pytorch-inferno
PyTorch implementation of inference aware neural optimisation (de Castro and Dorigo, 2018 https://www.sciencedirect.com/science/article/pii/S0010465519301948)
Science Score: 36.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
✓DOI references
Found 10 DOI reference(s) in README -
✓Academic publication links
Links to: sciencedirect.com, zenodo.org -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (14.7%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
PyTorch implementation of inference aware neural optimisation (de Castro and Dorigo, 2018 https://www.sciencedirect.com/science/article/pii/S0010465519301948)
Basic Info
- Host: GitHub
- Owner: GilesStrong
- License: apache-2.0
- Language: Jupyter Notebook
- Default Branch: master
- Homepage: https://gilesstrong.github.io/pytorch_inferno/
- Size: 30.8 MB
Statistics
- Stars: 4
- Watchers: 2
- Forks: 1
- Open Issues: 3
- Releases: 5
Topics
Metadata Files
README.md
Title
PyTorch INFERNO
Documentation: https://gilesstrong.github.io/pytorch_inferno/
This package provides a PyTorch implementation of INFERNO (de Castro and Dorigo, 2018), 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.
For 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/talkpyhep21pytorch_inferno)
For 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
The authors' Tensorflow 1 code may be found here: https://github.com/pablodecm/paper-inferno And Lukas Layer's Tenforflow 2 version may be found here: https://github.com/llayer/inferno
For a talk and tutorial on PyTorch INFERNO, please see https://github.com/GilesStrong/talkpyhep21pytorch_inferno, and https://youtu.be/5aWAxvdrszw?t=13543 for the YouTube recording.
User install
pip install pytorch_inferno
Developer install
[install torch>=1.7 according to CUDA version]
pip install nbdev fastcore numpy pandas fastprogress matplotlib>=3.0.0 seaborn scipy
git clone git@github.com:GilesStrong/pytorch_inferno.git
cd pytorch_inferno
pip install -e .
nbdev_install_git_hooks
Overview
Library developed and testing in nbs directory.
Experiments run in experiments directory.
Use 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.
Results
This package has been tested against the paper problem and reproduces its results within uncertainty
Reference
If you have used this implementation of INFERNO in your analysis work and wish to cite it, the preferred reference is: Giles C. Strong, pytorchinferno, Zenodo (Mar. 2021), http://doi.org/10.5281/zenodo.4597140, Note: Please check https://github.com/GilesStrong/pytorchinferno/graphs/contributors for the full list of contributors
@misc{giles_chatham_strong_2021_5040810,
author = {Giles Chatham Strong},
title = {pytorch\_inferno},
month = jun,
year = 2021,
note = {{Please check https://github.com/GilesStrong/pytorch_inferno/graphs/contributors for the full list of contributors}},
doi = {10.5281/zenodo.4597140},
url = {https://doi.org/10.5281/zenodo.4597140}
}
The INFERNO algorithm should also be cited:
@article{DECASTRO2019170,
title = {INFERNO: Inference-Aware Neural Optimisation},
journal = {Computer Physics Communications},
volume = {244},
pages = {170-179},
year = {2019},
issn = {0010-4655},
doi = {https://doi.org/10.1016/j.cpc.2019.06.007},
url = {https://www.sciencedirect.com/science/article/pii/S0010465519301948},
author = {Pablo {de Castro} and Tommaso Dorigo},
}
Owner
- Login: GilesStrong
- Kind: user
- Location: Shibuya, Tokyo, Japan
- Website: https://gilesstrong.github.io/website/
- Twitter: Giles_C_Strong
- Repositories: 66
- Profile: https://github.com/GilesStrong
Doctor of physics | Researcher at Braid Technologies. Previously: Deep-learning approaches for high-energy particle physics at CERN's CMS experiment.
