Metadata-Version: 2.1
Name: da
Version: 0.0.1
Summary: Pytorch domain adaptation package
Home-page: https://github.com/CPJKU/da
Author: Schmid, F. and Masoudian, S.
Author-email: florian.schmid@jku.at, shahed.masoudian@jku.at
License: GNU License
Keywords: deep learning,pytorch,AI,domain adaptation
Platform: UNKNOWN
Classifier: Environment :: Console
Classifier: Natural Language :: English
Classifier: Development Status :: 3 - Alpha
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: numpy (==1.21.5)
Requires-Dist: POT (==0.8.0)
Requires-Dist: scipy (==1.7.3)
Requires-Dist: torch (==1.10.1)

# DomainAdaptation

This package is created to tackle the problem of domain shifts when dealing with two domains of different feature distributions. In domain adaptation the training data usually consists of labeled source and unlabeled target domain data. The final goal is to achieve a low generalization error when testing in the target domain.

The package supports pytorch only.

More details about the package can be found [here](https://CPJKU.github.io/da/).

