Flux

Flux: Elegant machine learning with Julia - Published in JOSS (2018)

Science Score: 100.0%

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
Found .zenodo.json file
✓
DOI references
Found 4 DOI reference(s) in README and JOSS metadata
✓
Academic publication links
Links to: joss.theoj.org
✓
Committers with academic emails
14 of 257 committers (5.4%) from academic institutions
○
Institutional organization owner
✓
JOSS paper metadata
Published in Journal of Open Source Software

Keywords

data-science deep-learning flux machine-learning neural-networks the-human-brain

Keywords from Contributors

graphics optimisation optim unconstrained-optimisation unconstrained-optimization ensemble-learning pipelines predictive-modeling stacking tuning-parameters

Last synced: 4 months ago · JSON representation ·

Repository

Relax! Flux is the ML library that doesn't make you tensor

Basic Info

Host: GitHub
Owner: FluxML
License: other
Language: Julia
Default Branch: master
Homepage: https://fluxml.ai/
Size: 13.2 MB

Statistics

Stars: 4,662
Watchers: 91
Forks: 614
Open Issues: 277
Releases: 113

Topics

data-science deep-learning flux machine-learning neural-networks the-human-brain

Created over 9 years ago · Last pushed 5 months ago

Metadata Files

Readme Changelog Contributing Funding License Citation

[![](https://img.shields.io/badge/Documentation-stable-blue.svg)](https://fluxml.github.io/Flux.jl/stable/) [![](https://img.shields.io/badge/Documentation-dev-blue.svg)](https://fluxml.github.io/Flux.jl/dev/) [![DOI](https://joss.theoj.org/papers/10.21105/joss.00602/status.svg)](https://doi.org/10.21105/joss.00602) [![Flux Downloads](https://img.shields.io/badge/dynamic/json?url=http%3A%2F%2Fjuliapkgstats.com%2Fapi%2Fv1%2Fmonthly_downloads%2FFlux&query=total_requests&suffix=%2Fmonth&label=Downloads)](http://juliapkgstats.com/pkg/Flux)
[![][action-img]][action-url] [![][codecov-img]][codecov-url] [![ColPrac: Contributor's Guide on Collaborative Practices for Community Packages](https://img.shields.io/badge/ColPrac-Contributor's%20Guide-blueviolet)](https://github.com/SciML/ColPrac)

Flux is an elegant approach to machine learning. It's a 100% pure-Julia stack, and provides lightweight abstractions on top of Julia's native GPU and AD support. Flux makes the easy things easy while remaining fully hackable.

Works best with Julia 1.10 or later. Here's a very short example to try it out: ```julia using Flux data = [(x, 2x-x^3) for x in -2:0.1f0:2]

model = let w, b, v = (randn(Float32, 23) for _ in 1:3) # parameters x -> sum(v .* tanh.(w*x .+ b)) # callable end

model = Chain(vcat, Dense(1 => 23, tanh), Dense(23 => 1, bias=false), only)

optstate = Flux.setup(Adam(), model) for epoch in 1:100 Flux.train!((m,x,y) -> (m(x) - y)^2, model, data, optstate) end

using Plots plot(x -> 2x-x^3, -2, 2, label="truth") scatter!(model, -2:0.1f0:2, label="learned") ``In Flux 0.15, almost any parameterised function in Julia is a valid Flux model -- such as this closure overw, b, v`. The same function can also be implemented with built-in layers as shown.

The quickstart page has a longer example. See the documentation for details, or the model zoo for examples. Ask questions on the Julia discourse or slack.

If you use Flux in your research, please cite our work.

