AI面部修复项目：GFP-GAN

GitHub项目页：
https://github.com/TencentARC/GFPGAN

Hugging Face试玩传送门：
https://huggingface.co/spaces/akhaliq/GFPGAN

安装anaconda

下载解压GFPGAN-0.2.0.zip文件

安装dependent 包

安装 basicsr - https://github.com/xinntao/BasicSR

# We use BasicSR for both training and inference

pip install basicsr

安装 facexlib - https://github.com/xinntao/facexlib

# We use face detection and face restoration helper in the facexlib package

pip install facexlib

pip install -r requirements.txt

图片推理转换

python inference_gfpgan_full.py --upscale_factor 2 --test_path inputs/whole_imgs --save_root results

 已训练模型https://github.com/TencentARC/GFPGAN/releases/download/v0.2.0/GFPGANCleanv1-NoCE-C2.pth 下载拷贝到 experiments/pretrained_models目录

相关参数配置

    parser.add_argument('--upscale_factor', type=int, default=2)
    parser.add_argument('--arch', type=str, default='clean')
    parser.add_argument('--channel', type=int, default=2)
    parser.add_argument('--model_path', type=str, default='experiments/pretrained_models/GFPGANCleanv1-NoCE-C2.pth')
    parser.add_argument('--test_path', type=str, default='inputs/whole_imgs')
    parser.add_argument('--suffix', type=str, default=None, help='Suffix of the restored faces')
    parser.add_argument('--only_center_face', action='store_true')
    parser.add_argument('--aligned', action='store_true')
    parser.add_argument('--paste_back', action='store_false')
    parser.add_argument('--save_root', type=str, default='results')