open-mmlab/mmpretrain

Health v2 · maintenance only

Adoption not part of the score

3850 stars · 1109 forks observed · 2026-08-28

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

MMPretrain is OpenMMLab's PyTorch-based toolbox and benchmark for image classification model pre-training, covering supervised, self-supervised, and multimodal approaches. It provides a large model zoo including ResNet, Vision Transformers, CLIP, MAE, and MoCo with modular training and evaluation configs.

Use cases

• train an image classification model on my own dataset
• benchmark pretrained vision transformers like Swin or ViT
• run self-supervised pretraining such as MAE or MoCo
• fine-tune a pretrained ResNet or ConvNeXt classifier
• extract image features with a pretrained backbone
• compare image classification models on ImageNet

When to choose

• you need a configurable PyTorch framework for image classification or pretraining research
• you want access to a broad zoo of pretrained vision backbones with consistent APIs
• you are benchmarking supervised or self-supervised vision models

When to avoid

• you only need simple inference without the OpenMMLab config ecosystem
• your task is detection or segmentation rather than classification or pretraining
• you prefer lightweight single-file training scripts

Facets

library · maturity active

machine-learning deep-learning image-processing computer-vision benchmarking deep-learning computer-vision machine-learning image-processing python image-classification pretrained-models self-supervised-learning vision-transformer pytorch model-zoo openmmlab linux gpu

Member repositories

For agents

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