How did you split the train dataset and test dataset for ffhq inversion？ - Githubissues

genforce / idinvert_pytorch

[ECCV 2020] In-Domain GAN Inversion for Real Image Editing (PyTorch code)

https://genforce.github.io/idinvert/

MIT License

410 stars 54 forks source link

How did you split the train dataset and test dataset for ffhq inversion？ #17

Open wty-ustc opened 3 years ago

wty-ustc commented 3 years ago

How did you split the train dataset and test dataset for ffhq inversion？

zhujiapeng commented 3 years ago

Take the first 65000 images as the training set and take the rest as the test set.