open-mmlab /mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
★ 9,991⑂ 2,862👁 48⑃ 1,345● 2,450▤ 45
-1
Daily
9,991
stars
2,862
forks
48
watchers
1,345
prs
2,450
issues
45
releases
README
OpenMMLab website
HOT
OpenMMLab platform
TRY IT OUT
Documentation:
English | 简体中文
Introduction
MMSegmentation is an open source semantic segmentation toolbox based on PyTorch.
It is a part of the OpenMMLab project.
The main branch works with PyTorch 1.6+.
🎉 Introducing MMSegmentation v1.0.0 🎉
We are thrilled to announce the official release of MMSegmentation's latest version! For this new release, the main branch serves as the primary branch, while the development branch is dev-1.x. The stable branch for the previous release remains as the 0.x branch. Please note that the master branch will only be maintained for a limited time before being removed. We encourage you to be mindful of branch selection and updates during use. Thank you for your unwavering support and enthusiasm, and let's work together to make MMSegmentation even more robust and powerful! 💪
MMSegmentation v1.x brings remarkable improvements over the 0.x release, offering a more flexible and feature-packed experience. To utilize the new features in v1.x, we kindly invite you to consult our detailed 📚 migration guide, which will help you seamlessly transition your projects. Your support is invaluable, and we eagerly await your feedback!
!demo image
Major features
- Unified Benchmark
We provide a unified benchmark toolbox for various semantic segmentation methods.
- Modular Design
We decompose the semantic segmentation framework into different components and one can easily construct a customized semantic segmentation framework by combining different modules.
- Support of multiple methods out of box
The toolbox directly supports popular and contemporary semantic segmentation frameworks, e.g. PSPNet, DeepLabV3, PSANet, DeepLabV3+, etc.
- High efficiency
The training speed is faster than or comparable to other codebases.
What's New
v1.2.0 was released on 10/12/2023, from 1.1.0 to 1.2.0, we have added or updated the following features:
Highlights
- Support for the open-vocabulary semantic segmentation algorithm SAN
- Support monocular depth estimation task, please refer to VPD and Adabins for more details.
!depth estimation
- Add new projects: open-vocabulary semantic segmentation algorithm CAT-Seg, real-time semantic segmentation algofithm PP-MobileSeg
Installation
Please refer to get_started.md for installation and dataset_prepare.md for dataset preparation.
Get Started
Please see Overview for the general introduction of MMSegmentation.
Please see user guides for the basic usage of MMSegmentation.
There are also advanced tutorials for in-depth understanding of mmseg design and implementation .
A Colab tutorial is also provided. You may preview the notebook here or directly run on Colab.
To migrate from MMSegmentation 0.x, please refer to migTop issues
#13Roadmap of MMSegmentation45 comments · 2020-07-13#196Semantic Flow for Fast and Accurate Scene Parsing22 comments · 2020-10-16#3163installation error19 comments · 2023-07-04#3167Too much GPU memory consumption and seems wrong18 comments · 2023-07-06#688dataloader is so slow?16 comments · 2021-07-09#1179How to make Multi-Input-Single-Output segmentation?15 comments · 2022-01-04#1625 ValueError: Input and output must have the same number of spatial dimensions,14 comments · 2022-05-28#2594Inconsistent evaluation results13 comments · 2023-02-14
Discussions
#3825Prebuilt mmcv wheels provided via 3rd party repository0 comments · 2024-12-05#3813How to understand "reduce_zero_label" in MMSeg0 comments · 2024-11-13#3806What is the difference between configs from two different locations?0 comments · 2024-11-05#3771Problems occurred in the encode_decode function after the update.0 comments · 2024-09-12#3708Will MP-Former support be provided?0 comments · 2024-06-14#3688How to track the validation loss0 comments · 2024-05-30#3644"When will get_flops.py support calculating the parameter count for mask2former.py?"0 comments · 2024-04-21#3633I NEED SUPPORT, AND CAN EVEN DONATE FOR IT, PLEASE SOME ONE ANSWER ME0 comments · 2024-04-12
Latest release
MMSegmentation v1.2.2 release v1.2.2 2023-12-14v1.2.2 (12/14/2023) Bug Fixes - Fix bug in cross entropy loss (3457) - Allow custom visualizer (3455) - test resize with pad_shape (3421) - add with-labels args to inferencer for visualization without labels (3466) New Contributors - @okotaku made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/3421