Pixel Level Domain Transfer
A torch implementation of “Pixel-Level Domain Transfer”. based on dcgan.torch.
The dataset used is “LookBook”, from Donggeun Yoo.
To train the model, put the LOOKBOOK dataset under repository, resize images to 64*64. Prepare the dataset using
You can tune the parameters, such as number of filters, optimizer, etc.
Example results on LOOKBOOK dataset(top), left is input, right is generated clothes. Results on a similar dataset (bottom). More results will be added soon.
Monitor the performance
- Install display package with:
luarocks install https://raw.githubusercontent.com/szym/display/master/display-scm-0.rockspec
- Start the server with:
- Open this URL in your browser:
Below shows the results after 7 epochs, each 3*1 block is generated cloth, true cloth, input image. Errors of G, D, and A network will be plotted.