lorenzobrigato/gem

A Pytorch-based library to evaluate learning methods on small image classification datasets

29
/ 100
Experimental

This project helps machine learning engineers and researchers evaluate how well different image classification methods perform when only a small amount of training data is available. You input a small image dataset and select a learning algorithm, and the project outputs performance metrics showing how effectively that algorithm generalizes to new, unseen images. This is for professionals building or researching image classification systems, especially in specialized domains where large datasets are hard to come by.

No commits in the last 6 months.

Use this if you need to compare and benchmark various image classification algorithms to find the most effective one for your specific task, particularly when you only have small image datasets.

Not ideal if you are looking for a pre-trained, production-ready image classifier or if you have very large datasets and are not focused on small-sample learning challenges.

image-classification machine-learning-research small-data-problems model-evaluation computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

16

Forks

4

Language

Jupyter Notebook

License

Last pushed

Jun 22, 2022

Commits (30d)

0

Get this data via API

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

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