{"id":20054869,"url":"https://github.com/thu-ml/zhusuan-jittor","last_synced_at":"2025-08-01T16:08:11.967Z","repository":{"id":67921753,"uuid":"377864774","full_name":"thu-ml/Zhusuan-Jittor","owner":"thu-ml","description":"Zhusuan with backend Jittor","archived":false,"fork":false,"pushed_at":"2022-03-04T05:01:17.000Z","size":550,"stargazers_count":14,"open_issues_count":1,"forks_count":1,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-06-09T06:37:00.862Z","etag":null,"topics":["bayesian-inference","machine-learning","probabilistic-programming"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/thu-ml.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing.rst","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-06-17T14:46:11.000Z","updated_at":"2024-01-07T16:04:11.000Z","dependencies_parsed_at":"2023-08-01T01:31:43.874Z","dependency_job_id":null,"html_url":"https://github.com/thu-ml/Zhusuan-Jittor","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/thu-ml/Zhusuan-Jittor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thu-ml%2FZhusuan-Jittor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thu-ml%2FZhusuan-Jittor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thu-ml%2FZhusuan-Jittor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thu-ml%2FZhusuan-Jittor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thu-ml","download_url":"https://codeload.github.com/thu-ml/Zhusuan-Jittor/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thu-ml%2FZhusuan-Jittor/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268256976,"owners_count":24221053,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-01T02:00:08.611Z","response_time":67,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bayesian-inference","machine-learning","probabilistic-programming"],"created_at":"2024-11-13T12:44:08.260Z","updated_at":"2025-08-01T16:08:11.938Z","avatar_url":"https://github.com/thu-ml.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Documentation Status](https://readthedocs.org/projects/zhusuan-jittor/badge/?version=latest)](https://zhusuan-jittor.readthedocs.io/en/latest/?badge=latest)\n\n# Zhusuan-Jittor\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://zhusuan-jittor.readthedocs.io/en/main/?badge=main\"\u003e \u003cimg width=\"450px\" height=\"auto\" \n    src=\"docs/_static/images/zhusuan-jittor.png\"\u003e\u003c/a\u003e\n\u003c/div\u003e\n\n---\n\nZhuSuan-Jittor is a python probabilistic programming library for\n**Bayesian deep learning**, which conjoins the complimentary advantages of\nBayesian methods and deep learning. ZhuSuan-Jittor is built upon\n[Jittor](http://cg.cs.tsinghua.edu.cn/jittor/). Unlike existing deep learning\nlibraries, which are mainly designed for deterministic neural networks and\nsupervised tasks, ZhuSuan-Jittor provides deep learning style primitives and\nalgorithms for building probabilistic models and applying Bayesian inference.\nThe supported inference algorithms include:\n\n* Variational inference with programmable variational posteriors, various\nobjectives and advanced gradient estimators (SGVB, SWI, etc.).\n\n* Importance sampling for learning and evaluating models, with programmable\nproposals.\n\n* MCMC samplers: Hamiltonian Monte Carlo (HMC) with parallel chains, and\nStochastic Gradient MCMC (sgmcmc).\n\n\n## Installation\n\nZhuSuan-Jittor is still under development. Before the first stable release (1.0),\nplease clone the repository and run\n```\npip install .\n```\nin the main directory. This will install ZhuSuan and its dependencies\nautomatically.  \n\nIf you are developing ZhuSuan, you may want to install in an\n\"editable\" or \"develop\" mode. Please refer to the Contributing section below.\n\n## Documentation\n\n* [Tutorials and API docs](https://zhusuan-jittor.readthedocs.io/en/main/?badge=main)\n\n## Examples\n\nWe provide examples on traditional hierarchical Bayesian models and recent\ndeep generative models.\n\n* Gaussian: \n  [HMC](examples/toy_models/gaussian.py)\n* Bayesian Neural Networks:\n  [SGVB](examples/bayesian_neural_nets/bnn_vi.py),\n  [SGMCMC](examples/bayesian_neural_nets/bnn_sgmcmc.py)\n* Variational Autoencoder (VAE):\n  [SGVB](examples/variational_autoencoders/vae_mnist.py),\n  [IWAE](examples/variational_autoencoders/vae_iw.py)\n\n## Citing ZhuSuan-Jittor\n\nIf you find ZhuSuan-Jittor useful, please cite it in your publications.\n\n```\n@ARTICLE{zhusuan2017,\n  title={Zhu{S}uan: A Library for {B}ayesian Deep Learning},\n  author={Shi, Jiaxin and Chen, Jianfei. and Zhu, Jun and Sun, Shengyang\n          and Luo, Yucen and Gu, Yihong and Zhou, Yuhao},\n  journal={arXiv preprint arXiv:1709.05870},\n  year=2017,\n}\n```\n\n## Contributing\n\nWe always welcome contributions to help make ZhuSuan-Jittor better. If you would like \nto contribute, please check out the guidelines [here](CONTRIBUTING.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthu-ml%2Fzhusuan-jittor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthu-ml%2Fzhusuan-jittor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthu-ml%2Fzhusuan-jittor/lists"}