cycle-gan-tf
cycle-gan-tf copied to clipboard
hiwonjoon
Reimplementation of cycle-gan(https://arxiv.org/pdf/1703.10593.pdf) with improved w-gan(https://arxiv.org/abs/1704.00028) loss in tensorflow.
Cycle-GAN-TF
Reimplementation of cycle-gan with improved w-gan loss in tensorflow.
Prerequisites
- Tensorflow v1.0
Training Result
- Training is done with nVidia Titan X Pascal GPU.
- aerial maps <-> maps
- A(aerial map) -> B(map) -> A
- B -> A -> B
- A(aerial map) -> B(map) -> A
Result on test sets
-
Each model trained 20000 steps(20000*8/1000 ~= about 160 epochs).
-
aerial maps <-> maps
-
horse <-> zebra
-
apple <-> orange
Training
Download dataset
./download_dataset.sh [specify a dataset you want]
Run code
Before running the code, change the paths and hyper-parameters as desired in the code.
python main.py
Using pretrained model & inference
Before running the code, change the paths as desired in the code.
python inference.py
Notes & Acknowledgement
- 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.
hiwonjoon