All Projects → mikigom → Wgan Lp Tensorflow

mikigom / Wgan Lp Tensorflow

Licence: mit
Reproduction code for WGAN-LP

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Wgan Lp Tensorflow

All About The Gan
All About the GANs(Generative Adversarial Networks) - Summarized lists for GAN
Stars: ✭ 630 (+4746.15%)
Mutual labels:  paper, generative-adversarial-network, arxiv
cv-arxiv-daily
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)
Stars: ✭ 216 (+1561.54%)
Mutual labels:  paper, arxiv
Awesome Grounding
awesome grounding: A curated list of research papers in visual grounding
Stars: ✭ 247 (+1800%)
Mutual labels:  paper, arxiv
Papernote
paper note, including personal comments, introduction, code etc
Stars: ✭ 268 (+1961.54%)
Mutual labels:  paper, arxiv
Dragan
A stable algorithm for GAN training
Stars: ✭ 189 (+1353.85%)
Mutual labels:  paper, generative-adversarial-network
Triplet Attention
Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]
Stars: ✭ 222 (+1607.69%)
Mutual labels:  paper, arxiv
TAGCN
Tensorflow Implementation of the paper "Topology Adaptive Graph Convolutional Networks" (Du et al., 2017)
Stars: ✭ 17 (+30.77%)
Mutual labels:  paper, arxiv
Research Paper Notes
Notes and Summaries on ML-related Research Papers (with optional implementations)
Stars: ✭ 218 (+1576.92%)
Mutual labels:  paper, arxiv
Cyclegan
Tensorflow implementation of CycleGAN
Stars: ✭ 348 (+2576.92%)
Mutual labels:  paper, generative-adversarial-network
Rgan
Recurrent (conditional) generative adversarial networks for generating real-valued time series data.
Stars: ✭ 480 (+3592.31%)
Mutual labels:  paper, arxiv
Arxiv Style
A Latex style and template for paper preprints (based on NIPS style)
Stars: ✭ 497 (+3723.08%)
Mutual labels:  paper, arxiv
Sparsely Grouped Gan
Code for paper "Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation"
Stars: ✭ 68 (+423.08%)
Mutual labels:  paper, generative-adversarial-network
paper-survey
Summary of machine learning papers
Stars: ✭ 26 (+100%)
Mutual labels:  paper, arxiv
Alae
[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+24346.15%)
Mutual labels:  paper, generative-adversarial-network
Awesome Gans
Awesome Generative Adversarial Networks with tensorflow
Stars: ✭ 585 (+4400%)
Mutual labels:  generative-adversarial-network, arxiv
Cv Arxiv Daily
分享计算机视觉每天的arXiv文章
Stars: ✭ 714 (+5392.31%)
Mutual labels:  paper, arxiv
Rticles
LaTeX Journal Article Templates for R Markdown
Stars: ✭ 895 (+6784.62%)
Mutual labels:  paper
Multi Viewpoint Image Generation
Given an image and a target viewpoint, generate synthetic image in the target viewpoint
Stars: ✭ 23 (+76.92%)
Mutual labels:  generative-adversarial-network
Splatter Paper
Data and analysis for the Splatter paper
Stars: ✭ 17 (+30.77%)
Mutual labels:  paper
Contrastive Unpaired Translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
Stars: ✭ 822 (+6223.08%)
Mutual labels:  generative-adversarial-network

WGAN-LP-tensorflow

Report on arXiv

Reproduction code for the following paper:

Title:	
On the regularization of Wasserstein GANs
Authors:	
Petzka, Henning; Fischer, Asja; Lukovnicov, Denis
Publication:	
eprint arXiv:1709.08894
Publication Date:	
09/2017
Origin:	
ARXIV
Keywords:	
Statistics - Machine Learning, Computer Science - Learning
2017arXiv170908894P

Original Paper on arXiv

Repository structure

data_generator.py

  • provides a class that generates the sample data needed for learning.

reg_losses.py

  • defines the sampling method and loss term for regularization.

model.py

  • implements 3-layer neural networks for a generator and a critic.

trainer.py

  • a pipeline for model learning and visualization.
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].