{"id":13806970,"url":"https://github.com/DarshanDeshpande/jax-models","last_synced_at":"2025-05-13T23:33:48.059Z","repository":{"id":37724043,"uuid":"445829911","full_name":"DarshanDeshpande/jax-models","owner":"DarshanDeshpande","description":"Unofficial JAX implementations of deep learning research papers","archived":false,"fork":false,"pushed_at":"2022-06-25T02:15:08.000Z","size":206,"stargazers_count":151,"open_issues_count":0,"forks_count":8,"subscribers_count":5,"default_branch":"main","last_synced_at":"2024-11-18T17:47:17.105Z","etag":null,"topics":["artificial-intelligence","computer-vision","convolutional-neural-networks","deep-learning","flax","jax","machine-learning","research-paper-implementation","transformers"],"latest_commit_sha":null,"homepage":"","language":"Python","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/DarshanDeshpande.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-01-08T13:40:38.000Z","updated_at":"2024-10-15T11:17:16.000Z","dependencies_parsed_at":"2022-08-08T21:30:28.581Z","dependency_job_id":null,"html_url":"https://github.com/DarshanDeshpande/jax-models","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DarshanDeshpande%2Fjax-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DarshanDeshpande%2Fjax-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DarshanDeshpande%2Fjax-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DarshanDeshpande%2Fjax-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DarshanDeshpande","download_url":"https://codeload.github.com/DarshanDeshpande/jax-models/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225267429,"owners_count":17447154,"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":["artificial-intelligence","computer-vision","convolutional-neural-networks","deep-learning","flax","jax","machine-learning","research-paper-implementation","transformers"],"created_at":"2024-08-04T01:01:18.799Z","updated_at":"2024-11-18T23:30:33.793Z","avatar_url":"https://github.com/DarshanDeshpande.png","language":"Python","funding_links":[],"categories":["Libraries"],"sub_categories":["New Libraries"],"readme":"\u003ch1\u003e JAX Models \u003c/h1\u003e\n\n\u003c!-- PROJECT SHIELDS --\u003e\n![license-shield]\n![release-shield]\n![python-shield]\n![code-style]\n\n\u003c!-- TABLE OF CONTENTS --\u003e\n\u003cdetails open=\"open\"\u003e\n  \u003csummary\u003eTable of Contents\u003c/summary\u003e\n  \u003col\u003e\n    \u003cli\u003e\n      \u003ca href=\"#about-the-project\"\u003eAbout The Project\u003c/a\u003e\n    \u003c/li\u003e\n    \u003cli\u003e\n      \u003ca href=\"#getting-started\"\u003eGetting Started\u003c/a\u003e\n      \u003cul\u003e\n        \u003cli\u003e\u003ca href=\"#prerequisites\"\u003ePrerequisites\u003c/a\u003e\u003c/li\u003e\n        \u003cli\u003e\u003ca href=\"#installation\"\u003eInstallation\u003c/a\u003e\u003c/li\u003e\n        \u003cli\u003e\u003ca href=\"#usage\"\u003eUsage\u003c/a\u003e\u003c/li\u003e\n      \u003c/ul\u003e\n    \u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"#contributing\"\u003eContributing\u003c/a\u003e\u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"#license\"\u003eLicense\u003c/a\u003e\u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"#contact\"\u003eContact\u003c/a\u003e\u003c/li\u003e\n  \u003c/ol\u003e\n\u003c/details\u003e\n\n\n\n\u003c!-- ABOUT THE PROJECT --\u003e\n## About The Project\n\nThe \u003cb\u003eJAX Models\u003c/b\u003e repository aims to provide open sourced JAX/Flax implementations for research papers originally without code or code written with frameworks other than JAX. The goal of this project is to make a collection of models, layers, activations and other utilities that are most commonly used for research. All papers and derived or translated code is cited in either the README or the docstrings. If you think that any citation is missed then please raise an issue.\n\nAll implementations provided here are available on \u003ca href=\"https://www.paperswithcode.com\"\u003ePapers With Code\u003c/a\u003e.