search

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

Load own feature extractor #68

Closed iumyx2612 closed 3 years ago

iumyx2612 commented 3 years ago

How can I load my own feature extractor to calculate FID score on my own datasets? I use my own dataset that's anime-related and I don't think the pre-trained inception-v3 model is good for this

iumyx2612 commented 3 years ago

Sorry, just realize this is quite a silly question to ask