Comprehensive Guide to GANs: Theory, Reports, Tutorials, and Code

Comprehensive Guide to GANs: Theory, Reports, Tutorials, and Code

by

Click the “Expert Knowledge” above to follow for more AI knowledge!

[Introduction] Thematic aggregation knowledge is one of the core functions of Expert Knowledge, providing users with systematic knowledge learning services in the field of AI. Thematic aggregation offers users a collection of the essence (Awesome) knowledge materials about the theme from the entire network, enabling AI practitioners to learn conveniently and solve work problems! Based on the Expert Knowledge AI thematic knowledge tree, thematic aggregation is completed with the assistance of professional manual editing and algorithmic tools, and it is dynamically updated! Additionally, we welcome students interested in creating thematic aggregations to join our Expert Knowledge AI Creator Program for mutual benefit! Today, Expert Knowledge presents to everyone the eleventh thematic aggregation–Generative Adversarial Networks (GAN)knowledge resource collection (theory/reports/tutorials/reviews/code, etc.), please check it out! Visit Expert Knowledge at www.zhuanzhi.ai, or follow the WeChat public account and reply “Expert Knowledge” to enter Expert Knowledge and search for the theme “GAN”. Furthermore, we also provide complete access to this document on the web desktop and mobile (www.zhuanzhi.ai), you can directly click to access the collected link at the end of the article, please check!This is the initial version, please correct and supplement it, and feel free to leave a message in the backend! We welcome everyone to share and forward~

Understand Expert Knowledge,Expert Knowledge, a new way of cognition!

  • Generative Adversarial Networks (GAN) Thematic Aggregation

    • 1. Theory Learning

    • 2. Reports

    • 3. Tutorials

    • 4. Reviews

    • 5. Chinese Blog Materials

    • 6. Github Resources and Models

    • 7. Latest Research Papers

1. Theory Learning

  1. Tips for training GANs reference link: [http://papers.nips.cc/paper/6124-improved-techniques-for-training-gans.pdf]

  2. Energy-Based GANs and related research by Yann Le Cun reference link: [http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf]

  3. Mode Regularization GAN reference link: [https://arxiv.org/pdf/1612.02136.pdf]

  4. The latest NIPS 2016 also has the latest summary on training GAN models reference link: [https://github.com/soumith/ganhacks]

  5. The GAN Zoo, a variety of generative adversarial networks, are all here. You read that right, there are nearly a hundred in there. Reference link: [https://github.com/hindupuravinash/the-gan-zoo]

2. Reports

  1. Ian Goodfellow’s GANs report ICCV 2017 reference link: [https://pan.baidu.com/s/1bpIZvfL]

  2. Ian Goodfellow’s GANs report ICCV 2017 Chinese manuscript reference link: [https://mp.weixin.qq.com/s/nPBFrnO3_QJjAzm37G5ceQ]

  3. Ian Goodfellow’s GANs report NIPS 2016 reference link: [http://www.iangoodfellow.com/slides/2016-12-04-NIPS.pdf]

  4. Ian Goodfellow’s GANs report NIPS 2016 Chinese manuscript reference link: [http://www.sohu.com/a/121189842_465975]

  5. Russ Salakhutdinov’s deep generative models reference link: [http://www.cs.toronto.edu/~rsalakhu/talk_Montreal_2016_Salakhutdinov.pdf]

3. Tutorials

  1. NIPS 2016 tutorial: Generative Adversarial Networks reference link: [https://arxiv.org/pdf/1701.00160.pdf]

  2. Tips and tricks for training GANs reference link: [https://github.com/soumith/ganhacks]

  3. OpenAI generative models reference link: [https://blog.openai.com/generative-models/]

  4. Implementing MNIST generative adversarial model with Keras reference link: [https://oshearesearch.com/index.PHP/2016/07/01/mnist-generative-adversarial-model-in-keras/]

  5. Image inpainting using deep learning TensorFlow reference link: [http://bamos.github.io/2016/08/09/deep-completion/]

4. Reviews

1. Chinese Academy of Sciences Institute of Automation Chinese review “Research Progress and Prospects of Generative Adversarial Networks (GAN)” reference link: [https://pan.baidu.com/s/1dEMITo9] Password: qqcc

