yinboc/prototypical-network-pytorch

A re-implementation of "Prototypical Networks for Few-shot Learning"

47
/ 100
Emerging

This project helps machine learning researchers and practitioners explore 'few-shot learning' scenarios. It takes image datasets with limited examples per category and trains a model to classify new, unseen images with high accuracy, even when only one or a few examples of that category were available during training. This is useful for those developing or evaluating classification systems under data scarcity.

328 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or developer focusing on image classification and need to experiment with 'Prototypical Networks' for tasks where you have very few training examples for each new class.

Not ideal if you are a data scientist or business user looking for an off-the-shelf image classification solution without deep learning development.

few-shot-learning image-classification deep-learning-research model-prototyping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

328

Forks

62

Language

Python

License

MIT

Last pushed

Mar 26, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yinboc/prototypical-network-pytorch"

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