{"id":13777423,"url":"https://github.com/airctic/icevision","last_synced_at":"2025-05-14T04:10:31.290Z","repository":{"id":37287829,"uuid":"261059191","full_name":"airctic/icevision","owner":"airctic","description":"An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come","archived":false,"fork":false,"pushed_at":"2024-11-26T19:03:40.000Z","size":888954,"stargazers_count":857,"open_issues_count":83,"forks_count":148,"subscribers_count":22,"default_branch":"master","last_synced_at":"2025-05-12T11:23:45.537Z","etag":null,"topics":["ai","annotation-parsers","coco-dataset","coco-parser","computer-vision","deep-learning","effecientdet","fastai","faster-rcnn","mask-rcnn","object-detection","pycocotools","python","pytorch","pytorch-lightning","tutorials","voc-dataset","voc-parser"],"latest_commit_sha":null,"homepage":"https://airctic.github.io/icevision/","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/airctic.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":"2020-05-04T01:57:02.000Z","updated_at":"2025-04-19T20:32:21.000Z","dependencies_parsed_at":"2024-01-07T00:08:42.739Z","dependency_job_id":"4b5a7d1d-87b1-4cdb-8cc8-dd6d256ec9f5","html_url":"https://github.com/airctic/icevision","commit_stats":{"total_commits":1156,"total_committers":46,"mean_commits":"25.130434782608695","dds":0.5268166089965398,"last_synced_commit":"f7770b8f015539d518fdfb52fd0fe7b96daf08af"},"previous_names":[],"tags_count":41,"template":false,"template_full_name":"fastai/nbdev_template","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airctic%2Ficevision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airctic%2Ficevision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airctic%2Ficevision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airctic%2Ficevision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/airctic","download_url":"https://codeload.github.com/airctic/icevision/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254070124,"owners_count":22009560,"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":["ai","annotation-parsers","coco-dataset","coco-parser","computer-vision","deep-learning","effecientdet","fastai","faster-rcnn","mask-rcnn","object-detection","pycocotools","python","pytorch","pytorch-lightning","tutorials","voc-dataset","voc-parser"],"created_at":"2024-08-03T18:00:43.156Z","updated_at":"2025-05-14T04:10:26.269Z","avatar_url":"https://github.com/airctic.png","language":"Python","readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"images/icevision-logo-slogan.png\" alt=\"logo\" width=\"535px\" style=\"display: block; margin-left: auto; margin-right: auto\"/\u003e\n  \u003ch2\u003e\u003cb\u003eAn Agnostic Computer Vision Framework\u003c/b\u003e\u003c/h2\u003e\n\u003c/div\u003e\n\n* * * * *\n\n    \n[![tests](https://github.com/airctic/icevision/workflows/tests/badge.svg?event=push)](https://github.com/airctic/icevision/actions?query=workflow%3Atests)\n[![docs](https://github.com/airctic/icevision/workflows/docs/badge.svg)](https://airctic.com)\n[![codecov](https://codecov.io/gh/airctic/icevision/branch/master/graph/badge.svg)](https://codecov.io/gh/airctic/icevision)\n[![PyPI version](https://badge.fury.io/py/icevision.svg)](https://badge.fury.io/py/icevision)\n[![Downloads](https://pepy.tech/badge/icevision)](https://pepy.tech/project/icevision)\n\n[![black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![license](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/airctic/icevision/blob/master/LICENSE)\n[![Discord](https://img.shields.io/discord/735877944085446747?label=Discord\u0026logo=Discord)](https://discord.gg/2jqrwrQ)\n\n\u003c/div\u003e\n\n\n* * * * *\n\nIceVision is the first agnostic computer vision framework to offer a curated collection with hundreds of high-quality pre-trained models from [Torchvision](https://github.com/pytorch/vision), Open MMLab's [MMDetection](https://github.com/open-mmlab/mmdetection), Ultralytic's [YOLOv5](https://github.com/ultralytics/yolov5), Ross Wightman's [EfficientDet](https://github.com/rwightman/efficientdet-pytorch) and soon PyTorch Image Models. It orchestrates the end-to-end deep learning workflow allowing to train networks with easy-to-use robust high-performance libraries such as [PyTorch-Lightning](https://github.com/PyTorchLightning/pytorch-lightning) and [Fastai](https://github.com/fastai/fastai).\n\n**IceVision Unique Features:**\n\n- Data curation/cleaning with auto-fix\n\n- Access to an exploratory data analysis dashboard\n\n- Pluggable transforms for better model generalization \n\n- Access to hundreds of neural net models\n\n- Access to multiple training loop libraries\n\n- Multi-task training to efficiently combine object detection, segmentation, and classification models \n\n\u003c!-- Not included in docs - start --\u003e\n\n## Installation\n\n```bash\npip install icevision[all]\n```\n\nFor more installation options, check our [docs](https://airctic.com/0.7.0/install/).\n\n**Important:** We currently only support Linux/MacOS.\n\u003c!-- Not included in docs - end --\u003e\n\n## Quick Example: How to train the **Fridge Objects Dataset**\n\u003ca href=\"https://colab.research.google.com/github/airctic/icevision/blob/master/notebooks/getting_started_object_detection.ipynb\" target=\"_parent\"\u003e\u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/\u003e\u003c/a\u003e\n![image](images/icevision-readme.png)\n\n![image](images/icevision-end-to-end-training.gif)\n\n## Happy Learning!\nIf you need any assistance, feel free to:\n\n[Join our Forum](https://discord.gg/JDBeZYK)\n","funding_links":[],"categories":["Python","Libraries"],"sub_categories":["Computer Vision"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fairctic%2Ficevision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fairctic%2Ficevision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fairctic%2Ficevision/lists"}