Lower/Upper Bound Experiments

GMvandeVen / continual-learning

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

MIT License

1.54k stars 310 forks source link

Lower/Upper Bound Experiments #17

Closed kaustubholpadkar closed 3 years ago

kaustubholpadkar commented 3 years ago

How to run "None – lower bound" and "Offline – upper bound" experiments? I am not able to find any flags for that.

GMvandeVen commented 3 years ago

Thanks for your question, I realise this was indeed not clear from the instructions (I just updated the README to make it more clear). You can run these baselines using the following:

None: ./main.py
Offline: ./main.py --replay=offline

Probably it would have been more intuitive to have flags for these baseline approaches. I might change this when I have some time.

kaustubholpadkar commented 3 years ago

Thank you for clearing that up.