https://openmmlab.com/cvpr2021-tutorial

    OpenMMLabis an open-source algorithm platform for computer vision. It aims to provide a solid benchmark and promote the reproducibility for academic research. We have released more than 10 high-quality projects and toolboxes in various research areas such as image classification, object detection, semantic segmentation, action recognition, etc. OpenMMLab has made public more than 160 algorithms and 1300 checkpoints. Over the past two years, OpenMMLab gains popularity among both academia and industry. It receives over 37,000 stars on GitHub and involves more than 610 contributors in the community.