{"id":15057237,"url":"https://github.com/fluxml/model-zoo","last_synced_at":"2025-05-14T15:05:56.128Z","repository":{"id":21662180,"uuid":"93555389","full_name":"FluxML/model-zoo","owner":"FluxML","description":"Please do not feed the models","archived":false,"fork":false,"pushed_at":"2024-11-25T18:49:31.000Z","size":32157,"stargazers_count":924,"open_issues_count":107,"forks_count":332,"subscribers_count":46,"default_branch":"master","last_synced_at":"2025-04-06T06:11:22.996Z","etag":null,"topics":["deep-learning","flux","julia","machine-learning","model-zoo"],"latest_commit_sha":null,"homepage":"https://fluxml.ai/","language":"Julia","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FluxML.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE.md","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},"funding":{"github":["JuliaLang"]}},"created_at":"2017-06-06T19:23:23.000Z","updated_at":"2025-04-01T11:31:18.000Z","dependencies_parsed_at":"2024-12-29T16:00:38.006Z","dependency_job_id":"27bad1b8-fb36-477e-a049-217f90794613","html_url":"https://github.com/FluxML/model-zoo","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FluxML%2Fmodel-zoo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FluxML%2Fmodel-zoo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FluxML%2Fmodel-zoo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FluxML%2Fmodel-zoo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FluxML","download_url":"https://codeload.github.com/FluxML/model-zoo/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247675597,"owners_count":20977376,"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":["deep-learning","flux","julia","machine-learning","model-zoo"],"created_at":"2024-09-24T22:04:17.338Z","updated_at":"2025-04-07T15:00:25.767Z","avatar_url":"https://github.com/FluxML.png","language":"Julia","funding_links":["https://github.com/sponsors/JuliaLang"],"categories":[],"sub_categories":[],"readme":"\u003cimg align=\"right\" width=\"200px\" src=\"https://fluxml.ai/assets/logo-small.png\"\u003e\n\n# Flux Model Zoo\n\nThis repository contains various demonstrations of the [Flux](http://fluxml.github.io/) machine learning library. Any of these may freely be used as a starting point for your own models.\n\nThe models are broadly categorised into the folders [vision](/vision) (e.g. large convolutional neural networks (CNNs)), [text](/text) (e.g. various recurrent neural networks (RNNs) and natural language processing (NLP) models), [games](/contrib/games) (Reinforcement Learning / RL). See the READMEs of respective models for more information.\n\n## Usage\n\nEach model comes with its own [Julia project](https://pkgdocs.julialang.org/v1/environments/#Using-someone-else's-project). To use this, open Julia in the project folder, and enter\n\n```julia\nusing Pkg; Pkg.activate(\".\"); Pkg.instantiate()\n```\n\nThis will install all needed packages, at the exact versions when the model was last updated. Then you can run the model code with `include(\"\u003cmodel-to-run\u003e.jl\")`, or by running the model script line-by-line.\n\nModels may also be run with NVIDIA GPU support, if you have a CUDA installed. Most models will have this capability by default, pointed at by calls to `gpu` in the model code.\n\n### Gitpod Online IDE\n\nEach model can be used in [Gitpod](https://www.gitpod.io/), just [open the repository by gitpod](https://gitpod.io/#https://github.com/FluxML/model-zoo)\n\n* Based on [Gitpod's policies](https://www.gitpod.io/pricing/), free access is limited.\n* All of your work will place in the Gitpod's cloud.\n* It isn't an officially maintained feature.\n\n## Contributing\n\nWe welcome contributions of new models and documentation. \n\n### Share a new model\n\nIf you want to share a new model, we suggest you follow these guidelines:\n\n* Models should be in a folder with a project and manifest file to pin all relevant packages.\n* Models should include a README(.md) to explain what the model is about, how to run it, and what results it achieves (if applicable).\n* Models should ideally be CPU/GPU agnostic and not depend directly on GPU functionality.\n* Please keep the code short, clean, and self-explanatory, with as little boilerplate as possible.