Recurrent Feature Reasoning for Image Inpainting-image inpainting 实践

本文主要是介绍Recurrent Feature Reasoning for Image Inpainting-image inpainting 实践，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

Image inpainting 论文总结: https://github.com/geekyutao/Image-Inpainting

Recurrent Feature Reasoning for Image Inpainting

github: https://github.com/jingyuanli001/RFR-Inpainting

环境：Ubuntu16.04, python 3.6, cuda 10.0, pytorch 1.1.0

python run.py --data_root data --mask_root mask --model_path checkpoints/g_10000.pth --batch_size 1 --gpu 0

data_root 放图片 用的512*512

mask_root放mask

checkpoints 放预训练模型 

注意：paris的预训练模型迭代了60w次，run.py是60w开始。

这篇关于Recurrent Feature Reasoning for Image Inpainting-image inpainting 实践的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---