search

PKU-YuanGroup / LanguageBind

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
https://arxiv.org/abs/2310.01852
MIT License
549 stars 44 forks source link

About download weights #17

Closed dongfeicui closed 5 months ago

dongfeicui commented 5 months ago

Why do I download weights again every time I run inference.py ?

LinB203 commented 5 months ago

You can change what encoders you want to use here. The default code will download image, video, depth and thermal encoder. There are some instructions about how to use different branch of LanguageBind if you only use a single modality.