{"id":15290491,"url":"https://github.com/veb-101/keras-vision","last_synced_at":"2025-10-07T18:09:25.886Z","repository":{"id":232048123,"uuid":"783338157","full_name":"veb-101/keras-vision","owner":"veb-101","description":"Porting vision models to Keras 3 for easily accessibility. Contains MobileViT v1, MobileViT v2, fastvit","archived":false,"fork":false,"pushed_at":"2025-04-20T16:12:27.000Z","size":4671,"stargazers_count":14,"open_issues_count":1,"forks_count":3,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-09-07T08:21:32.230Z","etag":null,"topics":["cnn","computer-vision","deep-learning","fastvit","jax","keras","keras3","mobilevit","mobilevitv1","mobilevitv2","pytorch","self-attention","tensorflow","transformers"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/veb-101.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2024-04-07T16:04:51.000Z","updated_at":"2025-06-15T13:37:47.000Z","dependencies_parsed_at":"2024-04-07T17:24:29.943Z","dependency_job_id":"e6a25484-9a36-4f3e-a6ab-ba79540ac020","html_url":"https://github.com/veb-101/keras-vision","commit_stats":null,"previous_names":["veb-101/keras-vision"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/veb-101/keras-vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veb-101%2Fkeras-vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veb-101%2Fkeras-vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veb-101%2Fkeras-vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veb-101%2Fkeras-vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/veb-101","download_url":"https://codeload.github.com/veb-101/keras-vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veb-101%2Fkeras-vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278820735,"owners_count":26051767,"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","status":"online","status_checked_at":"2025-10-07T02:00:06.786Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cnn","computer-vision","deep-learning","fastvit","jax","keras","keras3","mobilevit","mobilevitv1","mobilevitv2","pytorch","self-attention","tensorflow","transformers"],"created_at":"2024-09-30T16:08:22.151Z","updated_at":"2025-10-07T18:09:25.881Z","avatar_url":"https://github.com/veb-101.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/keras-vision)](https://www.python.org/)  [![PyPI version](https://badge.fury.io/py/keras-vision.svg)](https://badge.fury.io/py/keras-vision) [![Keras](https://img.shields.io/badge/Keras%203.x-%23D00000.svg?logo=Keras\u0026logoColor=white)](https://github.com/keras-team/keras/releases) ![PyPI - Downloads](https://img.shields.io/pypi/dm/keras-vision?style=plastic\u0026logo=Keras\u0026logoColor=red\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fkeras-vision%2F)\n\nPorting all models from everywhere to Keras to leverage multi-backend support.\n\nCause why not?🤷🏻‍♂️\n\n# Table of Contents\n\n- [Table of Contents](#table-of-contents)\n  - [Progress](#progress)\n  - [Updates](#updates)\n  - [Quick Setup](#quick-setup)\n    - [Stable PyPi Package](#stable-pypi-package)\n    - [OR](#or)\n    - [Latest Git Updates](#latest-git-updates)\n  - [Models Supported](#models-supported)\n\n## Progress\n\n- Working on adding MobileNet V4\n\n## Updates\n\n1. [2025-03-12] Finished adding **FastViT** image classification model by Apple added. The model weights are available at [url](https://huggingface.co/veb-101/apple-fastvit-Keras-3/tree/main).\n2. [2025-02-22] Working (v1) FastViT classification code added.\n3. [2024-06-24] Released MobileViT v2 - All Image Classification variants.\n4. [2024-05-15] Fixed MobileViT v1 - Now works will all 3 backends. 🎉🎉\n5. [2024-05-04] Converted MobileViT to Keras 3 and released weights of all 3 variants.\n   1. Jax backend currently not working, I'm working on a fix.\n   2. Release: \u003chttps://github.com/veb-101/keras-vision/releases/tag/v0.4\u003e\n\n## Quick Setup\n\n### Stable PyPi Package\n\n```bash\npip install -U keras-vision\n```\n\n### OR\n\n### Latest Git Updates\n\n```bash\npip install git+https://github.com/veb-101/keras-vision.git\n```\n\n## Models Supported\n\n\u003ctable\u003e\n   \u003cthead\u003e\n      \u003ctr\u003e\n         \u003cth style=\"text-align:center\"\u003e\n            \u003cstrong\u003e# No.