5. Chinese Blog Materials

1. Introduction to Generative Adversarial Networks for beginners: Understand the basic principles of GAN in one article [http://www.xtecher.com/Xfeature/view?aid=7496] 2. In-depth introduction: An introductory guide to GAN principles and applications [https://zhuanlan.zhihu.com/p/28731033] 3. Hong Kong Polytechnic University PhD student Li Yanran’s in-depth introduction to GAN applications reference link: Link: [https://pan.baidu.com/s/1o8n4UDk] Password: 78wt 4. Cute generator: How to use four types of GANs to create cat images reference link: [https://zhuanlan.zhihu.com/p/27769807] 5. GAN learning guide: From principle introduction to creating generative demo reference link: [https://zhuanlan.zhihu.com/p/24767059x] 6. Research progress on Generative Adversarial Networks (GAN) reference link: [http://blog.csdn.net/solomon1558/article/details/52537114] 7. Summary of the latest progress in Generative Adversarial Networks (GAN) (papers, reports, frameworks, and Github resources) reference link: [http://blog.csdn.net/love666666shen/article/details/74953970]

6. Github Resources and Models

  1. Deep Convolutional Generative Adversarial Model (DCGAN) reference link: [https://github.com/Newmu/dcgan_code]

  2. TensorFlow implementation of Deep Convolutional Generative Adversarial Model (DCGAN) reference link: [https://github.com/carpedm20/DCGAN-tensorflow]

  3. Torch implementation of Deep Convolutional Generative Adversarial Model (DCGAN) reference link: [https://github.com/soumith/dcgan.torch]

  4. Keras implementation of Deep Convolutional Generative Adversarial Model (DCGAN) reference link: [https://github.com/jacobgil/keras-dcgan]

  5. Using neural networks to generate natural images (Facebook’s Eyescream project) reference link: [https://github.com/facebook/eyescream]

  6. Adversarial Autoencoder reference link: [https://github.com/musyoku/adversarial-autoencoder]

  7. Using ThoughtVectors for text-to-image synthesis reference link: [https://github.com/paarthneekhara/text-to-image]

  8. Adversarial Example Generator reference link: [https://github.com/e-lab/torch-toolbox/tree/master/Adversarial]

  9. Semi-supervised learning for deep generative models reference link: [https://github.com/dpkingma/nips14-ssl]

  10. Training methods for GANs reference link: [https://github.com/openai/improved-gan]

  11. Generative Moment Matching Networks (GMMNs) reference link: [https://github.com/yujiali/gmmn]

  12. Adversarial video generation reference link: [https://github.com/dyelax/Adversarial_Video_Generation]

  13. Image-to-image translation based on conditional adversarial networks (pix2pix) reference link: [https://github.com/phillipi/pix2pix]

  14. Cleverhans, a library for adversarial machine learning, reference link: [https://github.com/openai/cleverhans]

7. Latest Research Papers

2014

  1. Explaining and Harnessing Adversarial Examples 2014 original link: [https://arxiv.org/pdf/1412.6572.pdf]

  2. Semi-Supervised Learning with Deep Generative Models 2014 original link: [https://arxiv.org/pdf/1406.5298v2.pdf]

  3. Conditional Generative Adversarial Nets 2014 original link: [https://arxiv.org/pdf/1411.1784v1.pdf]

2015

  1. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (DCGANs) 2015 original link: [https://arxiv.org/pdf/1511.06434v2.pdf]

  2. Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks 2015 original link: [http://papers.nips.cc/paper/5773-deep-generative-image-models-using-a-5. laplacian-pyramid-of-adversarial-networks.pdf]

  3. Generative Moment Matching Networks 2015 original link: [http://proceedings.mlr.press/v37/li15.pdf]

  4. Deep multi-scale video prediction beyond mean square error 2015 original link: [https://arxiv.org/pdf/1511.05440.pdf]

  5. Autoencoding beyond pixels using a learned similarity metric 2015 original link: [https://arxiv.org/pdf/1512.09300.pdf]

  6. Adversarial Autoencoders 2015 original link: [https://arxiv.org/pdf/1511.05644.pdf]

  7. Conditional Image Generation with PixelCNN Decoders 2015 original link: [https://arxiv.org/pdf/1606.05328.pdf]

  8. Training generative neural networks via Maximum Mean Discrepancy optimization 2015 original link: [https://arxiv.org/pdf/1505.03906.pdf]