GitHub Events
Total
Last Year
Committers
Last synced: 8 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| GilesStrong | g****g@o****m | 97 |
| dependabot[bot] | 4****] | 9 |
| Cloud User | c****s@i****l | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 0
- Total pull requests: 20
- Average time to close issues: N/A
- Average time to close pull requests: 13 days
- Total issue authors: 0
- Total pull request authors: 3
- Average comments per issue: 0
- Average comments per pull request: 0.15
- Merged pull requests: 16
- Bot issues: 0
- Bot pull requests: 13
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
- dependabot[bot] (13)
- GilesStrong (6)
- llayer (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 17 last-month
- Total dependent packages: 0
- Total dependent repositories: 1
- Total versions: 4
- Total maintainers: 1
pypi.org: pytorch-inferno
PyTorch Implementation of INFERNO
- Homepage: https://github.com/GilesStrong/pytorch_inferno/tree/master/
- Documentation: https://pytorch-inferno.readthedocs.io/
- License: Apache Software License 2.0
-
Latest release: 0.2.2
published over 4 years ago
Rankings
Maintainers (1)
Dependencies
- github-pages >= 0 development
- jekyll >= 3.7
- kramdown >= 2.3.0
- nokogiri < 1.13.7
- activesupport 6.0.3.2
- addressable 2.8.0
- coffee-script 2.4.1
- coffee-script-source 1.11.1
- colorator 1.1.0
- commonmarker 0.17.13
- concurrent-ruby 1.1.7
- dnsruby 1.61.4
- em-websocket 0.5.1
- ethon 0.12.0
- eventmachine 1.2.7
- execjs 2.7.0
- faraday 1.0.1
- ffi 1.13.1
- forwardable-extended 2.6.0
- gemoji 3.0.1
- github-pages 207
- github-pages-health-check 1.16.1
- html-pipeline 2.14.0
- http_parser.rb 0.6.0
- i18n 0.9.5
- jekyll 3.9.0
- jekyll-avatar 0.7.0
- jekyll-coffeescript 1.1.1
- jekyll-commonmark 1.3.1
- jekyll-commonmark-ghpages 0.1.6
- jekyll-default-layout 0.1.4
- jekyll-feed 0.13.0
- jekyll-gist 1.5.0
- jekyll-github-metadata 2.13.0
- jekyll-mentions 1.5.1
- jekyll-optional-front-matter 0.3.2
- jekyll-paginate 1.1.0
- jekyll-readme-index 0.3.0
- jekyll-redirect-from 0.15.0
- jekyll-relative-links 0.6.1
- jekyll-remote-theme 0.4.1
- jekyll-sass-converter 1.5.2
- jekyll-seo-tag 2.6.1
- jekyll-sitemap 1.4.0
- jekyll-swiss 1.0.0
- jekyll-theme-architect 0.1.1
- jekyll-theme-cayman 0.1.1
- jekyll-theme-dinky 0.1.1
- jekyll-theme-hacker 0.1.1
- jekyll-theme-leap-day 0.1.1
- jekyll-theme-merlot 0.1.1
- jekyll-theme-midnight 0.1.1
- jekyll-theme-minimal 0.1.1
- jekyll-theme-modernist 0.1.1
- jekyll-theme-primer 0.5.4
- jekyll-theme-slate 0.1.1
- jekyll-theme-tactile 0.1.1
- jekyll-theme-time-machine 0.1.1
- jekyll-titles-from-headings 0.5.3
- jekyll-watch 2.2.1
- jemoji 0.11.1
- kramdown 2.3.0
- kramdown-parser-gfm 1.1.0
- liquid 4.0.3
- listen 3.2.1
- mercenary 0.3.6
- mini_portile2 2.8.0
- minima 2.5.1
- minitest 5.14.1
- multipart-post 2.1.1
- nokogiri 1.13.6
- octokit 4.18.0
- pathutil 0.16.2
- public_suffix 3.1.1
- racc 1.6.0
- rb-fsevent 0.10.4
- rb-inotify 0.10.1
- rexml 3.2.5
- rouge 3.19.0
- ruby-enum 0.8.0
- rubyzip 2.3.0
- safe_yaml 1.0.5
- sass 3.7.4
- sass-listen 4.0.0
- sawyer 0.8.2
- simpleidn 0.1.1
- terminal-table 1.8.0
- thread_safe 0.3.6
- typhoeus 1.4.0
- tzinfo 1.2.7
- unf 0.1.4
- unf_ext 0.0.7.7
- unicode-display_width 1.7.0
- zeitwerk 2.4.0
- actions/checkout v1 composite
- actions/setup-python v1 composite