weixin_43723625的博客

Helen人脸数据集包括2330张人脸图像，并且每张人脸图像包含11个部位的掩模，通常做人脸分割只需要面部以及面部特征掩模即可。数据集文件的整体结构如下：

GTA5:S. R. Richter, V. Vineet, S. Roth, and V. Koltun, “Playing for data: Ground truth from computer games,” in Proc. of the European Conference on Computer Vision (ECCV), J. Matas, B. Leibe, M. Welling and N. Sebe, Eds., ser. LNCS, Springer, 2016https

中大人脸素描FERET数据库（CUFSF）：https://www.datafountain.cn/datasets/191

线稿上色的数据集：dataset link：https://pan.baidu.com/s/1Abm7V6J2uNOy5U6nvsRSlgkey：eepvtxt文件生成import osimport globdef Create_Txt(data_name, data_path, data_class,txt_path, ratio = 0.01): # absolute path data_path = os.path.join(data_pa