{"id":13443935,"url":"https://github.com/zisianw/FaceBoxes.PyTorch","last_synced_at":"2025-03-20T17:32:24.271Z","repository":{"id":45566530,"uuid":"165017326","full_name":"zisianw/FaceBoxes.PyTorch","owner":"zisianw","description":"A PyTorch Implementation of FaceBoxes","archived":false,"fork":false,"pushed_at":"2024-12-11T02:53:22.000Z","size":207,"stargazers_count":848,"open_issues_count":18,"forks_count":213,"subscribers_count":19,"default_branch":"master","last_synced_at":"2024-12-11T03:28:55.435Z","etag":null,"topics":["face-detection","faceboxes","pytorch"],"latest_commit_sha":null,"homepage":null,"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/zisianw.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":"2019-01-10T08:04:39.000Z","updated_at":"2024-12-11T02:53:27.000Z","dependencies_parsed_at":"2022-09-04T13:00:24.827Z","dependency_job_id":null,"html_url":"https://github.com/zisianw/FaceBoxes.PyTorch","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/zisianw%2FFaceBoxes.PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zisianw%2FFaceBoxes.PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zisianw%2FFaceBoxes.PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zisianw%2FFaceBoxes.PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zisianw","download_url":"https://codeload.github.com/zisianw/FaceBoxes.PyTorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660683,"owners_count":20489380,"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":["face-detection","faceboxes","pytorch"],"created_at":"2024-07-31T03:02:14.396Z","updated_at":"2025-03-20T17:32:19.262Z","avatar_url":"https://github.com/zisianw.png","language":"Python","funding_links":[],"categories":["Python","Paper implementations｜论文实现","Paper implementations"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"# FaceBoxes in PyTorch\n\n[![License](https://img.shields.io/badge/license-BSD-blue.svg)](LICENSE)\n\nBy [Zisian Wong](https://github.com/zisianw), [Shifeng Zhang](http://www.cbsr.ia.ac.cn/users/sfzhang/)\n\nA [PyTorch](https://pytorch.org/) implementation of [FaceBoxes: A CPU Real-time Face Detector with High Accuracy](https://arxiv.org/abs/1708.05234). The official code in Caffe can be found [here](https://github.com/sfzhang15/FaceBoxes).\n\n## Performance\n| Dataset | Original Caffe | PyTorch Implementation |\n|:-|:-:|:-:|\n| AFW | 98.98 % | 98.55% |\n| PASCAL | 96.77 % | 97.05% |\n| FDDB | 95.90 % | 96.00% |\n\n## Citation\nPlease cite the paper in your publications if it helps your research:\n\n    @inproceedings{zhang2017faceboxes,\n      title = {Faceboxes: A CPU Real-time Face Detector with High Accuracy},\n      author = {Zhang, Shifeng and Zhu, Xiangyu and Lei, Zhen and Shi, Hailin and Wang, Xiaobo and Li, Stan Z.},\n      booktitle = {IJCB},\n      year = {2017}\n    }\n\n### Contents\n- [Installation](#installation)\n- [Training](#training)\n- [Evaluation](#evaluation)\n- [References](#references)\n\n## Installation\n1. Install [PyTorch](https://pytorch.org/) \u003e= v1.0.0 following official instruction.\n\n2. Clone this repository. We will call the cloned directory as `$FaceBoxes_ROOT`.\n```Shell\ngit clone https://github.com/zisianw/FaceBoxes.PyTorch.git\n```\n\n3. Compile the nms:\n```Shell\n./make.sh\n```\n\n_Note: Codes are based on Python 3+._\n\n## Training\n1. Download [WIDER FACE](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/index.html) dataset, place the images under this directory:\n  ```Shell\n  $FaceBoxes_ROOT/data/WIDER_FACE/images\n  ```\n2. Convert WIDER FACE annotations to VOC format or download [our converted annotations](https://drive.google.com/open?id=1-s4QCu_v76yNwR-yXMfGqMGgHQ30WxV2), place them under this directory:\n  ```Shell\n  $FaceBoxes_ROOT/data/WIDER_FACE/annotations\n  ```\n\n3. Train the model using WIDER FACE:\n  ```Shell\n  cd $FaceBoxes_ROOT/\n  python3 train.py\n  ```\n\nIf you do not wish to train the model, you can download [our pre-trained model](https://drive.google.com/file/d/1tRVwOlu0QtjvADQ2H7vqrRwsWEmaqioI) and save it in `$FaceBoxes_ROOT/weights`.\n\n\n## Evaluation\n1. Download the images of [AFW](https://drive.google.com/open?id=1Kl2Cjy8IwrkYDwMbe_9DVuAwTHJ8fjev), [PASCAL Face](https://drive.google.com/open?id=1p7dDQgYh2RBPUZSlOQVU4PgaSKlq64ik) and [FDDB](https://drive.google.com/open?id=17t4WULUDgZgiSy5kpCax4aooyPaz3GQH) to:\n```Shell\n$FaceBoxes_ROOT/data/AFW/images/\n$FaceBoxes_ROOT/data/PASCAL/images/\n$FaceBoxes_ROOT/data/FDDB/images/\n```\n\n2. Evaluate the trained model using:\n```Shell\n# dataset choices = ['AFW', 'PASCAL', 'FDDB']\npython3 test.py --dataset FDDB\n# evaluate using cpu\npython3 test.py --cpu\n# visualize detection results\npython3 test.py -s --vis_thres 0.3\n```\n\n3. Download [eval_tool](https://github.com/sfzhang15/face-eval) to evaluate the performance.\n    \n## References\n- [Official release (Caffe)](https://github.com/sfzhang15/FaceBoxes)\n- A huge thank you to SSD ports in PyTorch that have been helpful:\n  * [ssd.pytorch](https://github.com/amdegroot/ssd.pytorch), [RFBNet](https://github.com/ruinmessi/RFBNet)\n\n  _Note: If you can not download the converted annotations, the provided images and the trained model through the above links, you can download them through [BaiduYun](https://pan.baidu.com/s/1HoW3wbldnbmgW2PS4i4Irw)._\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzisianw%2FFaceBoxes.PyTorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzisianw%2FFaceBoxes.PyTorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzisianw%2FFaceBoxes.PyTorch/lists"}