Semi-supervised-learning and TorchSSL

These are competitors offering overlapping PyTorch-based frameworks for semi-supervised learning with similar scope (unified codebases implementing multiple SSL algorithms), though Microsoft's version is slightly more recent (NeurIPS'22 vs '21) and marginally more starred.

Semi-supervised-learning
54
Established
TorchSSL
48
Emerging
Maintenance 6/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Stars: 1,563
Forks: 213
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 1,366
Forks: 188
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About Semi-supervised-learning

microsoft/Semi-supervised-learning

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

This project helps machine learning developers efficiently train models for image, text, or audio classification tasks when they only have a small amount of labeled data, but access to a lot of unlabeled data. It takes in both labeled and unlabeled datasets and outputs a high-performing classification model. Machine learning engineers and researchers in computer vision, natural language processing, or audio analysis will find this useful.

image-classification text-classification audio-classification machine-learning-engineering data-efficiency

About TorchSSL

TorchSSL/TorchSSL

A PyTorch-based library for semi-supervised learning (NeurIPS'21)

This project provides a collection of established methods for semi-supervised learning. It takes in datasets where only a small portion of the data is labeled and a larger portion is unlabeled, then outputs trained machine learning models that can classify new, unseen data. Researchers and practitioners working on computer vision tasks who need to build classification models with limited labeled data would find this useful.

semi-supervised-learning image-classification machine-learning-research computer-vision data-labeling-efficiency

Scores updated daily from GitHub, PyPI, and npm data. How scores work