mindspore-lab/mindcv

A toolbox of vision models and algorithms based on MindSpore

62
/ 100
Established

This is a comprehensive toolkit for anyone working with image and video analysis who needs to implement or research computer vision models. It provides a wide array of pre-built and state-of-the-art models like ResNet and SwinTransformer, along with their pre-trained weights and training strategies. Users can input image datasets and receive model predictions, classifications, or trained models ready for deployment or further customization.

266 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a computer vision engineer, researcher, or data scientist needing to quickly build, train, or evaluate advanced vision models, especially for tasks like image classification, object detection, or general image understanding.

Not ideal if you are looking for a no-code solution or primarily work outside of deep learning frameworks, as it requires a foundational understanding of machine learning and programming concepts.

image-classification computer-vision-research deep-learning-models object-recognition machine-vision-development
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

266

Forks

147

Language

Python

License

Apache-2.0

Last pushed

Jul 24, 2025

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mindspore-lab/mindcv"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.