A PyTorch implementation for Adversarial Discriminative Domain Adaptation.
- Python 3.6
- PyTorch 0.2.0
I only test on MNIST -> USPS, you can just run the following command:
python3 main.py| MNIST (Source) | USPS (Target) | |
|---|---|---|
| Source Encoder + Source Classifier | 99.140000% | 83.978495% |
| Target Encoder + Source Classifier | 97.634409% |
Domain Adaptation does work (97% vs 83%).