ShichenLiu/CondenseNet

CondenseNet: Light weighted CNN for mobile devices

50
/ 100
Established

This project offers a method to build highly efficient image recognition models that can run on devices with limited computational power, such as mobile phones or embedded systems. It takes raw image data and processes it into classification results, such as identifying objects or faces. This is for engineers or product managers who need to deploy robust image recognition features in resource-constrained environments.

691 stars. No commits in the last 6 months.

Use this if you need to deploy advanced image classification or object recognition capabilities on mobile devices or other hardware with limited processing power and memory.

Not ideal if you are solely focused on achieving the absolute highest accuracy without any concern for model size or inference speed.

mobile-computer-vision edge-ai image-classification embedded-systems resource-constrained-devices
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

691

Forks

130

Language

Python

License

MIT

Last pushed

Nov 11, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ShichenLiu/CondenseNet"

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