mccorby/PhotoLabeller

Federated Learning: Client application doing classification of images and local training. Works better with the Parameter Server at https://github.com/mccorby/PhotoLabellerServer

44
/ 100
Emerging

This system helps organizations train image classification models using data from many different devices (like phones or IoT gadgets) without ever collecting the raw data in a central location. It takes raw image data stored on individual devices and outputs a privacy-preserving, collaboratively trained image classification model. Data privacy officers, researchers, or product managers building applications that need to classify images from user devices will find this useful.

150 stars. No commits in the last 6 months.

Use this if you need to train a robust image classification model from diverse, real-world data sources (like user photos) while strictly adhering to data privacy regulations and ensuring user data never leaves their device.

Not ideal if your data can be freely aggregated in a central database or if you don't require federated learning for privacy protection.

data-privacy image-classification machine-learning-training mobile-app-development IoT-data-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

150

Forks

25

Language

Kotlin

License

MIT

Last pushed

Mar 18, 2019

Commits (30d)

0

Get this data via API

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

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