OpenMMLab builds the most influential open-source computer vision algorithm system in the deep learning era. It aims to
- provide high-quality libraries to reduce the difficulties in algorithm reimplementation
- create efficient deployment toolchains targeting a variety of backends and devices
- build a solid foundation for computer vision research and development
- bridge the gap between academic research and industrial applications with full-stack toolchains
Based on PyTorch, OpenMMLab develops MMEngine to provide universal training and evaluation engine, and MMCV to provide neural network operators and data transforms, which serves as a foundation of the whole project. Since the initial release in October 2018, OpenMMLab has released 30+ vision libraries, has implemented 300+ algorithms, and contains 2000+ pre-trained models.
Check ourtutorials videos (in Chinese) to get started.
PinnedLoading
- mmsegmentation
mmsegmentation PublicOpenMMLab Semantic Segmentation Toolbox and Benchmark.
Repositories
- PowerPaint Public
[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model. 一个高质量多功能的图像修补模型，可以同时支持插入物体、移除物体、图像扩展、形状可控的物体生成，只需要一个模型
open-mmlab/PowerPaint’s past year of commit activity - Amphion Public
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
open-mmlab/Amphion’s past year of commit activity