# KaiyangZhou/Dassl.pytorch

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

Repository: https://github.com/KaiyangZhou/Dassl.pytorch
Canonical: https://ross.abutalabs.com/products/dasslpytorch
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, benchmark-datasets, semi-supervised-learning, domain-adaptation, domain-generalization, deep-learning, machine-learning, computer-vision, artificial-intelligence, deep-neural-networks
Last push: 2023-11-03T10:38:13+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2367, "days_push": 1034, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1428, forks 196 (observed 2026-08-28T04:04:42.036866+00:00)

## What it is
Dassl is a PyTorch toolbox for research in domain adaptation, domain generalization, and semi-supervised learning. It provides modular components and unified interfaces with implementations of many existing methods for fast prototyping.

## Use cases
- implement a new domain adaptation method in pytorch
- benchmark domain generalization algorithms
- run semi-supervised learning experiments
- prototype deep learning research code quickly
- reproduce DA/DG/SSL paper baselines
- train models on WILDS benchmark datasets

## When to choose
- you research domain adaptation, generalization, or semi-supervised learning
- you want unified interfaces and ready-made method implementations
- you need a clean codebase for deep learning experiments

## When to avoid
- you need distributed multi-GPU training (only DataParallel is supported)
- you want detailed documentation rather than reading source code
- you need a production training framework rather than a research toolbox

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, computer-vision, artificial-intelligence
- platform: python
- tags: pytorch, domain-adaptation, domain-generalization, semi-supervised-learning, research-toolbox, benchmark-datasets, gpu

## Member repositories
- KaiyangZhou/Dassl.pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:42.036866+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:37:17.833897+00:00, confidence not recorded.
  - readme: https://github.com/KaiyangZhou/Dassl.pytorch (fetched 2026-08-28T04:04:42.036866+00:00, sha 89d01b000c02)
- Data as of 2026-08-30T08:39:29.467469+00:00.