How to store accuracies for each experience during training?

ContinualAI / avalanche

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

http://avalanche.continualai.org

MIT License

1.79k stars 292 forks source link

How to store accuracies for each experience during training? #1643

Closed dajuguan closed 6 months ago

dajuguan commented 6 months ago

I want export some post result to plot benchmark figures like what's in "Overcoming catastrophic forgetting in neural networks", but currently I find I can get average accuracies for all tasks. I was wondering how to do this, thanks?

dajuguan commented 6 months ago

I‘ve figured out that I just need to implement a customized plugin.