open-mmlab/mmsegmentation

Health v2 · maintenance only

Adoption not part of the score

9930 stars · 2853 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

MMSegmentation is a PyTorch-based toolbox and benchmark for semantic segmentation, part of the OpenMMLab ecosystem. It provides implementations of many segmentation models (e.g., PSPNet, DeepLabV3, SegFormer, Swin Transformer), training/evaluation pipelines, and a large model zoo.

Use cases

• train a semantic segmentation model on a custom dataset
• run image segmentation inference with pretrained models
• benchmark segmentation architectures like DeepLabV3 and PSPNet
• segment retinal vessels or medical images
• fine-tune a transformer-based segmentation model like SegFormer
• evaluate segmentation models on standard datasets like ADE20K or Cityscapes

When to choose

• you need a well-tested PyTorch framework for semantic segmentation with many ready-made models
• you want config-driven training and evaluation with a large model zoo
• you need strong baselines for image or medical image segmentation research

When to avoid

• you need a lightweight inference-only solution without the OpenMMLab dependency stack
• you work outside PyTorch or need real-time deployment on edge devices without conversion tooling
• you want a simple one-off segmentation script rather than a full training framework

Facets

library · maturity stable

machine-learning deep-learning image-processing computer-vision computer-vision image-processing deep-learning machine-learning healthcare python windows semantic-segmentation pytorch deeplabv3 pspnet swin-transformer model-zoo benchmark medical-imaging openmmlab linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="open-mmlab/mmsegmentation")