A PyTorch implementation for paper Unsupervised Domain Adaptation by Backpropagation
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
wogong 637a26cc64 add office datasets and experiment. 7 years ago
core add office datasets and experiment. 7 years ago
datasets add office datasets and experiment. 7 years ago
models add office datasets and experiment. 7 years ago
.gitignore initial commit 7 years ago
LICENSE Initial commit 7 years ago
README.md initial commit 7 years ago
main.py minor update. 7 years ago
main_office.py add office datasets and experiment. 7 years ago
params.py add office datasets and experiment. 7 years ago
utils.py minor update. 7 years ago

README.md

PyTorch-DANN

A pytorch implementation for paper Unsupervised Domain Adaptation by Backpropagation

InProceedings (icml2015-ganin15)
Ganin, Y. & Lempitsky, V.
Unsupervised Domain Adaptation by Backpropagation
Proceedings of the 32nd International Conference on Machine Learning, 2015

Environment

  • Python 2.7
  • PyTorch 0.3.1

Result

results of the default params.py

MNIST (Source) USPS (Target)
Source Classifier 99.140000% 83.978495%
DANN 97.634409%

Credit