IShengFang / Spectralnormalizationkeras
Licence: other
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100
Labels
Projects that are alternatives of or similar to Spectralnormalizationkeras
Relativistic Average Gan Keras
The implementation of Relativistic average GAN with Keras
Stars: ✭ 36 (-64%)
Mutual labels: jupyter-notebook, gan, deeplearning, generative-adversarial-network, cifar10
Deep Learning Resources
由淺入深的深度學習資源 Collection of deep learning materials for everyone
Stars: ✭ 422 (+322%)
Mutual labels: jupyter-notebook, gan, deeplearning, generative-adversarial-network
Generative adversarial networks 101
Keras implementations of Generative Adversarial Networks. GANs, DCGAN, CGAN, CCGAN, WGAN and LSGAN models with MNIST and CIFAR-10 datasets.
Stars: ✭ 138 (+38%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network, cifar10
Dragan
A stable algorithm for GAN training
Stars: ✭ 189 (+89%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network, generative-model
Seqgan
A simplified PyTorch implementation of "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient." (Yu, Lantao, et al.)
Stars: ✭ 502 (+402%)
Mutual labels: gan, generative-adversarial-network, generative-model
Generative Models
Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN
Stars: ✭ 438 (+338%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Calogan
Generative Adversarial Networks for High Energy Physics extended to a multi-layer calorimeter simulation
Stars: ✭ 87 (-13%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Specgan
SpecGAN - generate audio with adversarial training
Stars: ✭ 92 (-8%)
Mutual labels: gan, deeplearning, generative-adversarial-network
T81 558 deep learning
Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks
Stars: ✭ 4,152 (+4052%)
Mutual labels: jupyter-notebook, gan, deeplearning
Generative Adversarial Networks
Introduction to generative adversarial networks, with code to accompany the O'Reilly tutorial on GANs
Stars: ✭ 505 (+405%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Sprint gan
Privacy-preserving generative deep neural networks support clinical data sharing
Stars: ✭ 92 (-8%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Gans In Action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
Stars: ✭ 748 (+648%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Simgan Captcha
Solve captcha without manually labeling a training set
Stars: ✭ 405 (+305%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Ganspace
Discovering Interpretable GAN Controls [NeurIPS 2020]
Stars: ✭ 1,224 (+1124%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Sdv
Synthetic Data Generation for tabular, relational and time series data.
Stars: ✭ 360 (+260%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: ✭ 513 (+413%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Fewshot Face Translation Gan
Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.
Stars: ✭ 705 (+605%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Discogan Pytorch
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
Stars: ✭ 961 (+861%)
Mutual labels: jupyter-notebook, gan, generative-model
Alae
[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+3078%)
Mutual labels: gan, generative-adversarial-network, generative-model
Faceswap Gan
A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.
Stars: ✭ 3,099 (+2999%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Spectral Normalization for Keras
The simple Keras implementation of ICLR 2018 paper, Spectral Normalization for Generative Adversarial Networks. [openreview][arixiv][original code(chainer)]
Result
CIFAR10
DCGAN architecture
10epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
100epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
200epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
300epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
400epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
500epoch | with SN | without SN |
---|---|---|
With GP | ||
Without GP |
Loss | with SN | without SN |
---|---|---|
With GP | ||
Without GP |
ResNet architecture
10epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
100epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
200epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
300epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
400epoch | With SN | Without SN |
---|---|---|
With GP | ||
Without GP |
500epoch | with SN | without SN |
---|---|---|
With GP | ||
Without GP |
Loss | with SN | without SN |
---|---|---|
With GP | ||
Without GP |
How to use?
- Move SpectralNormalizationKeras.py in your dir
- Import these layer class
from SpectralNormalizationKeras import DenseSN, ConvSN1D, ConvSN2D, ConvSN3D
- Use these layers in your discriminator as usual
Example notebook
CIFAR10 with DCGAN architecture
CIFAR10 with ResNet architecture
Model Detail
Architecture
DCGAN
Generator
Discriminator
ResNet GAN
Generator
Generator UpSampling ResBlock
Dicriminator
Discriminator DownSampling ResBlock
Discriminator ResBlock
Issue
- [x] Compare with WGAN-GP
- [ ] Projection Discriminator
Acknowledgment
- Thank @anshkapil pointed out and @IFeelBloated corrected this implementation.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].