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
{{ message }}
This repository has been archived by the owner on Mar 19, 2024. It is now read-only.
Looking at the implementation of ModelEmaV2, it seems that compared to timm the model only works on fp32 parameters? (see this line )
Does it mean that it will not work if I use AMP ?
Furthermore, another difference with timm is that the ema_model is not copied (in timm copying is done here ). I am probably missing where the model is copied, can you point it to me please? (if the model is not copied then EMA simply corresponds to momentum)
The text was updated successfully, but these errors were encountered:
YannDubs
changed the title
EMA does not copy weights and does not work on fp16?
EMA does not work on fp16 and does not copy weights?
Sep 14, 2022
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Hi,
Looking at the implementation of ModelEmaV2, it seems that compared to
timm
the model only works on fp32 parameters? (see this line )Does it mean that it will not work if I use AMP ?
Furthermore, another difference with
timm
is that the ema_model is not copied (in timm copying is done here ). I am probably missing where the model is copied, can you point it to me please? (if the model is not copied then EMA simply corresponds to momentum)The text was updated successfully, but these errors were encountered: