Real

TSDA on Real dataset

If you have any questions, feel free to pose an issue or send an email to [email protected]. We are always happy to receive feedback!

The code for TSDA is developed based on CIDA. CIDA also provides many baseline implementations (e.g., DANN, MDD), which we used for performance comparasion in our paper. Please refer to its code for details. For baseline GRDA, please refer to this code.

ImageNet-Attribute-DT

How to Train on ImageNet-Attribute-DT

    python default_run.py -c config_imagenet_11 (or)
    python default_run.py --config config_imagenet_11

CUB-DT

How to Train on CUB-DT

1. Download the dataset from here and unzip under the folder "Real".

2. Run the following code:

    python default_run.py -c config_cub_18 (or)
    python default_run.py --config config_cub_18

Loss Visualization during Training

We use visdom to visualize. We assume the code is run on a remote gpu machine.

Change Configurations

Find the config in "config" folder. Choose the config you need and Set "opt.use_visdom" to "True".

Start a Visdom Server on Your Machine

python -m visdom.server -p 2000

Now connect your computer with the gpu server and forward the port 2000 to your local computer. You can now go to: http://localhost:2000 (Your local address) to see the visualization during training.