Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/qsh-zh/DiffFlow
[Neurips 2021]Diffusion Normalizing Flow (DiffFlow)
https://github.com/qsh-zh/DiffFlow
Last synced: 14 days ago
JSON representation
[Neurips 2021]Diffusion Normalizing Flow (DiffFlow)
- Host: GitHub
- URL: https://github.com/qsh-zh/DiffFlow
- Owner: qsh-zh
- License: mit
- Created: 2021-10-06T04:10:11.000Z (about 3 years ago)
- Default Branch: master
- Last Pushed: 2023-09-13T15:49:28.000Z (about 1 year ago)
- Last Synced: 2024-08-01T16:52:39.553Z (3 months ago)
- Language: Python
- Homepage: https://arxiv.org/abs/2110.07579
- Size: 727 KB
- Stars: 116
- Watchers: 3
- Forks: 13
- Open Issues: 5
-
Metadata Files:
- Readme: readme.md
- License: LICENSE
Awesome Lists containing this project
README
# Diffusion Normalizing Flow (DiffFlow)
![DiffFlow](asserts/DiffFlow_fig1.png)
![DiffFlow](asserts/DiffFlow_tree.png)## Reproduce
### setup environment
The repo heavily depends on [jam](https://github.com/qsh-zh/jam), a personal toolbox developed by [Qsh.zh](https://github.com/qsh-zh). The API may change and check the [jammy](https://jammy.readthedocs.io/en/stable/index.html) version for running the repo.
*pip*
```shell
pip install .
```*[poetry](https://python-poetry.org/)*
```shell
curl -fsS -o /tmp/get-poetry.py https://raw.githubusercontent.com/sdispater/poetry/master/get-poetry.py
python3 /tmp/get-poetry.py -y --no-modify-path
export PATH=$HOME/.poetry/bin:$PATH
poetry shell
poetry install
```### Run
```shell
python main.py trainer.epochs=100 data.dataset=tree
```The repo supports viz results on [wandb](https://wandb.ai/site)
```shell
python main.py trainer.epochs=100 data.dataset=tree log=true wandb.project=pub_diff wandb.name=tree
```There are some [results](https://wandb.ai/qinsheng/pub_diff?workspace=user-qinsheng) reproduced by the repo.
## Reference
```tex
@inproceedings{zhang2021diffusion,
author = {Qinsheng Zhang and Yongxin Chen},
title = {Diffusion Normalizing Flow},
booktitle = {Advances in Neural Information Processing Systems},
year = {2021}
}
```