Owner

Name: FluxML
Login: FluxML
Kind: organization

Website: https://fluxml.ai
Twitter: FluxML
Repositories: 36
Profile: https://github.com/FluxML

The Elegant Machine Learning Stack

JOSS Publication

Flux: Elegant machine learning with Julia

Published

May 03, 2018

DOI

10.21105/joss.00602

Volume 3, Issue 25, Page 602

Authors

Mike Innes

Julia Computing

Editor

Kevin M. Moerman

Citation (CITATION.bib)

@article{Flux.jl-2018,
  author    = {Michael Innes and
               Elliot Saba and
               Keno Fischer and
               Dhairya Gandhi and
               Marco Concetto Rudilosso and
               Neethu Mariya Joy and
               Tejan Karmali and
               Avik Pal and
               Viral Shah},
  title     = {Fashionable Modelling with Flux},
  journal   = {CoRR},
  volume    = {abs/1811.01457},
  year      = {2018},
  url       = {https://arxiv.org/abs/1811.01457},
  archivePrefix = {arXiv},
  eprint    = {1811.01457},
  timestamp = {Thu, 22 Nov 2018 17:58:30 +0100},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1811-01457},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{innes:2018,
  author    = {Mike Innes},
  title     = {Flux: Elegant Machine Learning with Julia},
  journal   = {Journal of Open Source Software},
  year      = {2018},
  doi       = {10.21105/joss.00602},
}

GitHub Events

Total

Create event: 56
Commit comment event: 23
Release event: 9
Issues event: 100
Watch event: 227
Delete event: 15
Issue comment event: 322
Push event: 396
Pull request review comment event: 69
Pull request review event: 103
Pull request event: 161
Fork event: 27

Last Year

Create event: 56
Commit comment event: 23
Release event: 9
Issues event: 100
Watch event: 227
Delete event: 15
Issue comment event: 322
Push event: 396
Pull request review comment event: 69
Pull request review event: 103
Pull request event: 161
Fork event: 27

Committers

Last synced: 5 months ago

All Time

Total Commits: 4,173
Total Committers: 257
Avg Commits per committer: 16.237
Development Distribution Score (DDS): 0.701

Past Year

Commits: 101
Committers: 23
Avg Commits per committer: 4.391
Development Distribution Score (DDS): 0.495

Top Committers

Name	Email	Commits
Mike Innes	m**s@g**m	1,249
Dhairya Gandhi	d**a@j**m	426
Carlo Lucibello	c**o@g**m	337
Michael Abbott	3****t	183
Kyle Daruwalla	d**a@w**u	178
Saransh	s**1@g**m	125
Avik Pal	a**l@i**n	75
thebhatman	m**0@g**m	75
Michael Abbott	me@e****k	53
Logan Kilpatrick	2**3@g**m	48
Brian Chen	T****r	44
Abhirath Anand	7****h	40
SomTambe	t**m@g**m	36
jeremie.db	j**b@e**m	35
Anton Smirnov	t**7@g**m	35
Matt Kelley	m**y@g**m	35
Matěj Račinský	m**y@a**m	34
DrChainsaw	c**y@g**m	34
Tim Besard	t**d@g**m	32
Johnny Chen	j**4@h**m	32
Bruno Hebling Vieira	b**a@u**r	31
Matthew Schlegel	m**g@g**m	31
Tejan Karmali	t**0@g**m	30
cossio	j**z@g**m	28
Ali Hamdi	a**2@o**m	26
dependabot[bot]	4****]	26
Lyndon White	l**e@i**k	25
janEbert	j**t@p**t	24
Elliot Saba	s**t@g**m	24
Billy Moses	w**s@g**m	21
and 227 more...

Committer Domains (Top 20 + Academic)

juliacomputing.com: 3 qq.com: 2 mailbox.org: 2 invenialabs.co.uk: 2 gmx.net: 2 roames.com.au: 1 da3.net: 1 online.no: 1 aalto.fi: 1 freeboson.org: 1 kelman.net: 1 flatironinstitute.org: 1 knoppweb.de: 1 paulnovo.us: 1 snm.ku.dk: 1 comcast.net: 1 buzzsumo.com: 1 chrisrackauckas.com: 1 julialang.org: 1 mayin.org: 1 hs.ntnu.edu.tw: 1 iitk.ac.in: 1 wisc.edu: 1 turing.ac.uk: 1 alumni.stanford.edu: 1 sydney.edu.au: 1 umich.edu: 1 ucl.ac.uk: 1 iitkgp.ac.in: 1 my.bristol.ac.uk: 1 seas.upenn.edu: 1 alumni.epfl.ch: 1

