search

snap-research / Panda-70M

[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
https://snap-research.github.io/Panda-70M/
438 stars 15 forks source link

Training code #47

Open LiquidAmmonia opened 2 months ago

LiquidAmmonia commented 2 months ago

Hi, great work and thank you for your contribution~

Is there any plan to release the caption model's training script?

Thank you

tsaishien-chen commented 2 months ago

Hi @LiquidAmmonia,

Thanks for your interest in our captioning code! Our in-house legal team are reviewing the training code now and there is no clear promise that we are able to release them in the future. But, we mostly follow the training code in Video-LLaMA. You can also try to check the training scripts. Sorry for your inconvenience.