salesforce/BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

语言：Jupyter Notebook · GitHub 星标：5,703 · Fork：765

话题：image-captioning · image-text-retrieval · vision-and-language-pre-training · vision-language · vision-language-transformer · visual-question-answering · visual-reasoning

在 GitHub 上查看原仓库