YinlinHu/DANN

pytorch implementation of Domain-Adversarial Training of Neural Networks

This is a pytorch implementation of the paper Unsupervised Domain Adaptation by Backpropagation

Environment

• Pytorch 1.0
• Python 2.7

Network Structure

Dataset

First, you need download the target dataset mnist_m from pan.baidu.com fetch code: kjan or Google Drive

cd dataset
tar -zvxf mnist_m.tar.gz

Training

Then, run:

cd ../train
python3 main.py

python 3 and docker version please go to DANN_py3