gan3sh500/mixmatch-pytorch

Pytorch Implementation of the paper MixMatch: A Holistic Approach to Semi-Supervised Learning (https://arxiv.org/pdf/1905.02249.pdf)

29
/ 100
Experimental

This project helps machine learning practitioners efficiently train classification models using a combination of labeled and unlabeled data. It takes your existing labeled datasets and a larger pool of unlabeled data, then outputs a robust classification model ready for deployment. Data scientists and ML engineers working with limited labeled data would find this useful.

123 stars. No commits in the last 6 months.

Use this if you need to build high-performing classification models but have a scarcity of labeled examples, while a large amount of unlabeled data is readily available.

Not ideal if your dataset is entirely labeled or if you lack significant amounts of unlabeled data, as its core benefit relies on semi-supervised learning.

machine-learning-engineering data-science image-classification predictive-modeling model-training
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

123

Forks

11

Language

Jupyter Notebook

License

Last pushed

May 30, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gan3sh500/mixmatch-pytorch"

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