X-PLUG/mPLUG

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections. (EMNLP 2022)

语言：Python · GitHub 星标：97 · Fork：8

话题：image-captioning · image-text · image-text-retrieval · multimodal · pretraining · pytorch · transformer · visual-language

在 GitHub 上查看原仓库