IsaacRodgz/ConcatBERT

Baseline model for multimodal classification based on images and text. Text representation obtained from pretrained BERT base model and image representation obtained from VGG16 pretrained model.

语言：Jupyter Notebook · GitHub 星标：43 · Fork：6

话题：deep-learning · late-fusion · multimodal · multimodal-deep-learning · nlp · pytorch

在 GitHub 上查看原仓库