照片修复-GPEN框架-编程知识

照片修复-GPEN框架

一照片修复-GPEN介绍：

gpen是一个优秀的照片修复框架,关键是开源的，它是基于GAN先验嵌入网络的野外盲脸复原，特别是针对人脸修复效果特别好，先看一下官方的效果图：

修复效果图前后对比：

二安装GPEN

1 下载GPEN

从github下载GPEN源码

git clone https://github.com/yangxy/GPEN.git
cd GPEN

2 安装GPEN环境

安装搭建环境与依赖

pip install "modelscope[cv]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

安装项目依赖包：

pip install -r requirements.txt

安装 torch

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

环境安装完后占用大概大小（不同的版本，大小也不同）

3 下载项目数据模型：

[RetinaFace-R50](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/RetinaFace-R50.pth) [ParseNet-latest](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/ParseNet-latest.pth) | [model_ir_se50](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/model_ir_se50.pth) | [GPEN-BFR-512](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-BFR-512.pth) | [GPEN-BFR-512-D](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-BFR-512-D.pth) | [GPEN-BFR-256](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-BFR-256.pth) | [GPEN-BFR-256-D](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-BFR-256-D.pth) | [GPEN-Colorization-1024](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-Colorization-1024.pth) | [GPEN-Inpainting-1024](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-Inpainting-1024.pth) | [GPEN-Seg2face-512](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-Seg2face-512.pth) | [realesrnet_x1](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/realesrnet_x1.pth) | [realesrnet_x2](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/realesrnet_x2.pth) | [realesrnet_x4](https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/realesrnet_x4.pth)

如下图，已下载好放在weights目录下：

三运行GPEN修复照片

python demo.py --task FaceEnhancement --model GPEN-BFR-512 --in_size 512 --channel_multiplier 2 --narrow 1 --use_sr --sr_scale 4 --use_cuda --save_face --indir examples/imgs --outdir examples/outs-bfr