\u003c/strong\u003e\n         \u003c/th\u003e\n         \u003cth style=\"text-align:center\"\u003e\n            \u003cstrong\u003eModels\u003c/strong\u003e\n         \u003c/th\u003e\n         \u003cth style=\"text-align:center\"\u003e\n            \u003cstrong\u003ePaper\u003c/strong\u003e\n         \u003c/th\u003e\n         \u003cth style=\"text-align:center\"\u003e\n            \u003cstrong\u003eAdditional Materials\u003c/strong\u003e\n         \u003c/th\u003e\n         \u003cth style=\"text-align:center\"\u003e\n            \u003cstrong\u003eExample notebook\u003c/strong\u003e\n         \u003c/th\u003e\n         \u003cth style=\"text-align:center\"\u003e\n            \u003cstrong\u003eWeights URL\u003c/strong\u003e\n         \u003c/th\u003e\n      \u003c/tr\u003e\n   \u003c/thead\u003e\n   \u003ctbody\u003e\n      \u003ctr\u003e\n         \u003ctd style=\"text-align:center\"\u003e1\u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://github.com/veb-101/keras-vision/blob/main/keras_vision/MobileViT_v1/mobile_vit_v1.py\"\u003eMobileViT-V1\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://arxiv.org/abs/2110.02178\"\u003eMobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://learnopencv.com/mobilevit-keras-3/\"\u003eBlogpost: Building MobileViT In Keras 3\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://colab.research.google.com/github/veb-101/keras-vision/blob/main/examples/mobile_vit_v1.ipynb\"\u003eColab link\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://huggingface.co/veb-101/Keras-3-apple-mobilevit/tree/main/keras-3-mobilevit-v1-weights\"\u003e🤗\u003c/a\u003e\n         \u003c/td\u003e\n      \u003ctr\u003e\n         \u003ctd style=\"text-align:center\"\u003e2\u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://github.com/veb-101/keras-vision/blob/main/keras_vision/MobileViT_v2/mobile_vit_v2.py\"\u003eMobileViT-V2\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://arxiv.org/abs/2206.02680\"\u003eSeparable Self-attention for Mobile Vision Transformers\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            --\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://colab.research.google.com/github/veb-101/keras-vision/blob/main/examples/mobile_vit_v2.ipynb\"\u003eColab link\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://huggingface.co/veb-101/Keras-3-apple-mobilevit/tree/main/keras-3-mobilevit-v2-weights\"\u003e🤗\u003c/a\u003e\n         \u003c/td\u003e\n      \u003c/tr\u003e\n      \u003ctr\u003e\n         \u003ctd style=\"text-align:center\"\u003e2\u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://github.com/veb-101/keras-vision/blob/main/keras_vision/fastvit/fastvit.py\"\u003eFastViT\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://arxiv.org/abs/2206.02680\"\u003eFastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            --\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://colab.research.google.com/github/veb-101/keras-vision/blob/main/examples/fastvit.ipynb\"\u003eColab link\u003c/a\u003e\n         \u003c/td\u003e\n         \u003ctd style=\"text-align:center\"\u003e\n            \u003ca href=\"https://huggingface.co/veb-101/apple-fastvit-Keras-3/tree/main\"\u003e🤗\u003c/a\u003e\n         \u003c/td\u003e\n      \u003c/tr\u003e\n   \u003c/tbody\u003e\n\u003c/table\u003e\n\n\n## Citation\n\n* MobileViT-v1\n\n```\n@inproceedings{mehta2022mobilevit,\n     title={MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer},\n     author={Sachin Mehta and Mohammad Rastegari},\n     booktitle={International Conference on Learning Representations},\n     year={2022}\n}\n```\n\n* MobileViT-v2\n```\nMehta, S., \u0026 Rastegari, M. (2022). Separable Self-attention for Mobile Vision Transformers. ArXiv. https://arxiv.org/abs/2206.02680\n```\n\n* FastViT\n```\n@inproceedings{vasufastvit2023,\n  author = {Pavan Kumar Anasosalu Vasu and James Gabriel and Jeff Zhu and Oncel Tuzel and Anurag Ranjan},\n  title = {FastViT:  A Fast Hybrid Vision Transformer using Structural Reparameterization},\n  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},\n  year = {2023}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fveb-101%2Fkeras-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fveb-101%2Fkeras-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fveb-101%2Fkeras-vision/lists"}