\n\n### Create or improve documentation\n\nYou can contribute in one of the following ways \n\n* Add or improve documentation to existing models: Write the following information:\n  * Give a brief introduction to the model’s architecture and the goal it archives.\n  * Describe the Flux API that the model demonstrates (high-level API, AD, custom operations, custom layers, etc.).\n  * Add literature background for the model. More specifically, add articles, blog posts, videos, and any other resource that is helpful to better understand the model.\n  * Mention the technique that is being demonstrated. Briefly describe the learning technique being demonstrated (Computer vision, regression, NLP, time series, etc.).\n* Write in-depth tutorials for a model: You can further extend the documentation of a model and create a tutorial to explain in more detail the architecture, the training routine, use your own data, and so forth. After you write a tutorial, create a PR with it for the [Tutorials](https://fluxml.ai/tutorials/) section on the [FluxML](https://fluxml.ai/) website.\n\n### Update a model\n\nEach example lists the version of Flux for which it was most recently updated.\nBringing them up to the latest is a great way to learn!\nFlux has a [NEWS page](https://github.com/FluxML/Flux.jl/blob/master/NEWS.md) listing important changes.\n(For other packages, see their releses page: [MLUtils](https://github.com/JuliaML/MLUtils.jl/releases), [MLDatasets](https://github.com/JuliaML/MLDatasets.jl/releases), etc.)\n\nTo run the old examples, Flux v0.11 can be installed and run on [Julia 1.6, the LTS version](https://julialang.org/downloads/#long_term_support_release).\nFlux v0.12 works on Julia 1.8.\nFlux v0.14 is the latest right now, this and v0.13 are marked with ☀️; models upgraded to use  \nexplicit gradients (v0.13.9+ or v0.14) have a `+`.\n\n## Examples in the Model Zoo\n\n**Vision**\n* MNIST\n  * [Simple multi-layer perceptron](vision/mlp_mnist) ☀️ v0.13 +\n  * [Simple ConvNet (LeNet)](vision/conv_mnist) ☀️ v0.14\n  * [Variational Auto-Encoder](vision/vae_mnist) ☀️ v0.13 +\n  * [Deep Convolutional Generative Adversarial Networks](vision/dcgan_mnist) ☀️ v0.13 +\n  * [Conditional Deep Convolutional Generative Adversarial Networks](vision/cdcgan_mnist) ☀️ v0.13\n  * [Score-Based Generative Modeling (Diffusion Model)](vision/diffusion_mnist) ☀️ v0.13\n  * [Spatial Transformer](vision/spatial_transformer) ☀️ v0.13 +\n* CIFAR10\n  * [VGG 16/19](vision/vgg_cifar10) ☀️ v0.13 +\n  * [ConvMixer \"Patches are all you need?\"](vision/convmixer_cifar10/) ☀️ v0.13\n\n**Text**\n* [CharRNN](text/char-rnn) ☀️ v0.13 +\n* [NanoGPT](text/nanogpt) ☀️ v0.14\n* [Character-level language detection](text/lang-detection) ☀️ v0.13 +\n* [Seq2Seq phoneme detection on CMUDict](text/phonemes) ⛅️ v0.11\n* [Recursive net on IMDB sentiment treebank](text/treebank) ⛅️ v0.11\n\n**Other** \u0026 contributed models\n* [Logistic Regression Iris](other/iris/iris.jl) ☀️ v0.13 +\n* [Autoregressive Model](other/autoregressive-process/) ☀️ v0.13 +\n* [BitString Parity Challenge](other/bitstring-parity) ⛅️ v0.11\n* [MLP on housing data](other/housing/) (low level API) ⛅️ v0.11\n* [FizzBuzz](other/fizzbuzz/fizzbuzz.jl) ☀️ v0.13 +\n* [Meta-Learning](contrib/meta-learning/MetaLearning.jl) ❄️ v0.7\n* [Speech recognition](contrib/audio/speech-blstm) ❄️ v0.6\n\n**Tutorials**\n* [A 60 Minute Blitz](tutorials/60-minute-blitz/60-minute-blitz.jl) ⛅️ v0.11\n* [DataLoader example with image data](tutorials/dataloader) ⛅️ v0.11\n* [Transfer Learning](tutorials/transfer_learning/transfer_learning.jl) ☀️ v0.13 +\n\n## Examples Elsewhere\n\n**MLJFlux** is a bridge to [MLJ.jl](https://github.com/alan-turing-institute/MLJ.jl), a package for mostly non-neural-network machine learning. They have some examples of interest, which like the model zoo's examples, each include a local Project \u0026 Manifest file:\n\n* [Iris](https://github.com/FluxML/MLJFlux.jl/tree/dev/examples/iris) ⛅️ v0.11\n* [Boston](https://github.com/FluxML/MLJFlux.jl/tree/dev/examples/boston) ⛅️ v0.11\n* [MNIST](https://github.com/FluxML/MLJFlux.jl/tree/dev/examples/mnist) ⛅️ v0.11\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffluxml%2Fmodel-zoo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffluxml%2Fmodel-zoo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffluxml%2Fmodel-zoo/lists"}