Issues and Pull Requests

Last synced: 4 months ago

All Time

Total issues: 197
Total pull requests: 409
Average time to close issues: 11 months
Average time to close pull requests: 2 months
Total issue authors: 118
Total pull request authors: 80
Average comments per issue: 5.02
Average comments per pull request: 2.92
Merged pull requests: 287
Bot issues: 0
Bot pull requests: 84

Past Year

Issues: 49
Pull requests: 112
Average time to close issues: 9 days
Average time to close pull requests: 6 days
Issue authors: 24
Pull request authors: 26
Average comments per issue: 2.14
Average comments per pull request: 2.0
Merged pull requests: 78
Bot issues: 0
Bot pull requests: 17

View more stats

Top Authors

Issue Authors

CarloLucibello (40)
alerem18 (5)
mcabbott (5)
ToucheSir (5)
lassepe (4)
BioTurboNick (4)
darsnack (4)
FelixBenning (3)
chengchingwen (3)
cirobr (3)
NeroBlackstone (3)
piever (3)
IanButterworth (2)
jacob-m-wilson-42 (2)
mkschleg (2)

Pull Request Authors

CarloLucibello (109)
mcabbott (64)
dependabot[bot] (47)
github-actions[bot] (43)
pxl-th (19)
wsmoses (15)
MartinuzziFrancesco (9)
ToucheSir (8)
DhairyaLGandhi (7)
christiangnrd (7)
paulnovo (6)
4SAnalyticsnModelling (6)
codetalker7 (5)
BioTurboNick (5)
diegozea (4)

Top Labels

Issue Labels

good first issue (14) RNN (14) bug (13) enhancement (12) documentation (12) help wanted (11) cuda (9) optimisers-dot-jl (7) discussion (5) gradients (4) testing (2) float16 (2) performance (2) enzyme (2) dependencies (1) deprecation (1)

Pull Request Labels

dependencies (47) documentation (24) RNN (20) breaking (16) run downstream test (13) enhancement (10) gradients (10) cuda (6) enzyme (6) discussion (4) regression (4) performance (2) optimisers-dot-jl (2) good first issue (1) testing (1) github_actions (1)

Packages

Total packages: 3
Total downloads:
- julia 2,271 total

Total dependent packages: 174
(may contain duplicates)
Total dependent repositories: 14
(may contain duplicates)
Total versions: 328

juliahub.com: Flux

Relax! Flux is the ML library that doesn't make you tensor

Homepage: https://fluxml.ai/
Documentation: https://docs.juliahub.com/General/Flux/stable/
License: MIT
Latest release: 0.16.5
published 6 months ago

Versions: 102
Dependent Packages: 174
Dependent Repositories: 14
Downloads: 2,271 Total

Rankings

Forks count: 0.0%

Stargazers count: 0.0%

Dependent packages count: 0.5%

Average: 0.7%

Dependent repos count: 2.4%

Last synced: 4 months ago

proxy.golang.org: github.com/FluxML/Flux.jl

Documentation: https://pkg.go.dev/github.com/FluxML/Flux.jl#section-documentation
License: other
Latest release: v0.16.5
published 5 months ago

Versions: 113
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 5.4%

Average: 5.6%

Dependent repos count: 5.8%

Last synced: 4 months ago

proxy.golang.org: github.com/fluxml/flux.jl

Documentation: https://pkg.go.dev/github.com/fluxml/flux.jl#section-documentation
License: other
Latest release: v0.16.5
published 5 months ago

Versions: 113
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 5.4%

Average: 5.6%

Dependent repos count: 5.8%

Last synced: 4 months ago

Flux

Science Score: 100.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

model = Chain(vcat, Dense(1 => 23, tanh), Dense(23 => 1, bias=false), only)

Owner

JOSS Publication

Flux: Elegant machine learning with Julia

Authors

Editor

Tags

Citation (CITATION.bib)

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

juliahub.com: Flux

Rankings

proxy.golang.org: github.com/FluxML/Flux.jl

Rankings

proxy.golang.org: github.com/fluxml/flux.jl

Rankings