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
I am currently struggling a lot with implementing a hyperparameter tuning strategy for my detectron2 model (resnet50 for object detection). I only found this threat about how RayTune can't be implemented, because of how the dataset registration works: #3057 - and until now couldn't find any working/practical tipps on a working solution. Has anyone managed to implement a hyperparameter tuning library/workflow for a detectron2 model? I find it very surprising that this is made so hard by the makers of detectron2. ANY HELP GREATLY APPRECIATED! THANKS :)
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hey community,
I am currently struggling a lot with implementing a hyperparameter tuning strategy for my detectron2 model (resnet50 for object detection). I only found this threat about how RayTune can't be implemented, because of how the dataset registration works: #3057 - and until now couldn't find any working/practical tipps on a working solution. Has anyone managed to implement a hyperparameter tuning library/workflow for a detectron2 model? I find it very surprising that this is made so hard by the makers of detectron2. ANY HELP GREATLY APPRECIATED! THANKS :)
Beta Was this translation helpful? Give feedback.
All reactions