How to train the VAE image tokenizer?

BrandonHanx / mmf

[ECCV 2022] FashionViL: Fashion-Focused V+L Representation Learning

https://mmf.sh/

Other

58 stars 7 forks source link

How to train the VAE image tokenizer? #20

Open deepalchemist opened 7 months ago

deepalchemist commented 7 months ago

🚀 Feature

Thanks for your excellent work！ As mentioned in the paper， we first train a discrete VAE as the image tokenizer on our collected fashion images with the perceputal loss.

Does the code support the image tokenizer training?