2016

  1. Improved Techniques for Training GANs 2016 original link: [https://arxiv.org/pdf/1606.03498v1.pdf]

  2. InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets 2016 original link: [https://arxiv.org/pdf/1606.03657v1.pdf] 3. Context Encoders: Feature Learning by Inpainting 2016 original link: [http://www.cvfoundation.org/openaccess/content_cvpr_2016/papers/Pathak_Context_Encoders_Feature_CVPR_2016_paper.pdf]

  3. Generative Adversarial Text to Image Synthesis 2016 original link: [http://proceedings.mlr.press/v48/reed16.pdf]

  4. Adversarial Feature Learning 2016 original link: [https://arxiv.org/pdf/1605.09782.pdf]

  5. Improving Variational Inference with Inverse Autoregressive Flow 2016 original link: [https://papers.nips.cc/paper/6581-improving-variational-autoencoders-with-inverse-autoregressive-flow.pdf]

  6. Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples 2016 original link: [https://arxiv.org/pdf/1602.02697.pdf]

  7. Attend, infer, repeat: Fast scene understanding with generative models 2016 original link: [https://arxiv.org/pdf/1603.08575.pdf]

  8. f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization 2016 original link: [http://papers.nips.cc/paper/6066-tagger-deep-unsupervised-perceptual-grouping.pdf] 10. Generative Visual Manipulation on the Natural Image Manifold 2016 original link: [https://arxiv.org/pdf/1609.03552.pdf]

  9. Adversarially Learned Inference 2016 original link: [https://arxiv.org/pdf/1606.00704.pdf]

  10. Generating images with recurrent adversarial networks 2016 original link: [https://arxiv.org/pdf/1602.05110.pdf]

  11. Generative Adversarial Imitation Learning 2016 original link: [http://papers.nips.cc/paper/6391-generative-adversarial-imitation-learning.pdf]

  12. Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling 2016 original link: [https://arxiv.org/pdf/1610.07584.pdf]

  13. Learning What and Where to Draw 2016 original link: [https://arxiv.org/pdf/1610.02454v1.pdf]

  14. Conditional Image Synthesis with Auxiliary Classifier GANs 2016 original link: [https://arxiv.org/pdf/1610.09585.pdf]

  15. Learning in Implicit Generative Models 2016 original link: [https://arxiv.org/pdf/1610.03483.pdf]

  16. VIME: Variational Information Maximizing Exploration 2016 original link: [http://papers.nips.cc/paper/6591-vime-variational-information-maximizing-exploration.pdf]

  17. Unrolled Generative Adversarial Networks 2016 original link: [https://arxiv.org/pdf/1611.02163.pdf]

  18. Neural Photo Editing with Introspective Adversarial Networks 2016 original link: [https://arxiv.org/pdf/1609.07093.pdf]

  19. On the Quantitative Analysis of Decoder-Based Generative Models 2016 original link: [https://arxiv.org/pdf/1611.04273.pdf]

  20. Connecting Generative Adversarial Networks and Actor-Critic Methods 2016 original link: [https://arxiv.org/pdf/1610.01945.pdf]

  21. Learning from Simulated and Unsupervised Images through Adversarial Training 2016 original link: [https://arxiv.org/pdf/1612.07828.pdf]

  22. Contextual RNN-GANs for Abstract Reasoning Diagram Generation 2016 original link: [https://arxiv.org/pdf/1609.09444.pdf]

  23. Generative Multi-Adversarial Networks 2016 original link: [https://arxiv.org/pdf/1611.01673.pdf]

  24. Ensembles of Generative Adversarial Network 2016 original link: [https://arxiv.org/pdf/1612.00991.pdf]

  25. Improved generator objectives for GANs 2016 original link: [https://arxiv.org/pdf/1612.02780.pdf]

2017

  1. Towards Principled Methods for Training Generative Adversarial Networks 2017 original link: [https://arxiv.org/pdf/1701.04862.pdf]

  2. Precise Recovery of Latent Vectors from Generative Adversarial Networks 2017 original link: [https://openreview.NET/pdf?id=HJC88BzFl]

  3. Generative Mixture of Networks 2017 original link: [https://arxiv.org/pdf/1702.03307.pdf]

  4. Generative Temporal Models with Memory 2017 original link: [https://arxiv.org/pdf/1702.04649.pdf]

  5. Stopping GAN Violence: Generative Unadversarial Networks 2017 original link: [https://arxiv.org/pdf/1703.02528.pdf]

  6. Bayesian GANs: Combining Bayesian and GANs

Original link: https://arxiv.org/abs/1705.09558

Preliminary version, limited level, if there are errors or imperfections, please feel free to suggest and supplement, and it will be continuously updated, please pay attention to http://www.zhuanzhi.ai and follow the Expert Knowledge public account for the latest AI-related knowledge

