audrina-ebrahimi/AK_SSL
A python library for self-supervised learning
This library helps machine learning researchers and practitioners pre-train models using unlabeled image data. By applying various self-supervised techniques, it takes raw, unannotated image datasets and outputs robust, pre-trained models that can then be fine-tuned more efficiently for specific tasks, even with limited labeled data. It is designed for those developing or implementing advanced computer vision systems.
Available on PyPI.
Use this if you need to train high-performing computer vision models but have access to large amounts of unlabeled image data and only small amounts of labeled data.
Not ideal if you already have fully labeled datasets for your specific computer vision task or if you are not working with image-based data.
Stars
12
Forks
2
Language
Python
License
MIT
Category
Last pushed
Nov 17, 2025
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/audrina-ebrahimi/AK_SSL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification