Conversation
Co-authored-by: vfdev <[email protected]>
Co-authored-by: vfdev <[email protected]>
|
@kzkadc can you please check this failure with pytorch 1.5.1: https://github.com/pytorch/ignite/actions/runs/8730344048/job/23953994151
Looks like |
|
Thanks. The kl_div's behaviour in 1.5.1 is equivalent to log_target=False (default) in the current version. |
|
we can also make a small if-else depending on pytorch version. For example: ignite/ignite/metrics/gan/fid.py Line 15 in f431e60 Using log_target may be has better computation result stability (to confirm), so, for recent pytorch it would be better to use this option if it makes more sense to use vs keeping default |
Description: added KL and JS divergences between two categorical predictions
Check list: