Implementation of "Adversarial Discriminative Domain Adaptation" in PyTorch
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 506c25df6d Changes for new file organization 4 years ago
core Changes for new file organization 4 years ago
input add .gitignore 6 years ago
models Changes for new file organization 4 years ago
outputs add .gitignore 6 years ago
utils Changes for new file organization 4 years ago
.gitignore General changes for development environment 4 years ago
README.md Changes for new file organization 4 years ago
__init__.py Changes for new file organization 4 years ago
main.py Changes for new file organization 4 years ago

README.md

ADDA.PyTorch

implement Adversarial Discriminative Domain Adapation in PyTorch

This repo is mostly based on https://github.com/Fujiki-Nakamura/ADDA.PyTorch

Note

Before running the training code, make sure that DATASETDIR environment variable is set to dataset directory.

Example

$ python train_source.py --logdir outputs
$ python main.py --logdir outputs --trained outputs/best_model.pt --slope 0.2

Result

SVHN -> MNIST

Paper This Repro
Source only 0.601 0.659
ADDA 0.760 ~0.83

adversarial target_domain

Resource