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.
Fazil Altinel
eb1daa18bf
ResNet changes for Office dataset
|
4 years ago |
| .. |
|
__init__.py
|
initial commit
|
7 years ago |
|
gtsrb.py
|
using random seed.
|
5 years ago |
|
gtsrb_prepare.py
|
update GTSRB dataloader, using ROI information.
|
5 years ago |
|
mnist.py
|
Changes for SVHN-MNIST training
|
4 years ago |
|
mnistm.py
|
remove params.py, add split task file, etc.
|
7 years ago |
|
office.py
|
ResNet changes for Office dataset
|
4 years ago |
|
officecaltech.py
|
remove params.py, add split task file, etc.
|
7 years ago |
|
svhn.py
|
update svhnmodel structure, basically the same as paper, except for the last conv layers, kernel change from 5x5 to 4x4, get better result 75%.
|
5 years ago |
|
syndigits.py
|
add syndigits-svhn experiment.
|
5 years ago |
|
synsigns.py
|
add bn layer, source only get 60%, while DA get unstable results, maximum 61%, very similar to source only.
|
5 years ago |
