arthurdouillard / incremental_learning.pytorch

A collection of incremental learning paper implementations including PODNet (ECCV20) and Ghost (CVPR-W21).
MIT License
383 stars 60 forks source link

E2E code is not using exemplars #9

Closed Akella17 closed 5 years ago

Akella17 commented 5 years ago

Where is the train loader being appended with old class exemplars in E2E model. For instance, before doing this, shouldn't we be updating the train loader by adding the old-class exemplars aswell?

arthurdouillard commented 5 years ago

My online code is not up to date, especially for E2E but yes it was using the examplars.

See iCaRL to adapt E2E to use my new way of handling examplars.