autonlab/weasel
Weakly Supervised End-to-End Learning (NeurIPS 2021)
This tool helps data scientists and machine learning engineers classify data efficiently, even without fully labeled training examples. You provide a set of 'labeling functions'—simple rules or crowd-sourced annotations—and the tool uses these to directly train a neural network. The output is a highly accurate classification model ready for your specific tasks.
156 stars. No commits in the last 6 months.
Use this if you need to build powerful classification models but lack the time or resources to hand-label a large training dataset.
Not ideal if you already have extensive, high-quality labeled datasets or if you are not comfortable working with machine learning frameworks.
Stars
156
Forks
12
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/autonlab/weasel"
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