Real-ESRGAN-docker

Simple image to upscaling images and videos in by Real-ESRGAN

准备数据

1. 将图片或视频放入data/input文件夹
2. 在docker-compose.yml可以自定义输入输出文件夹，均从data/目录进行，输入文件夹默认为data/input，输出文件夹为data/output
3. 使用以下命令启动

sudo docker-compose up

官方命令行示例

Usage: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile -o outfile [options]...

A common command: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile --outscale 3.5 --face_enhance

  -h                   show this help
  -i --input           Input image or folder. Default: inputs
  -o --output          Output folder. Default: results
  -n --model_name      Model name. Default: RealESRGAN_x4plus
  -s, --outscale       The final upsampling scale of the image. Default: 4
  --suffix             Suffix of the restored image. Default: out
  -t, --tile           Tile size, 0 for no tile during testing. Default: 0
  --face_enhance       Whether to use GFPGAN to enhance face. Default: False
  --fp32               Use fp32 precision during inference. Default: fp16 (half precision).
  --ext                Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto

本库为简化版本，只有输入输出和模型自定义，暂未开放其他参数，可以自行到scripts/start.sh修改

python 环境修改

由于与官方环境有出入，docker 选择了带有 torch 的镜像，我对requirements.txt进行了修改，无需重复安装 torch 和 torchvision

这一改就是三天两夜，终于跑通了。

BibTeX

@InProceedings{wang2021realesrgan,
    author    = {Xintao Wang and Liangbin Xie and Chao Dong and Ying Shan},
    title     = {Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
    booktitle = {International Conference on Computer Vision Workshops (ICCVW)},
    date      = {2021}
}