{"id":13443948,"url":"https://github.com/cavalleria/cavaface","last_synced_at":"2025-03-20T17:32:28.739Z","repository":{"id":41315168,"uuid":"255841322","full_name":"cavalleria/cavaface","owner":"cavalleria","description":"face recognition training project(pytorch)","archived":false,"fork":false,"pushed_at":"2021-11-12T08:01:36.000Z","size":312,"stargazers_count":461,"open_issues_count":31,"forks_count":87,"subscribers_count":24,"default_branch":"master","last_synced_at":"2024-10-28T07:41:55.385Z","etag":null,"topics":["amsoftmax","apex","arcface","arcnegface","attention-irse","circleloss","cosface","curricularface","dataparallel","efficientnet","face-recognition","ghostnet","loss","mixup","model-parallel","network","pytorch","randaugment","resnest","resnet-irse"],"latest_commit_sha":null,"homepage":"","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/cavalleria.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":"2020-04-15T07:39:58.000Z","updated_at":"2024-10-10T19:37:22.000Z","dependencies_parsed_at":"2022-08-10T01:54:07.377Z","dependency_job_id":null,"html_url":"https://github.com/cavalleria/cavaface","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/cavalleria%2Fcavaface","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cavalleria%2Fcavaface/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cavalleria%2Fcavaface/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cavalleria%2Fcavaface/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cavalleria","download_url":"https://codeload.github.com/cavalleria/cavaface/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660705,"owners_count":20489382,"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":["amsoftmax","apex","arcface","arcnegface","attention-irse","circleloss","cosface","curricularface","dataparallel","efficientnet","face-recognition","ghostnet","loss","mixup","model-parallel","network","pytorch","randaugment","resnest","resnet-irse"],"created_at":"2024-07-31T03:02:14.729Z","updated_at":"2025-10-14T12:09:57.377Z","avatar_url":"https://github.com/cavalleria.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# cavaface: A Pytorch Training Framework for Deep Face Recognition\n\n[![python-url](https://img.shields.io/badge/Python-3.x-red.svg)](https://www.python.org/)\n[![pytorch-url](https://img.shields.io/badge/Pytorch-1.9-blue.svg)](https://pytorch.org/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n![Docker Pulls](https://img.shields.io/docker/pulls/cavall/cavaface_env?logo=docker).\n\nBy Yaobin Li and Liying Chi\n\n## Introduction\n\nThis repo provides a high-performance distribute parallel training framework for face recognition with pytorch, including various backbones (e.g., ResNet, IR, IR-SE, ResNeXt, AttentionNet-IR-SE, ResNeSt, HRNet, etc.), various losses (e.g., Softmax, Focal, SphereFace, CosFace, AmSoftmax, ArcFace, ArcNegFace, CurricularFace, Li-Arcface, QAMFace, etc.), various data augmentation(e.g., RandomErasing, Mixup, RandAugment, Cutout, CutMix, etc.) and bags of tricks for improving performance (e.g., FP16 training(apex), Label smooth, LR warmup, etc)\n\n## Features\n\n\u003cdetails open\u003e\n\u003csummary\u003e(click to collapse)\u003c/summary\u003e\n\n* **Backbone**\n  * [x] ResNet(IR-SE)\n  * [x] ResNeXt\n  * [x] DenseNet\n  * [x] MobileFaceNet\n  * [x] MobileNetV3\n  * [x] EfficientNet\n  * [x] ProxylessNas\n  * [x] GhostNet\n  * [x] AttentionNet-IRSE\n  * [x] ResNeSt\n  * [x] ReXNet\n  * [x] MobileNetV2\n  * [x] MobileNeXt\n* **Attention Module**\n  * [x] SE\n  * [x] CBAM\n  * [x] ECA\n  * [x] GCT\n* **Loss**\n  * [x] Softmax\n  * [x] SphereFace\n  * [x] AMSoftmax\n  * [x] CosFace\n  * [x] ArcFace\n  * [x] Combined Loss\n  * [x] AdaCos\n  * [x] SV-X-Softmax\n  * [x] CurricularFace\n  * [x] ArcNegFace\n  * [x] Li-Arcface\n  * [x] QAMFace\n  * [x] Circle Loss \n* **Parallel Training**\n  * [x] DDP\n  * [x] Model Parallel\n* **Automatic Mixed Precision**\n  * [x] AMP\n* **Optimizer**\n  * [x] LRScheduler([faireq](https://github.com/pytorch/fairseq/tree/master/fairseq/optim/lr_scheduler),[rwightman](https://github.com/rwightman/pytorch-image-models/tree/master/timm/scheduler))\n  * [x] Optim(SGD,Adam,RAdam,LookAhead,Ranger,AdamP,SGDP)\n  * [x] ZeRO\n* **[Data Augmentation**\n  * [x] RandomErasing\n  * [x] Mixup\n  * [x] RandAugment\n  * [x] Cutout\n  * [x] CutMix\n  * [x] Colorjitter \n* **Distillation**\n  * [ ] KnowledgeDistillation\n  * [ ] Multi Feature KD\n* **Bag of Tricks**\n  * [x] Label smooth\n  * [x] LR warmup\n\n\u003c/details\u003e\n\n## Installation\n\nSee [INSTALL.md](https://github.com/cavalleria/cavaface.pytorch/blob/master/docs/INSTALL.md).\n\n## Quick start\n\nSee [GETTING_STARTED.md](https://github.com/cavalleria/cavaface.pytorch/blob/master/docs/GETTING_STARTED.md).\n\n## Model Zoo and Benchmark\n\nSee [MODEL_ZOO.md](https://github.com/cavalleria/cavaface.pytorch/blob/master/docs/MODEL_ZOO.md).\n\n## License\n\ncavaface is released under the [MIT license](https://github.com/cavalleria/cavaface.pytorch/blob/master/docs/LICENSE).\n\n## Acknowledgement\n\n* This repo is modified and adapted on these great repositories [face.evoLVe.PyTorch](https://github.com/ZhaoJ9014/face.evoLVe.PyTorch), [CurricularFace](https://github.com/HuangYG123/CurricularFace), [insightface](https://github.com/deepinsight/insightface) and [imgclsmob](https://github.com/osmr/imgclsmob/)\n* The evaluation tools is developed by [Charrin](https://github.com/Charrin)\n\n## Contact\n\n```markdown\ncavallyb@gmail.com\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcavalleria%2Fcavaface","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcavalleria%2Fcavaface","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcavalleria%2Fcavaface/lists"}