https://github.com/albinsou/online_ema

Code for the CoLLAs 2023 paper "Improving Online Continual Learning Performance and Stability With Temporal Ensemble"
https://github.com/albinsou/online_ema

continual deep-learning learning online

Last synced: 3 months ago
JSON representation

Code for the CoLLAs 2023 paper "Improving Online Continual Learning Performance and Stability With Temporal Ensemble"

• Host: GitHub
• URL: https://github.com/albinsou/online_ema
• Owner: AlbinSou
• License: mit
• Created: 2023-06-19T12:39:52.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2024-01-11T14:05:40.000Z (12 months ago)
• Last Synced: 2024-01-11T20:45:27.442Z (12 months ago)
• Topics: continual, deep-learning, learning, online
• Language: Python
• Homepage: https://arxiv.org/abs/2306.16817
• Size: 5.44 MB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Code for "Improving Online Continual Learning Performance and Stability With Temporal Ensemble"

Code for the paper [Improving Online Continual Learning Performance and Stability With Temporal Ensemble](https://arxiv.org/abs/2306.16817), Soutif--Cormerais et. al., CoLLAs 2023.

The code is based on [Pytorch](https://pytorch.org) and [Avalanche](https://avalanche.continualai.org).

# Installation

Install pytorch with conda ([Instructions](https://pytorch.org))

install the environment and update it using the environment file

```

cd avalanchev3

conda env create -f environment.yml

conda env config vars set PYTHONPATH=online_ema.git_path:avalanchev3_path

```

Change the data directory DATADIR inside toolkit/dataset.py to match the one on your system

Create the results dir

# How to use

To run single experiments, find the appropriate config file in config dir an run

```

python main_noboundaries.py --config config/experiment_config.yml

```

Add the EMA ensembling and parallel evaluation for more efficient continual evaluation

```

python main_noboundaries.py --config config/experiment_config.yml --mean_evaluation --parallel_evaluation --eval_every 1

```

# License

Please check the License file listed in this repository.

# Cite

```

@inproceedings{soutifcormerais2023improving,

  title={Improving Online Continual Learning Performance and Stability with Temporal Ensembles},

  author={Soutif--Cormerais, Albin and Carta, Antonio and Van de Weijer, Joost},

  booktitle={Conference on Lifelong Learning Agents},

  pages={828--845},

  year={2023},

  organization={PMLR}

}

```