{"id":20607293,"url":"https://github.com/albumentations-team/autoalbument","last_synced_at":"2025-04-07T17:10:45.297Z","repository":{"id":41089335,"uuid":"299343389","full_name":"albumentations-team/autoalbument","owner":"albumentations-team","description":"AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/","archived":false,"fork":false,"pushed_at":"2021-09-04T14:42:15.000Z","size":246,"stargazers_count":205,"open_issues_count":27,"forks_count":19,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-03-31T15:18:42.872Z","etag":null,"topics":["augmentation","automated-machine-learning","automl","computer-vision","deep-learning","image-augmentation","machine-learning","pytorch"],"latest_commit_sha":null,"homepage":"https://albumentations.ai/docs/autoalbument/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/albumentations-team.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":"2020-09-28T14:58:01.000Z","updated_at":"2025-03-13T12:30:25.000Z","dependencies_parsed_at":"2022-07-21T04:35:05.115Z","dependency_job_id":null,"html_url":"https://github.com/albumentations-team/autoalbument","commit_stats":null,"previous_names":[],"tags_count":9,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albumentations-team%2Fautoalbument","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albumentations-team%2Fautoalbument/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albumentations-team%2Fautoalbument/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albumentations-team%2Fautoalbument/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/albumentations-team","download_url":"https://codeload.github.com/albumentations-team/autoalbument/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247694876,"owners_count":20980733,"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":["augmentation","automated-machine-learning","automl","computer-vision","deep-learning","image-augmentation","machine-learning","pytorch"],"created_at":"2024-11-16T10:06:19.615Z","updated_at":"2025-04-07T17:10:45.276Z","avatar_url":"https://github.com/albumentations-team.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AutoAlbument\n\nAutoAlbument is an AutoML tool that learns image augmentation policies from data using the [Faster AutoAugment algorithm](https://arxiv.org/abs/1911.06987). It relieves the user from the burden of manually selecting augmentations and tuning their parameters. AutoAlbument provides a complete ready-to-use configuration for an augmentation pipeline.\n\nThe library supports image classification and semantic segmentation tasks. You can use [Albumentations](https://github.com/albumentations-team/albumentations) to utilize policies discovered by AutoAlbument in your computer vision pipelines.\n\nThe documentation is available at [https://albumentations.ai/docs/autoalbument/](https://albumentations.ai/docs/autoalbument/)\n\n## Benchmarks\n\nHere is a comparison between a baseline augmentation strategy and an augmentation policy discovered by AutoAlbument\nfor different classification and semantic segmentation tasks. You can read more about these benchmarks in the [autoalbument-benchmarks](https://github.com/albumentations-team/autoalbument-benchmarks) repository.\n\n### Classification\n| Dataset  | Baseline Top-1 Accuracy | AutoAlbument Top-1 Accuracy  |\n|----------|:-----------------------:|:----------------------------:|\n| [CIFAR10](https://github.com/albumentations-team/autoalbument-benchmarks#cifar-10-classification)  |          91.79          |           **96.02**          |\n| [SVHN](https://github.com/albumentations-team/autoalbument-benchmarks#svhn-classification)     |          98.31          |           **98.48**          |\n| [ImageNet](https://github.com/albumentations-team/autoalbument-benchmarks#imagenet-classification) |          73.27          |           **75.17**          |\n\n\n### Semantic segmentation\n| Dataset    | Baseline mIOU | AutoAlbument mIOU |\n|------------|:-------------:|:-----------------:|\n| [Pascal VOC](https://github.com/albumentations-team/autoalbument-benchmarks#pascal-voc-semantic-segmentation) |     73.34     |     **75.55**     |\n| [Cityscapes](https://github.com/albumentations-team/autoalbument-benchmarks#cityscapes) |     79.47     |     **79.92**     |\n\n\n## Installation\nAutoAlbument requires Python 3.6 or higher. To install the latest stable version from PyPI:\n\n`pip install -U autoalbument`\n\n## How to use AutoAlbument\n\n![How to use AutoAlbument](https://albumentations.ai/docs/images/autoalbument/how_to_use/autoalbument_usage.png)\n\n1. You need to create a configuration file with AutoAlbument parameters and a Python file that implements a custom PyTorch Dataset for your data. Next, you need to pass those files to AutoAlbument.\n2. AutoAlbument will use Generative Adversarial Network to discover augmentation policies and then create a file containing those policies.\n3. Finally, you can use [Albumentations](https://github.com/albumentations-team/albumentations) to load augmentation policies from the file and utilize them in your computer vision pipelines.\n\nYou can read the detailed description of all steps at [https://albumentations.ai/docs/autoalbument/how_to_use/](https://albumentations.ai/docs/autoalbument/how_to_use/)\n\n## Examples\nThe [`examples`](https://github.com/albumentations-team/autoalbument/tree/master/examples) directory contains example configs for different tasks and datasets:\n\n### Classification\n- [CIFAR10](https://github.com/albumentations-team/autoalbument/tree/master/examples/cifar10)\n- [SVHN](https://github.com/albumentations-team/autoalbument/tree/master/examples/svhn)\n- [ImageNet](https://github.com/albumentations-team/autoalbument/tree/master/examples/imagenet)\n\n### Semantic segmentation\n- [Pascal VOC](https://github.com/albumentations-team/autoalbument/tree/master/examples/pascal_voc)\n- [Cityscapes](https://github.com/albumentations-team/autoalbument/tree/master/examples/cityscapes)\n\nTo run the search with an example config:\n\n```\nautoalbument-search --config-dir \u003c/path/to/directory_with_dataset.py_and_search.yaml\u003e\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falbumentations-team%2Fautoalbument","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falbumentations-team%2Fautoalbument","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falbumentations-team%2Fautoalbument/lists"}