid/blob/master/asteroid/losses/pit_wrapper.py#L8], which can convert any loss function into a PIT loss function.
I've had a look at the Hungarian algorithm in the past and thought about integrating it but I thought the time spent on CPU-GPU transfers would outweigh the gain of the Hungarian algorithm.
I cannot access your paper so I don't see if you made the experiments, but I guess yes. Did you actually gain some time or lose some time when using OPTMLoss against FastPITLoss?
Thanks,
Manu
The text was updated successfully, but these errors were encountered:
Thanks a lot for the implementation, it's great to have to have all three possibilities in the same code-base to be able to benchmark those.
We have something similar in Asteroid, (
PITLossWrapper
)[https://github.com/mpariente/asteroid/blob/master/asteroid/losses/pit_wrapper.py#L8], which can convert any loss function into a PIT loss function.I've had a look at the Hungarian algorithm in the past and thought about integrating it but I thought the time spent on CPU-GPU transfers would outweigh the gain of the Hungarian algorithm.
I cannot access your paper so I don't see if you made the experiments, but I guess yes. Did you actually gain some time or lose some time when using
OPTMLoss
againstFastPITLoss
?Thanks,
Manu
The text was updated successfully, but these errors were encountered: