MMF is a modular framework for vision and language multimodal research from Facebook AI Research. MMF contains reference implementations of state-of-the-art vision and language models.
MMF is powered by PyTorch, allows distributed training and is un-opinionated, scalable and fast. Use MMF to bootstrap for your next vision and language multimodal research project
Website: https://mmf.sh/
GitHub: https://github.com/facebookresearch/mmf
Tutorial: https://bit.ly/a-multimodal-framework