{"id":15650544,"url":"https://github.com/ayulockin/dataaugmentationtf","last_synced_at":"2025-04-30T18:06:19.100Z","repository":{"id":109750123,"uuid":"265839448","full_name":"ayulockin/DataAugmentationTF","owner":"ayulockin","description":"Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline. ","archived":false,"fork":false,"pushed_at":"2020-07-03T07:56:21.000Z","size":13451,"stargazers_count":34,"open_issues_count":0,"forks_count":12,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-30T18:06:12.553Z","etag":null,"topics":["augmix","computer-vision","cutmix","cutout","data-augmentation","deeplearning","keras","mixup","tensorflow2"],"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/ayulockin.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}},"created_at":"2020-05-21T12:11:30.000Z","updated_at":"2025-01-09T23:59:39.000Z","dependencies_parsed_at":"2023-04-25T19:15:19.870Z","dependency_job_id":null,"html_url":"https://github.com/ayulockin/DataAugmentationTF","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/ayulockin%2FDataAugmentationTF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayulockin%2FDataAugmentationTF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayulockin%2FDataAugmentationTF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayulockin%2FDataAugmentationTF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ayulockin","download_url":"https://codeload.github.com/ayulockin/DataAugmentationTF/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251758162,"owners_count":21638988,"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":["augmix","computer-vision","cutmix","cutout","data-augmentation","deeplearning","keras","mixup","tensorflow2"],"created_at":"2024-10-03T12:35:00.997Z","updated_at":"2025-04-30T18:06:19.057Z","avatar_url":"https://github.com/ayulockin.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Modern Data Augmentation Techniques for Computer Vision\n\n## About\n\nImplementation of various data augmentation techniques in TensorFlow 2.x. They can be easily used in your training pipeline. This repository contain the supplementary notebooks for the [Modern Data Augmentation Techniques for Computer Vision](https://app.wandb.ai/authors/tfaugmentation/reports/Modern-Data-Augmentation-Techniques-for-Computer-Vision--VmlldzoxNDA2NTc)(Weights and Biases) report.\n\n## Techniques Covered\n\n* [Cutout](https://github.com/ayulockin/DataAugmentationTF/blob/master/CIFAR_10_with_Cutout_Augmentation.ipynb)\n* [Mixup](https://github.com/ayulockin/DataAugmentationTF/blob/master/CIFAR_10_with_Mixup_Augmentation.ipynb)\n* [CutMix](https://github.com/ayulockin/DataAugmentationTF/blob/master/CIFAR_10_with_CutMix_Augmentation.ipynb)\n* [Augmix](https://github.com/ayulockin/DataAugmentationTF/blob/master/Cifar_10_with_AugMix_Augmentation.ipynb)\n\n**Note**: Cutout, Mixup and CutMix are implememted in `tf.data` and can be found in the linked colab notebooks. I am using TensorFlow 2.x implementation of AugMix by [Aakash Nain](https://twitter.com/A_K_Nain?s=09). His repo can be found [here](https://github.com/AakashKumarNain/AugMix_TF2). The [fork](https://github.com/ayulockin/AugMix_TF2) of this repo contains Weights and Biases integration and some additional command like arguments for more control.   \n\n## Result\n\nCheck out the linked [report](https://app.wandb.ai/authors/tfaugmentation/reports/Modern-Data-Augmentation-Techniques-for-Computer-Vision--VmlldzoxNDA2NTc) for:\n\n* The comparative study of these augmentation techniques. \n* Augmentation implementations.\n* Evaluation of these augmentation techniques against [Cifar-10-C dataset](https://zenodo.org/record/2535967).\n\n## Model Used\n\n![ResNet-20](https://github.com/ayulockin/DataAugmentationTF/blob/master/images/model.png)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayulockin%2Fdataaugmentationtf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fayulockin%2Fdataaugmentationtf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayulockin%2Fdataaugmentationtf/lists"}