\n\n\u003cbr\u003e\nAvailable model implementations for JAX are:\n\n1. \u003ca href=\"https://arxiv.org/abs/2111.11418\"\u003eMetaFormer is Actually What You Need for Vision\u003c/a\u003e (Weihao Yu et al., 2021)\n2. \u003ca href=\"https://arxiv.org/abs/2112.13692v1\"\u003eAugmenting Convolutional networks with attention-based aggregation\u003c/a\u003e (Hugo Touvron et al., 2021)\n3. \u003ca href=\"https://arxiv.org/abs/2112.11010\"\u003eMPViT : Multi-Path Vision Transformer for Dense Prediction\u003c/a\u003e (Youngwan Lee et al., 2021)\n4. \u003ca href=\"https://arxiv.org/abs/2105.01601v1\"\u003eMLP-Mixer: An all-MLP Architecture for Vision\u003c/a\u003e (Ilya Tolstikhin et al., 2021)\n5. \u003ca href=\"https://openreview.net/pdf?id=TVHS5Y4dNvM\"\u003ePatches Are All You Need\u003c/a\u003e (Anonymous et al., 2021)\n6. \u003ca href=\"https://arxiv.org/abs/2105.15203\"\u003eSegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers\u003c/a\u003e (Enze Xie et al., 2021)\n7. \u003ca href=\"https://arxiv.org/abs/2201.03545\"\u003eA ConvNet for the 2020s\u003c/a\u003e (Zhuang Liu et al., 2021)\n8. \u003ca href=\"https://arxiv.org/abs/2111.06377v1\"\u003eMasked Autoencoders Are Scalable Vision Learners\u003c/a\u003e (Kaiming He et al., 2021)\n9. \u003ca href=\"https://arxiv.org/abs/2103.14030\"\u003eSwin Transformer: Hierarchical Vision Transformer using Shifted Windows\u003c/a\u003e (Ze Liu et al., 2021)\n10. \u003ca href=\"https://arxiv.org/abs/2102.12122\"\u003ePyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions\u003c/a\u003e (Wenhai Wang et al., 2021)\n11. \u003ca href=\"https://arxiv.org/abs/2103.17239\"\u003eGoing deeper with Image Transformers\u003c/a\u003e (Hugo Touvron et al., 2021)\n12. \u003ca href=\"https://arxiv.org/abs/2202.09741\"\u003eVisual Attention Network\u003c/a\u003e (Meng-Hao Guo et al., 2022)\n\n\u003cbr\u003e\nAvailable layers for out-of-the-box integration:\n\n1. \u003ca href=\"https://arxiv.org/abs/1603.09382\"\u003eDropPath (Stochastic Depth)\u003c/a\u003e (Gao Huang et al., 2021)\n2. \u003ca href=\"https://arxiv.org/abs/1709.01507\"\u003eSqueeze-and-Excitation Layer\u003c/a\u003e (Jie Hu et al. 2019)\n3. \u003ca href=\"https://arxiv.org/abs/1610.02357v3\"\u003e Depthwise Convolution \u003c/a\u003e (François Chollet, 2017)\n\n\u003c!-- PREREQUISITES --\u003e\n## Prerequisites\n\nPrerequisites can be installed separately through the `requirements.txt` file in the main directory using:\n\n```sh\npip install -r requirements.txt\n```\nThe use of a virtual environment is highly recommended to avoid version incompatibilites.\n\n\u003c!-- INSTALLATION --\u003e\n## Installation\n\nThis project is built with Python 3 for the latest JAX/Flax versions and can be directly installed via pip.\n```sh\npip install jax-models\n```\nIf you wish to use the latest version then you can directly clone the repository too.\n```sh\ngit clone https://github.com/DarshanDeshpande/jax-models.git\n```\n\n\u003c!-- USAGE --\u003e\n## Usage\n\nTo see all model architectures available:\n\n```py\nfrom jax_models import list_models\nfrom pprint import pprint\n\npprint(list_models())\n```\n\nTo load your desired model:\n\n```py\nfrom jax_models import load_model\nload_model('swin-tiny-224', attach_head=True, num_classes=1000, dropout=0.0, pretrained=True)\n```\n\nNote: It is necessary to pass `attach_head=True` and `num_classes` while loading pretrained models.\n\n\n\u003c!-- CONTRIBUTING --\u003e\n## Contributing\n\nPlease raise an issue if any implementation gives incorrect results, crashes unexpectedly during training/inference or if any citation is missing.\n\nYou can contribute to `jax_models` by supporting me with compute resources or by contributing your own resources to provide pretrained weights. \n\nIf you wish to donate to this inititative then please drop me a mail \u003ca href=\"https://mail.google.com/mail/u/0/?view=cm\u0026fs=1\u0026to=darshan.g.deshpande@gmail.com\u0026tf=1\"\u003ehere\u003c/a\u003e.\n\u003cbr\u003e\n\n\u003c!-- LICENSE --\u003e\n## License\n\nDistributed under the Apache 2.0 License. See `LICENSE` for more information.\n\n\u003c!-- CONTACT --\u003e\n## Contact\nFeel free to reach out for any issues or requests related to these implementations\n\nDarshan Deshpande - [Email](https://mail.google.com/mail/u/0/?view=cm\u0026fs=1\u0026to=darshan.g.deshpande@gmail.com\u0026tf=1) | [Twitter](https://www.twitter.com/getdarshan) | [LinkedIn](https://www.linkedin.com/in/darshan-deshpande/) \n\n\n\n\n\n\u003c!-- MARKDOWN LINKS \u0026 IMAGES --\u003e\n\u003c!-- https://www.markdownguide.org/basic-syntax/#reference-style-links --\u003e\n[license-shield]: https://img.shields.io/badge/LICENSE-Apache_2.0-magenta?style=for-the-badge\n[python-shield]: https://img.shields.io/badge/PYTHON-3.6+-blue?style=for-the-badge\n[release-shield]: https://img.shields.io/badge/Build-Alpha-red?style=for-the-badge\n[code-style]: https://img.shields.io/badge/Code_Style-Black-black?style=for-the-badge\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDarshanDeshpande%2Fjax-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FDarshanDeshpande%2Fjax-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDarshanDeshpande%2Fjax-models/lists"}