/RDA

Robust Domain Adaptation under Noisy Environments

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

Robust Domain Adaptation

Code release for "Towards Accurate and Robust Domain Adaptation under Multiple Noisy Environments" submitted into TKDE.

Prerequisites:

  • Python == 3.7
  • PyTorch ==1.8.1 (with suitable CUDA and CuDNN version)
  • torchvision == 0.9.01
  • Numpy
  • argparse
  • easydict
  • pillow = 2.3.5
  • tqdm

Dataset:

You need to modify the path of the image in every ".txt" in "./data". The COVID-19 dataset can be downloaded at the BaiduCloud and the code is c8kk.

Training:

You can run "./scripts/train.sh" to train and evaluate on the task. Before that, you need to change the project root, dataset (Office-home or Office-31), data address and CUDA_VISIBLE_DEVICES in the script.

Contact

If you have any problem about our code, feel free to contact hanzhongyicn@gmail.com