Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
This is a toolbox for machine learning engineers and researchers who develop computer vision systems. It helps you efficiently experiment with different visual representation learning techniques, specifically supervised, semi-supervised, and self-supervised methods that often involve 'mixup' data augmentation. You can input image datasets and configuration files, and it outputs trained models capable of image classification or acting as powerful pre-trained models for tasks like object detection or segmentation.
656 stars. Available on PyPI.
Use this if you are a machine learning engineer or researcher focused on developing state-of-the-art computer vision models, particularly those leveraging mixup or self-supervised learning for visual tasks.
Not ideal if you are looking for a simple, out-of-the-box solution to apply pre-trained models without deep customization or extensive experimentation with model architectures and training strategies.
Stars
656
Forks
61
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 15, 2025
Commits (30d)
0
Dependencies
16
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Westlake-AI/openmixup"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
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