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 e751b5984d 58% office task commit. 7 years ago
core 58% office task commit. 7 years ago
datasets remove params.py, add split task file, etc. 7 years ago
models 58% office task commit. 7 years ago
.gitignore minor update, remove some params 7 years ago
LICENSE Initial commit 7 years ago
README.md update readme. 7 years ago
mnist_mnistm.py remove params.py, add split task file, etc. 7 years ago
office.py 58% office task commit. 7 years ago
svhn_mnist.py remove params.py, add split task file, etc. 7 years ago
utils.py remove params.py, add split task file, etc. 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 2.7/3.6
  • PyTorch 0.3.1post2

Note

  • Config() 为针对特定任务的配置参数。
  • MNISTmodel() 完全按照论文中的结构,但是 feature 部分添加了 Dropout2d(),实验发现是否添 加 Dropout2d() 对于最后的性能影响很大。最后实验重现结果高于论文,因为使用了额外的技巧,这里 还有值得探究的地方。
  • SVHNmodel() 无法理解论文中提出的结构,为自定义结构。最后实验重现结果完美。

Result

MNIST-MNISTM SVHN-MNIST
Source Only 0.5225 0.5490
DANN 0.7666 0.7385
This Repo 0.8400 0.7339
  • MNIST-MNISTM: python mnist_mnistm.py
  • SVHN-MNIST: python svhn_mnist.py

Other implementations

Credit