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
6a9e484102
update svhnmodel structure, basically the same as paper, except for the last conv layers, kernel change from 5x5 to 4x4, get better result 75%.
|
6 years ago |
| .. |
|
mnist_mnistm.py
|
rename dann.py to train.py
|
6 years ago |
|
office.py
|
rename dann.py to train.py
|
6 years ago |
|
office31_10.py
|
rename dann.py to train.py
|
6 years ago |
|
svhn_mnist.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%.
|
6 years ago |
|
synsigns_gtsrb.py
|
add bn layer, source only get 60%, while DA get unstable results, maximum 61%, very similar to source only.
|
6 years ago |
|
synsigns_gtsrb_src_only.py
|
add bn layer, source only get 60%, while DA get unstable results, maximum 61%, very similar to source only.
|
6 years ago |
