AILab-CVC / SEED

Official implementation of SEED-LLaMA (ICLR 2024).
https://ailab-cvc.github.io/seed
Other
515 stars 30 forks source link

Where are the core code lines that transform image to discrete token? #42

Closed guotong1988 closed 1 month ago

guotong1988 commented 1 month ago

Great work to learn!

Thank you very much!

geyuying commented 1 month ago

You can refer to line 89 of models/seed_llama_tokenizer.py, which discretizes images to codes.