qcsbm
[ICML 2023] On Investigating the Conservative Property of Score-Based Generative Models
Science Score: 41.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.9%) to scientific vocabulary
Keywords
Repository
[ICML 2023] On Investigating the Conservative Property of Score-Based Generative Models
Basic Info
- Host: GitHub
- Owner: chen-hao-chao
- License: apache-2.0
- Language: Python
- Default Branch: master
- Homepage: https://chen-hao-chao.github.io/qcsbm/
- Size: 11.5 MB
Statistics
- Stars: 1
- Watchers: 2
- Forks: 1
- Open Issues: 0
- Releases: 0
Topics
Metadata Files
README.md
On Investigating the Conservative Property of Score-Based Generative Models
This repository contains the code implementation of the experiments presented in the paper On Investigating the Conservative Property of Score-Based Generative Models.
The project page is available at: https://chen-hao-chao.github.io/qcsbm/
Directory Structure
- Use the code in qcsbm/gaussian_example to reproduce the experimental results presented in Section 3.1.
- Use the code in qcsbm/2d_examples to reproduce the experimental results presented in Section 3.2.
- Use the code in qcsbm/real_world to reproduce the experimental results presented in Section 5.
- Use the code in qcsbm/autoencoder_example to reproduce the experimental results presented in Section 6.
Dependencies
(Optional) Launch a docker container:
```sh
assume the current directory is the root of this repository
docker run --rm -it --gpus all --ipc=host -v$(pwd):/app nvcr.io/nvidia/pytorch:20.12-py3
inside the docker container, run:
cd /app ```
Install the necessary Python packages through the following commands:
pip install -r requirements.txt --use-feature=2020-resolver
Citing QCSBM
If you find this code useful, please consider citing our paper.
bib
@inproceedings{chao2023investigating,
title={On Investigating the Conservative Property of Score-Based Generative Models},
author={Chen-Hao Chao and Wei-Fang Sun and Bo-Wun Cheng and Chun-Yi Lee},
year={2023},
booktitle={International Conference on Machine Learning (ICML)},
}
License
To maintain reproducibility, we freezed the following repository and list its license below: - yang-song/scoresdepytorch (at commit 1618dde) is licensed under the Apache-2.0 License
Further changes based on the repository above are licensed under the Apache-2.0 License.
Owner
- Name: Lance Chao
- Login: chen-hao-chao
- Kind: user
- Location: Taipei
- Company: National Tsing Hua University
- Repositories: 2
- Profile: https://github.com/chen-hao-chao
NTHU CS
Citation (CITATION.bib)
@inproceedings{chao2023investigating,
title={On Investigating the Conservative Property of Score-Based Generative Models},
author={Chen-Hao Chao and Wei-Fang Sun and Bo-Wun Cheng and Chun-Yi Lee},
year={2023},
booktitle={International Conference on Machine Learning (ICML)},
}
GitHub Events
Total
- Watch event: 1
- Fork event: 1
Last Year
- Watch event: 1
- Fork event: 1
Dependencies
- absl-py ==0.10.0
- celluloid *
- jax *
- jaxlib *
- matplotlib *
- ml-collections ==0.1.0
- ninja *
- numpy ==1.23
- pandas *
- prdc *
- protobuf ==3.20.3
- scikit-learn *
- scipy *
- seaborn *
- tensorboard ==2.4.0
- tensorflow ==2.4.0
- tensorflow-addons ==0.12.0
- tensorflow-gan ==2.0.0
- tensorflow-probability ==0.12
- tensorflow_datasets ==3.1.0
- tensorflow_io *
- torch >=1.7.0
- torchvision *
- torchviz *