FaceXLib

English | 简体中文

---

facexlib aims at providing ready-to-use face-related functions based on current SOTA open-source methods. <br> Only PyTorch reference codes are available. For training or fine-tuning, please refer to their original repositories listed below. <br> Note that we just provide a collection of these algorithms. You need to refer to their original LICENCEs for your intended use.

If facexlib is helpful in your projects, please help to :star: this repo. Thanks:blush: <br> Other recommended projects:   :arrow_forward: Real-ESRGAN   :arrow_forward: GFPGAN   :arrow_forward: BasicSR

---

:sparkles: Functions

| Function | Sources | Original LICENSE | | :--- | :---: | :---: | | Detection | Pytorch_Retinaface | MIT | | Alignment |AdaptiveWingLoss | Apache 2.0 | | Recognition | InsightFace_Pytorch | MIT | | Parsing | face-parsing.PyTorch | MIT | | Matting | MODNet | CC 4.0 | | Headpose | deep-head-pose | Apache 2.0 | | Tracking | SORT | GPL 3.0 | | Assessment | hyperIQA | - | | Utils | Face Restoration Helper | - |

:eyes: Demo and Tutorials

:wrench: Dependencies and Installation

• Python >= 3.7 (Recommend to use Anaconda or Miniconda)
• PyTorch >= 1.7
• Option: NVIDIA GPU + CUDA

Installation

pip install facexlib

Pre-trained models

It will automatically download pre-trained models at the first inference. <br> If your network is not stable, you can download in advance (may with other download tools), and put them in the folder: PACKAGE_ROOT_PATH/facexlib/weights.

:scroll: License and Acknowledgement

This project is released under the MIT license. <br>

:e-mail: Contact

If you have any question, open an issue or email xintao.wang@outlook.com.