{"id":24871329,"url":"https://github.com/gilesstrong/pytorch_inferno","last_synced_at":"2025-06-29T21:40:54.484Z","repository":{"id":39863511,"uuid":"299618987","full_name":"GilesStrong/pytorch_inferno","owner":"GilesStrong","description":"PyTorch implementation of inference aware neural optimisation (de Castro and Dorigo, 2018 https://www.sciencedirect.com/science/article/pii/S0010465519301948)","archived":false,"fork":false,"pushed_at":"2023-04-12T06:06:10.000Z","size":32314,"stargazers_count":4,"open_issues_count":3,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-07-23T14:38:10.510Z","etag":null,"topics":["inferno","likelihood-free-inference","neural-networks","pytorch","statistical-inference"],"latest_commit_sha":null,"homepage":"https://gilesstrong.github.io/pytorch_inferno/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GilesStrong.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGES.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.md","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-09-29T13:02:27.000Z","updated_at":"2022-02-08T15:13:17.000Z","dependencies_parsed_at":"2024-11-16T03:28:03.281Z","dependency_job_id":"d2fef55f-5644-4429-bff7-ff5e06f89216","html_url":"https://github.com/GilesStrong/pytorch_inferno","commit_stats":{"total_commits":107,"total_committers":3,"mean_commits":"35.666666666666664","dds":0.09345794392523366,"last_synced_commit":"ebee7305d3fbf5fe50b6b7075294a4ec14033e01"},"previous_names":[],"tags_count":5,"template":false,"template_full_name":"fastai/nbdev_template","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GilesStrong%2Fpytorch_inferno","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GilesStrong%2Fpytorch_inferno/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GilesStrong%2Fpytorch_inferno/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GilesStrong%2Fpytorch_inferno/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GilesStrong","download_url":"https://codeload.github.com/GilesStrong/pytorch_inferno/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":236619372,"owners_count":19178207,"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","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":["inferno","likelihood-free-inference","neural-networks","pytorch","statistical-inference"],"created_at":"2025-02-01T04:31:51.225Z","updated_at":"2025-02-01T04:31:52.372Z","avatar_url":"https://github.com/GilesStrong.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Title\n\n\n\n[![pypi pytorch_inferno version](https://img.shields.io/pypi/v/pytorch_inferno.svg)](https://pypi.python.org/pypi/pytorch_inferno)\n[![pytorch_inferno python compatibility](https://img.shields.io/pypi/pyversions/pytorch_inferno.svg)](https://pypi.python.org/pypi/pytorch_inferno) [![pytorch_inferno license](https://img.shields.io/pypi/l/pytorch_inferno.svg)](https://pypi.python.org/pypi/pytorch_inferno)\n[![CI](https://github.com/GilesStrong/pytorch_inferno/actions/workflows/main.yml/badge.svg)](https://github.com/GilesStrong/pytorch_inferno/actions)\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4597140.svg)](https://doi.org/10.5281/zenodo.4597140)\n\n# PyTorch INFERNO\n\nDocumentation: https://gilesstrong.github.io/pytorch_inferno/\n\nThis package provides a PyTorch implementation of INFERNO ([de Castro and Dorigo, 2018](https://www.sciencedirect.com/science/article/pii/S0010465519301948)), along with a minimal high-level wrapper for training and applying PyTorch models, and running statistical inference of parameters of interest in the presence of nuisance parameters. INFERNO is implemented in the form of a callback, allowing it to be dropped in and swapped out with heavy rewriting of code.\n\nFor a presentation of the package, check out my talk at PyHEP 2021: https://www.youtube.com/watch?v=copNcyHnHBs (slides here: https://github.com/GilesStrong/talk_pyhep21_pytorch_inferno)\n\nFor a deeper overview of the package, a breakdown of the INFERNO algorithm, and an introduction to parameter inference in HEP, I have written a 5-post blog series: https://gilesstrong.github.io/website/statistics/hep/inferno/2020/12/04/inferno-1.html\n\nThe authors' Tensorflow 1 code may be found here: https://github.com/pablodecm/paper-inferno\nAnd Lukas Layer's Tenforflow 2 version may be found here: https://github.com/llayer/inferno\n\nFor a talk and tutorial on PyTorch INFERNO, please see https://github.com/GilesStrong/talk_pyhep21_pytorch_inferno, and https://youtu.be/5aWAxvdrszw?t=13543 for the YouTube recording.\n\n### User install\n```\npip install pytorch_inferno\n```\n\n### Developer install\n```\n[install torch\u003e=1.7 according to CUDA version]\npip install nbdev fastcore numpy pandas fastprogress matplotlib\u003e=3.0.0 seaborn scipy\ngit clone git@github.com:GilesStrong/pytorch_inferno.git\ncd pytorch_inferno\npip install -e .\nnbdev_install_git_hooks\n```\n\n## Overview\nLibrary developed and testing in `nbs` directory.\n\nExperiments run in `experiments` directory.\n\nUse `nbdev_build_lib` to export code to library located in `pytorch_inferno`. This overwrites any changes in `pytorch_inferno`, i.e. only edit the notebooks.\n\n## Results\n\nThis package has been tested against the paper problem and reproduces its results within uncertainty\n![title](nbs/imgs/results.png)\n\n## Reference\n\nIf you have used this implementation of INFERNO in your analysis work and wish to cite it, the preferred reference is: *Giles C. Strong, pytorch_inferno, Zenodo (Mar. 2021), http://doi.org/10.5281/zenodo.4597140, Note: Please check https://github.com/GilesStrong/pytorch_inferno/graphs/contributors for the full list of contributors*\n\n```\n@misc{giles_chatham_strong_2021_5040810,  \n  author       = {Giles Chatham Strong},  \n  title        = {pytorch\\_inferno},  \n  month        = jun,  \n  year         = 2021,  \n  note         = {{Please check https://github.com/GilesStrong/pytorch_inferno/graphs/contributors for the full list of contributors}},  \n  doi          = {10.5281/zenodo.4597140},  \n  url          = {https://doi.org/10.5281/zenodo.4597140}  \n}\n```\n\nThe INFERNO algorithm should also be cited:\n```\n@article{DECASTRO2019170,\n    title = {INFERNO: Inference-Aware Neural Optimisation},\n    journal = {Computer Physics Communications},\n    volume = {244},\n    pages = {170-179},\n    year = {2019},\n    issn = {0010-4655},\n    doi = {https://doi.org/10.1016/j.cpc.2019.06.007},\n    url = {https://www.sciencedirect.com/science/article/pii/S0010465519301948},\n    author = {Pablo {de Castro} and Tommaso Dorigo},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgilesstrong%2Fpytorch_inferno","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgilesstrong%2Fpytorch_inferno","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgilesstrong%2Fpytorch_inferno/lists"}