ContinualAI/avalanche

Using validation set for early stopping

Open

#904 ouverte le 4 févr. 2022

Voir sur GitHub
 (0 commentaires) (0 réactions) (0 assignés)Python (258 forks)batch import
Evaluationbuggood first issue

Métriques du dépôt

Stars
 (1 516 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

Discussed in https://github.com/ContinualAI/avalanche/discussions/900

Originally posted by sivomke January 30, 2022 Hi, everyone!

I have created a benchmark with dataset_benchmark that contains 3 experiences, and then have added a validation set to this benchmark with benchmark_with_validation_stream. I am trying to use Early Stopping with validation set: for each experience, I would like to use loss on the validation set of the corresponding experience. I have indicated metric_name = 'Loss_Exp' and val_stream_name='valid' , however, it still uses Loss_Exp/eval_phase/train_stream of the corresponding experience instead. Could you please tell me what would be the correct way to use validation set for early stopping?

Here is the script

Thank you!

Guide contributeur