Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/yeonghyeon/wgan-tf
TensorFlow implementation of Wasserstein GAN (WGAN) with MNIST dataset.
https://github.com/yeonghyeon/wgan-tf
gan gans generative-adversarial-network generative-model mnist mnist-dataset tensorflow tensorflow-examples wasserstein wasserstein-gan wgan
Last synced: 17 days ago
JSON representation
TensorFlow implementation of Wasserstein GAN (WGAN) with MNIST dataset.
- Host: GitHub
- URL: https://github.com/yeonghyeon/wgan-tf
- Owner: YeongHyeon
- License: mit
- Created: 2020-11-02T11:18:04.000Z (about 4 years ago)
- Default Branch: master
- Last Pushed: 2020-11-09T09:22:15.000Z (about 4 years ago)
- Last Synced: 2024-10-17T13:13:49.804Z (about 1 month ago)
- Topics: gan, gans, generative-adversarial-network, generative-model, mnist, mnist-dataset, tensorflow, tensorflow-examples, wasserstein, wasserstein-gan, wgan
- Language: Python
- Homepage:
- Size: 4.35 MB
- Stars: 4
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[TensorFlow] Wasserstein GAN (WGAN)
=====
TensorFlow implementation of Wasserstein GAN (WGAN) with MNIST dataset.
### Training algorithm
The algorithm for training WGAN [1].
### WGAN architecture
The architecture of WGAN [1].
### Graph in TensorBoard
Graph of WGAN.
## Results
### Training Procedure
Loss graph in the training procedure. Each graph shows loss of the discriminator and loss of the generator respectively.
### Test Procedure
|z:2|z:2 (latent space walking)|
|:---:|:---:|
|
|
|
|z:64|z:128|
|:---:|:---:|
|
|
|
## Environment
* Python 3.7.4
* Tensorflow 1.14.0
* Numpy 1.17.1
* Matplotlib 3.1.1
* Scikit Learn (sklearn) 0.21.3
## Reference
[1] Martin Arjovsky et al. (2017). Wasserstein GAN. arXiv preprint arXiv:1701.07875.