https://github.com/blob42/face_generation_gan
Generative Adverserial Network for face generation using Tensorflow and DCGAN architecture
https://github.com/blob42/face_generation_gan
celeba dcgan deep-learning gan generative-adversarial-network jupyter-notebook mnist nd101 tensorflow
Last synced: 2 months ago
JSON representation
Generative Adverserial Network for face generation using Tensorflow and DCGAN architecture
- Host: GitHub
- URL: https://github.com/blob42/face_generation_gan
- Owner: blob42
- Created: 2017-09-20T00:17:08.000Z (almost 9 years ago)
- Default Branch: master
- Last Pushed: 2017-09-20T15:22:12.000Z (almost 9 years ago)
- Last Synced: 2025-04-05T10:30:46.270Z (about 1 year ago)
- Topics: celeba, dcgan, deep-learning, gan, generative-adversarial-network, jupyter-notebook, mnist, nd101, tensorflow
- Language: HTML
- Homepage:
- Size: 6.37 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Face Generation GAN based on DCGAN architecture
### Architecture
### Examples
#### Mnist
#### Celeba
### Details
**codes for layers**
- **1 layer** = (size)F|C(ks,str,p)|DC(ks,str)|BN|D|LR
- **(size):** size of layer or filters
- **F:** Fully Connected
- **C:** Convulution
- **DC(ks,str):** Deconvulution with (Kernel Size, Stride, padding)
- **BN:** Batch normalization
- **D:** Dropout
- **LR:** Leaky Relu
### Generator:
#### Full: (7x7x1024)F -> D -> LR
#### DCONV1: (512)DC(3,2,same) -> BN -> D -> LR
#### DCONV2: (256)DC(3,2,same) -> BN -> D -> LR
#### DCONV3: (128)DC(5,1,same) -> BN -> D -> LR
#### DCONV_OUT: (channles)DC(5,1)
### Discriminator:
#### CONV1: (64)C(5,1,valid) -> LR
#### CONV2: (128)C(5,1,valid) -> BN -> D -> LR
#### CONV3: (256)C(5,1,valid) -> BN -> D -> LR
#### CONV4: (512)C(5,2,valid) -> BN -> D -> LR
#### OUT: (flat)F
### Hyperparameters for celeba set
- Leaky Relu Slope: 0.2
- Adam Optimizaer beta: 0.5
- Learning rate: 0.0003
- Batch Size: 16
- latent vector dimension: 100
- dropout: 0.5
- 1 epoch