Pytorch implementation of WAE-MMD(paper).

python 3.6.4
pytorch 0.3.1.post2
visdom

1. download img_align_celeba.zip and list_eval_partition.txt files from here, make data directory, put downloaded files into data, and then run ./preprocess_celeba.sh. for example,

.
└── data
  └── img_align_celeba.zip
  └── list_eval_partition.txt

2. initialize visdom

python -m visdom.server

3. run by scripts

sh run_celeba_wae_mmd.sh

4. check training process on the visdom server

localhost:8097

1. Wasserstein Auto-Encoders, Tolstikhin et al, ICLR, 2018
2. Code repos : official, re-implementation, both in Tensorflow