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.
27 lines
829 B
27 lines
829 B
7 years ago
|
# PyTorch-DANN
|
||
|
|
|
||
|
|
A pytorch implementation for paper *[Unsupervised Domain Adaptation by Backpropagation](http://sites.skoltech.ru/compvision/projects/grl/)*
|
||
|
|
|
||
|
|
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
|
||
|
|
|
||
|
|
- <https://github.com/fungtion/DANN>
|
||
|
|
- <https://github.com/corenel/torchsharp>
|