Special Note – Expert KnowledgeGenerative Adversarial NetworksTheme:

Get the complete version to view the latest updated recommendation systemKnowledge materials, please log in to www.zhuanzhi.ai or click Read the original text, register and log in, search for “GAN” theme to see the collectedExpert Knowledge complete knowledge and other materials! As shown in the figure below~

Comprehensive Guide to GANs: Theory, Reports, Tutorials, and Code

In addition, please follow theExpert Knowledge public account (scan the QR code for Expert Knowledge at the bottom or click the blue Expert Knowledge above),

  • Reply “GAN” in the backend to obtain theExpert Knowledge GAN knowledge materials viewing link on the mobile terminal, directly open the collection materials link~~

Feel free to forward to your WeChat groups and moments to share professional AI knowledge!

For more complete collections of Expert Knowledge materials, please check:

[Expert Knowledge Collection 01] Deep Learning Knowledge Resource Collection (beginner/advanced/papers/code/data/reviews/field experts, etc.) (with PDF download)

[Expert Knowledge Collection 02] Natural Language Processing NLP Knowledge Resource Collection (beginner/advanced/papers/Toolkit/data/reviews/expert, etc.) (with PDF download)

[Expert Knowledge Collection 03] Knowledge Graph KG Knowledge Resource Collection (beginner/advanced/papers/code/data/reviews/expert, etc.) (with PDF download)

[Expert Knowledge Collection 04] Automatic Question Answering QA Knowledge Resource Collection (beginner/advanced/papers/code/data/reviews/expert, etc.) (with PDF download)

[Expert Knowledge Collection 05] Chatbot Knowledge Resource Collection (beginner/advanced/papers/software/data/expert, etc.) (with PDF download)

[Expert Knowledge Collection 06] Computer Vision CV Knowledge Resource Collection (beginner/advanced/papers/courses/conferences/expert, etc.) (with PDF download)

[Expert Knowledge Collection 07] Automatic Summarization AS Knowledge Resource Collection (beginner/advanced/code/data/expert, etc.) (with PDF download)

[Expert Knowledge Collection 08] Image Caption Generation Knowledge Resource Collection (beginner/advanced/papers/reviews/videos/expert, etc.)

[Expert Knowledge Collection 09] Object Detection Knowledge Resource Collection (beginner/advanced/papers/reviews/videos/code, etc.)

[Expert Knowledge Collection 10] Recommendation System RS Knowledge Resource Collection (beginner/advanced/papers/reviews/videos/code, etc.)

[Tutorial Practice] Google DeepMind David Silver “Deep Reinforcement Learning” public course tutorial notes and complete practical code

[GAN Resources] Comprehensive knowledge resources on Generative Adversarial Networks (papers/code/tutorials/videos/articles, etc.)

[Content] Google GAN father Ian Goodfellow ICCV2017 speech: Interpreting the principles and applications of Generative Adversarial Networks

[AlphaGo Zero Core Technology] Comprehensive knowledge resources on Deep Reinforcement Learning (papers/code/tutorials/videos/articles, etc.)

Please scan the assistant to join the Expert Knowledge AI group for communication and sharing~

Comprehensive Guide to GANs: Theory, Reports, Tutorials, and Code

For more knowledge resources on machine learning and artificial intelligence, please visit www.zhuanzhi.ai, or click Read the original text to obtain!

-END-

Welcome to use Expert Knowledge

Expert Knowledge, a new way of cognition! Currently focusing on the field of artificial intelligence to provide professional and reliable knowledge distribution services for AI practitioners, including theme customization, theme linkage, search discovery, and other services, helping you find the knowledge you need quickly and efficiently.

How to use>>Visit www.zhuanzhi.ai, or click the “Read the original text” at the bottom of the article to access Expert Knowledge

Expert Knowledge Team, Institute of Automation, Chinese Academy of Sciences

@2017 Expert Knowledge

Expert Knowledge

Follow our public account for the latest news on Expert Knowledge and artificial intelligence, technology, algorithms, deep content, and more. Scan the QR code below to follow our public account.

Comprehensive Guide to GANs: Theory, Reports, Tutorials, and Code

Leave a Comment