Reimplementation of cycle-gan with improved w-gan loss in tensorflow.
- Tensorflow v1.0
-
Each model trained 20000 steps(20000*8/1000 ~= about 160 epochs).
./download_dataset.sh [specify a dataset you want]
Before running the code, change the paths and hyper-parameters as desired in the code.
python main.py
Before running the code, change the paths as desired in the code.
python inference.py
- The code for download dataset was copied from here.
- Network architecture might slightly different from the original paper's one.
- For instance, different D network (actually, C network in the Wasserstein gan) is used.
- Tensorflow does not support reflection padding for conv(and decov) layer, so some artifacts can be seen.