Code in Pytorch for our article Dual Classifier Adaptation: Source-Free UDA via Adaptive Pseudo-labels Learning
- python 3.8.10
- pytorch 1.11.0
- torchvision 0.12.0
- cuda 10.1
- numpy, sklearn, scipy, tqdm
- Please manually download the datasets Office, Office-Home, VisDA-Cfrom the official websites, and modify the path of images in each '.txt' under the folder './data/'. [**How to generate such txt files could be found in https://github.com/tim-learn/Generate_list **]
Firstly, you need to train the source model by running this code
python train_source_31.py
Then, you can run the code of DCA to perform SFDA,
python train_target_31.py