Maskrcnn-benchmark: Save best model
❓ Questions and Help
I don't see the best model on validation being saved. Did I miss it or it wasn't really implemented?
If not implemented, any reason why?
wesleylp
All 2 comments
Hi,
We currently save all the checkpoints, and only perform validation in the end model.
We could perform validation after every checkpoint, but that's not implemented ATM (and follows what was implemented in Detectron).
I agree though that it would be nice to have evaluation after every checkpoint. The way it was implemented was to have a watcher job which would wait for checkpoints to be available and it would kick evaluation right away, on a separate machine.
fmassa
on 8 Jan 2019
👍2
👀1
@fmassa Hi there. Is this still on the cards? this would be a great feature in my opinion.
sno6
on 23 Feb 2020
Was this page helpful?
0 / 5 - 0 ratings
Related issues
jbitton
·
4Comments
Jinksi
·
3Comments
IenLong
·
4Comments
nanyoullm
·
3Comments
krumo
·
3Comments
Most helpful comment
Hi,
We currently save all the checkpoints, and only perform validation in the end model.
We could perform validation after every checkpoint, but that's not implemented ATM (and follows what was implemented in Detectron).
I agree though that it would be nice to have evaluation after every checkpoint. The way it was implemented was to have a watcher job which would wait for checkpoints to be available and it would kick evaluation right away, on a separate machine.