search

ContinualAI / avalanche

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.
http://avalanche.continualai.org
MIT License
1.77k stars 289 forks source link

Multi-Run Support for Avalanche Experiments #378

Open vlomonaco opened 3 years ago

vlomonaco commented 3 years ago

We should support averaging results across multiple runs. This is related to #300.

AntonioCarta commented 3 years ago

I would prefer to keep the training module (and corresponding tag) for CL algorithms. Model selection techniques and evaluation methods (such as averaging multiple results) should belong to the evaluation module.

vlomonaco commented 3 years ago

This is also related to #579