KaiyangZhou/Dassl.pytorch

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.

48
/ 100
Emerging

This toolkit helps machine learning researchers develop and experiment with models that can adapt to new, unseen data environments or learn effectively with very little labeled data. It takes in datasets (potentially from multiple sources or with few labels) and provides various algorithms for building robust deep learning models. It's designed for researchers working on advanced machine learning techniques, specifically in domain adaptation, generalization, and semi-supervised learning.

1,419 stars. No commits in the last 6 months.

Use this if you are an ML researcher prototyping new deep learning methods that need to perform well on data different from what they were trained on, or when labeled data is scarce.

Not ideal if you need distributed multi-GPU training for very large-scale experiments or require extensive, detailed documentation.

machine-learning-research domain-adaptation semi-supervised-learning deep-learning-experimentation model-generalization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,419

Forks

195

Language

Python

License

MIT

Last pushed

Nov 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KaiyangZhou/Dassl.pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.