https://github.com/prs-eth/film-ensemble
[NeurIPS 2022] FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation
https://github.com/prs-eth/film-ensemble
calibration cifar10 cifar100 deep-learning ece ensemble feature-wise-linear-modulation implicit-ensemble neurips probabilistic-deep-learning pytorch sub-models uncertanity
Last synced: about 1 month ago
JSON representation
[NeurIPS 2022] FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation
- Host: GitHub
- URL: https://github.com/prs-eth/film-ensemble
- Owner: prs-eth
- License: mit
- Created: 2022-09-29T10:33:23.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-12-19T10:53:48.000Z (over 2 years ago)
- Last Synced: 2025-03-24T18:11:23.251Z (2 months ago)
- Topics: calibration, cifar10, cifar100, deep-learning, ece, ensemble, feature-wise-linear-modulation, implicit-ensemble, neurips, probabilistic-deep-learning, pytorch, sub-models, uncertanity
- Language: Python
- Homepage:
- Size: 131 KB
- Stars: 24
- Watchers: 5
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation
Mehmet Ozgur Turkoglu, Alexander Becker, Hüseyin Anil Gündüz, Mina Rezaei, Bernd Bischl, Rodrigo Caye Daudt, Stefano D'Aronco, Jan Dirk Wegner, and Konrad Schindler. - **NeurIPS 2022**.
[ \[Paper on ArXiv\] ](https://arxiv.org/abs/2206.00050) [ \[Poster\] ](https://neurips.cc/media/PosterPDFs/NeurIPS%202022/53071.png?t=1669493329.1428604)
## 🌌 Overview
## ✏️ 📄 Citation
If you find our work useful or interesting, please cite our paper:
```latex
@inproceedings{turkoglu2022film,
title={FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation},
author={Turkoglu, Mehmet Ozgur and Becker, Alexander and G{\"u}nd{\"u}z, H{\"u}seyin Anil and Rezaei, Mina and Bischl, Bernd and Daudt, Rodrigo Caye and D'Aronco, Stefano and Wegner, Jan Dirk and Schindler, Konrad},
booktitle={Advances in Neural Information Processing Systems},
year={2022}
}
```
## Reproducing results: Cifar-10 / Cifar-100
### Installation
```
pip install -r requirements.txt
```
### Training
```
python main.py -e {number of ensemble}