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
Is your feature request related to a problem? Please describe.
When running the training script, there is no way to stop training early when performance plateaus.
This causes 2 problems:
Wasting resources because we continue training as the model does not improve
Overfitting since early stopping is a form of regularization
Describe the solution you'd like
I would like to add an early-stopping feature to the training script.
This would involve a few parameters:
The metric to monitor
Whether to minimize or maximize that metric
Number of steps or epochs to wait for an improvement
The delta in the metric to determine if it is an improvement
Describe alternatives you've considered
Many other CV training platforms offer early stopping. I would like to have early stopping in TIMM because I prefer this repo over others.
The text was updated successfully, but these errors were encountered:
you could easily modify the train.py script adding your own EarlyStopping method, it's straightforward.
You just have to gather validation losses (eval_metrics, line 813), select the metric you want to monitor (top1 for instance), and use it as a stopping criteria.
Is your feature request related to a problem? Please describe.
When running the training script, there is no way to stop training early when performance plateaus.
This causes 2 problems:
Describe the solution you'd like
I would like to add an early-stopping feature to the training script.
This would involve a few parameters:
Describe alternatives you've considered
Many other CV training platforms offer early stopping. I would like to have early stopping in TIMM because I prefer this repo over others.
The text was updated successfully, but these errors were encountered: