🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Trax — Deep Learning with Clear Code and Speed

Real-Time High-Resolution Background Matting

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

Pretrained language model with 100B parameters

A Simple and Versatile Framework for Object Detection and Instance Recognition

[NeurIPS'22] Official code of "ComMU: Dataset for Combinatorial Music Generation"