Add ICaRL to the CL Baselines

ContinualAI / avalanche

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

http://avalanche.continualai.org

MIT License

1.79k stars 291 forks source link

Add ICaRL to the CL Baselines #4

Closed vlomonaco closed 3 years ago

vlomonaco commented 4 years ago

Add the ICaRL strategy to the main CL Baselines.

akshitac8 commented 4 years ago

@vlomonaco Can I start with this?

lrzpellegrini commented 4 years ago

Hi Akshita, I already wrote and tested the PyTorch code iCaRL (which only needs to be ported to Avalanche).

I had to pause the porting because I'm been working on max priority issues. However, I think I can still handle this!

akshitac8 commented 4 years ago

okay @lrzpellegrini

vlomonaco commented 3 years ago

This is gonna be added soon with a PR by Andrea Rosasco.

Mathieu4141 commented 3 years ago

Are you still working on that @andrew-r96 ? For a school project we implemented iCaRL as a baseline, and we did it using avalanche. The code is not up to date with the latest version of avalanche, but it shouldn't be too much work to clean it. Let me know if you're still on it :)

andrearosasco commented 3 years ago

Hi @Mathieu4141 thanks for the interest :) Yeah I'm still working on it and just opened a PR here https://github.com/ContinualAI/avalanche/pull/637 if you wanna take a look.

Mathieu4141 commented 3 years ago

Great! Yes I'll take a look at your PR 🙂

qsunyuan commented 2 years ago

Hi!

Great work.

Recently I also reproduced iCaRL, but I cannot achieve the original results.

Could u pls share ur CIFAR100 icarl results.

For example, ten tasks which each task has 10 classes.

I cannot achieve the original results, about 49%. How's ur results.

Hope to get ur replay. Best wishes.

vlomonaco commented 2 years ago

Hi @qsunyuan! Results on Cifar100 are reproduced here: https://github.com/ContinualAI/reproducible-continual-learning

qsunyuan commented 2 years ago

THx for ur help, it helps me a lot. Best wishes.