Question about image sampling

mit-han-lab / data-efficient-gans

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

https://arxiv.org/abs/2006.10738

BSD 2-Clause "Simplified" License

1.27k stars 175 forks source link

Open cuikaiwen18 opened 3 years ago

cuikaiwen18 commented 3 years ago

Hi,

Do you sample the 1k images from the FFHQ dataset randomly for training or is there a specific way to sample these images?

zsyzzsoft commented 3 years ago

We always use the first 1k images in the FFHQ tfrecord file.