This is a pytorch implementation of the paper Unsupervised Domain Adaptation by Backpropagation
- Pytorch 1.6
- Python 3.8.5
First, download target dataset mnist_m from pan.quark.com or Google Drive, and put mnist_m dataset into dataset/mnist_m, the structure is as follows:
--dataset--mnist_m--mnist_m_train
|--mnist_m_test
|--mnist_m_train_labels.txt
|--mnist_m_test_labels.txt
|--.gitkeep
Then, run python main.py
- build image
docker build -t pytorch_dann .- run docker container
docker run -it --runtime=nvidia \
-u $(id -u):$(id -g) \
-v /YOUR/DANN/PROJECT/dataset:/DANN/dataset \
-v /YOUR/DANN/PROJECT/models:/DANN/models \
pytorch_dann:latest \
python main.py