abdulfatir/prototypical-networks-tensorflow

Tensorflow implementation of NIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

39
/ 100
Emerging

This project helps machine learning researchers and practitioners explore "few-shot learning" methods. You can input image datasets, like Omniglot or Mini-ImageNet, and it will output trained models that can classify new images even when they've only seen a few examples of each class. This is ideal for those working on computer vision tasks with limited data.

132 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer interested in experimenting with prototypical networks for image classification where you have very little labeled data per class.

Not ideal if you need a production-ready, highly optimized, and thoroughly tested few-shot learning solution, as this is a research-oriented implementation that may contain bugs.

few-shot learning image classification computer vision research machine learning experimentation deep learning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 21 / 25

How are scores calculated?

Stars

132

Forks

45

Language

Jupyter Notebook

License

Last pushed

Feb 09, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/abdulfatir/prototypical-networks-tensorflow"

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