YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
This project helps machine learning engineers and researchers classify images more accurately, especially when they have limited labeled data. By applying advanced semi-supervised learning techniques, it takes a small set of labeled images and a larger set of unlabeled images as input. It then outputs a trained image classification model with improved performance, particularly useful for tasks like object recognition.
653 stars. No commits in the last 6 months.
Use this if you are a machine learning practitioner working on image classification and need to build high-performing models with only a small amount of labeled training data.
Not ideal if your task does not involve image data, or if you already have a very large, fully labeled dataset for your classification problem.
Stars
653
Forks
135
Language
Python
License
MIT
Category
Last pushed
Nov 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YU1ut/MixMatch-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)
elijahcole/sinr
Spatial Implicit Neural Representations for Global-Scale Species Mapping - ICML 2023