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

docs: add if cuda available #7

Closed pphuc25 closed 7 months ago

pphuc25 commented 7 months ago

Hi, I encountered a bug when performing inference without a GPU. It appears that your code defaults to expecting CUDA. I believe your code could be made more versatile by incorporating an if-else case to handle both GPU and CPU devices.

Thank you for reviewing my pull request.

LinB203 commented 7 months ago

Sure, let's merge. Thanks for your contribution.