Repositories

open-mmlab repositories

31 supported repositories

OpenMMLab Pre-training Toolbox and Benchmark

Last commit Nov 1, 2024

 (3,848 stars) (1,109 forks) (3 indexed issues) (3 open good first issues)

OpenMMLab Rotated Object Detection Toolbox and Benchmark

Last commit Sep 28, 2024

 (2,163 stars) (644 forks) (5 indexed issues) (5 open good first issues)

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Last commit Dec 20, 2023

 (6,867 stars) (2,386 forks) (5 indexed issues) (5 open good first issues)

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

Last commit Nov 17, 2020

 (3,128 stars) (1,062 forks) (2 indexed issues) (2 open good first issues)

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.

Last commit Apr 25, 2023

 (3,876 stars) (622 forks) (1 indexed issue) (1 open good first issue)

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

Last commit Aug 15, 2023

 (3,467 stars) (630 forks) (0 indexed issues) (0 open good first issues)

Multimodal-GPT

Last commit Jun 3, 2023

 (1,511 stars) (128 forks) (0 indexed issues) (0 open good first issues)

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Last commit Oct 3, 2023

 (3,889 stars) (1,152 forks) (0 indexed issues) (0 open good first issues)

[CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA,你的个性化图像动画生成器,利用文本提示将图像变为奇妙的动画

Last commit Aug 5, 2024

 (976 stars) (74 forks) (1 indexed issue) (1 open good first issue)

A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.

Last commit Oct 16, 2023

 (1,237 stars) (128 forks) (0 indexed issues) (0 open good first issues)

[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

Last commit Aug 29, 2024

 (1,081 stars) (82 forks) (5 indexed issues) (5 open good first issues)