This is a pytorch implementation of the model Deep Reconstruction-Classification Network for Unsupervised Domain Adapation (DRCN).

Environment

• Pytorch 0.4.0
• Python 2.7

Structure

Usage

• put the mnist and svhn data in the entries in dataset, respectively
• if there is no Grayscale transform in your torchvision, please replace your functional.py and transforms.py with provided files in extra
• run python main.py for training
• the trained model will be saved in model, and recontructed images saved in recovery_image
• In our implementation, no denoising include

Result

Real and Recovered SVHN images