All Projects → RahulBhalley → gan-qp.pytorch

RahulBhalley / gan-qp.pytorch

Licence: other
Unofficial PyTorch implementation of "GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to gan-qp.pytorch

Wasserstein2GenerativeNetworks
PyTorch implementation of "Wasserstein-2 Generative Networks" (ICLR 2021)
Stars: ✭ 38 (+46.15%)
Mutual labels:  generative-adversarial-network, optimal-transport
progressive-growing-of-gans.pytorch
Unofficial PyTorch implementation of "Progressive Growing of GANs for Improved Quality, Stability, and Variation".
Stars: ✭ 51 (+96.15%)
Mutual labels:  generative-adversarial-network, optimal-transport
srgan
Pytorch implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"
Stars: ✭ 39 (+50%)
Mutual labels:  generative-adversarial-network
AvatarGAN
Generate Cartoon Images using Generative Adversarial Network
Stars: ✭ 24 (-7.69%)
Mutual labels:  generative-adversarial-network
lagvae
Lagrangian VAE
Stars: ✭ 27 (+3.85%)
Mutual labels:  generative-adversarial-network
GAN-Project-2018
GAN in Tensorflow to be run via Linux command line
Stars: ✭ 21 (-19.23%)
Mutual labels:  generative-adversarial-network
hgail
gail, infogail, hierarchical gail implementations
Stars: ✭ 25 (-3.85%)
Mutual labels:  generative-adversarial-network
catgan pytorch
Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
Stars: ✭ 50 (+92.31%)
Mutual labels:  generative-adversarial-network
domain adapt
Domain adaptation networks for digit recognitioning
Stars: ✭ 14 (-46.15%)
Mutual labels:  generative-adversarial-network
seqgan-music
Implementation of a paper "Polyphonic Music Generation with Sequence Generative Adversarial Networks" in TensorFlow
Stars: ✭ 21 (-19.23%)
Mutual labels:  generative-adversarial-network
CsiGAN
An implementation for our paper: CsiGAN: Robust Channel State Information-based Activity Recognition with GANs (IEEE Internet of Things Journal, 2019), which is the semi-supervised Generative Adversarial Network (GAN) for Channel State Information (CSI) -based activity recognition.
Stars: ✭ 23 (-11.54%)
Mutual labels:  generative-adversarial-network
GAN-auto-write
Generative Adversarial Network that learns to generate handwritten digits. (Learning Purposes)
Stars: ✭ 18 (-30.77%)
Mutual labels:  generative-adversarial-network
StyleGANCpp
Unofficial implementation of StyleGAN's generator
Stars: ✭ 25 (-3.85%)
Mutual labels:  generative-adversarial-network
Image-Colorization-CycleGAN
Colorization of grayscale images using CycleGAN in TensorFlow.
Stars: ✭ 16 (-38.46%)
Mutual labels:  generative-adversarial-network
AdverseBiNet
Improving Document Binarization via Adversarial Noise-Texture Augmentation
Stars: ✭ 34 (+30.77%)
Mutual labels:  generative-adversarial-network
gan-weightnorm-resnet
Generative Adversarial Network with Weight Normalization + ResNet
Stars: ✭ 19 (-26.92%)
Mutual labels:  generative-adversarial-network
Adventures-with-GANS
Showcasing various fun adventures with GANs
Stars: ✭ 13 (-50%)
Mutual labels:  generative-adversarial-network
AdvSegLoss
Official Pytorch implementation of Adversarial Segmentation Loss for Sketch Colorization [ICIP 2021]
Stars: ✭ 24 (-7.69%)
Mutual labels:  generative-adversarial-network
steam-stylegan2
Train a StyleGAN2 model on Colaboratory to generate Steam banners.
Stars: ✭ 30 (+15.38%)
Mutual labels:  generative-adversarial-network
skip-thought-gan
Generating Text through Adversarial Training(GAN) using Skip-Thought Vectors
Stars: ✭ 44 (+69.23%)
Mutual labels:  generative-adversarial-network

Generative Adversarial Network with Quadratic Potential

This is a minimal PyTorch code for GAN-QP without gradient vanishing which has no Lipschitz constraint like W-GANs on critic network. Also it is not trained to minimize Wasserstein divergence!

It's a totally different GAN with stable training even with high resolution data without requiring careful hyper-parameters and network architecture configurations!

Once again thanks Jianlin Su, creator of GAN-QP, for suggesting this code as PyTorch implementation of GAN-QP!

Experiments

I performed my own experiments on couple of datasets:

  • CelebFaces
  • LSUN Bedrooms

I trained the images on 128, 256, and 512 sized GAN-QP.

Note: Training is not yet complete! And maybe that's why results are not that good. I'll try to update these images when I'm done.

128 x 128 Resolution

CelebFaces

LSUN Bedrooms

256 x 256 Resolution

CelebFaces

512 x 512 Resolution

CelebFaces

References

  • GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint [arXiv]
  • Original GAN-QP 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].