-------生成动漫角色-------
illustration2vec 自动分类标注 tsne数据可视化工具
CGAN 条件gan
http://make.girls.moe/#/ make.girls.moe https://makegirlsmoe.github.io/assets/pdf/technical_report.pdf https://github.com/makegirlsmoe/makegirlsmoe.github.io 我们选择从 Getchu 处收集数据集
ACGAN，其尝试将鉴别器训练为辅助分类器，借以预测条件性输入内容。
SRResNet
https://github.com/openai/imitation 用gan 模仿行为
------------好奇心驱动------------- https://www.quantamagazine.org/clever-machines-learn-how-to-be-curious-20170919/ https://github.com/pathak22/noreward-rl
https://www.leiphone.com/news/201702/GZsIbIb9V9AUGmb6.html GAN的理解和tensorflow 的实现 -----------------ac-gan和info-gan 代码------------------ https://github.com/koryako/tensorflow-101
https://github.com/buriburisuri/ac-gan
https://arxiv.org/abs/1412.6980 adam
-------------lsgan-------------------- https://www.leiphone.com/news/201702/QlPJUIqgyw6brWr2.html LS-GAN 稳定性
https://github.com/guojunq/lsgan
https://www.leiphone.com/news/201612/Cdcb1X9tm1zsGSWD.html
生成对抗自动编码器 AAE
基于文本输入生成高质量图片和视频
https://github.com/roatienza/Deep-Learning-Experiments 内有keras 版本 gan
https://github.com/reedscot/icml2016 text2img infogan => beta-vea https://github.com/crcrpar/chainer-VAE beta-vae
https://github.com/chainer/chainer/tree/master/examples/vae
deepmind :early Visual concept learning with unsupervised DeepLearning
描述事件 再生事件 gan 生成视频
gan 学习到属性，把属性联系起来 进入强化学习 返回reward
https://github.com/msracver/Deep-Feature-Flow
- https://www.leiphone.com/news/201608/HPOt16vwh0UNYMPq.html commaai gan 视频预测
https://lmb.informatik.uni-freiburg.de/resources/datasets/FlyingChairs.en.html 光流数据集
https://github.com/apache/incubator-mxnet/tree/430ea7bfbbda67d993996d81c7fd44d3a20ef846/tools/caffe_converter caffe 模型 转 mxnet 模型 转换代码
--------------WassersteinGAN------------------- 推荐一篇用更通俗易懂的语言介绍WGAN的文章： https://zhuanlan.zhihu.com/p/25071913
WGAN源码，作者提供，Torch版本： https://github.com/martinarjovsky/WassersteinGAN Tensorflow版本：https://github.com/Zardinality/WGAN-tensorflow Keras版本： https://github.com/tdeboissiere/DeepLearningImplementations/tree/master/WassersteinGAN
参考文献 Arjovsky, M., & Bottou, L.eon. (2017). Towards Principled Methods for Training Generative AdversarialNetworks. Arjovsky, M., Soumith, C.,& Bottou, L. eon. (n.d.). Wasserstein GAN.
https://github.com/tdeboissiere
https://github.com/tdeboissiere/DeepLearningImplementations
https://github.com/255BITs/HyperGAN
https://junyanz.github.io/CycleGAN/
https://github.com/tjwei/GANotebooks 重要代码
https://github.com/shadySource/cyclegan_keras
https://github.com/junyanz/CycleGAN
https://github.com/PiscesDream/CycleGAN-keras demo
https://github.com/buriburisuri/supervised_infogan
https://github.com/shadySource/cyclegan_keras
https://www.baidu.com/home/news/data/newspage?nid=9868049299374505970&n_type=0&p_from=1&dtype=-1 有意思的东西
一、生成对抗网路(GAN) 生成对抗网络 https://arxiv.org/abs/1406.2661 条件生成对抗网络 https://arxiv.org/abs/1411.1784 InfoGAN https://arxiv.org/abs/1606.03657 Wasserstein GAN https://arxiv.org/abs/1701.07875 模式正则化GAN https://arxiv.org/abs/1612.02136 耦合GAN https://arxiv.org/abs/1606.07536 Conditional Image Synthesis With Auxiliary Classifier GANs https://arxiv.org/abs/1610.09585 Least Squares Generative Adversarial Networks https://arxiv.org/abs/1611.04076v2 Boundary-Seeking Generative Adversarial Networks https://arxiv.org/abs/1702.08431 基于能量的GAN https://arxiv.org/abs/1609.03126 F-GAN:Training Generative Neural Samplers using Variational Divergence Minimization https://arxiv.org/abs/1606.00709 生成对抗并行化 https://arxiv.org/abs/1612.04021 DiscoGAN https://arxiv.org/abs/1703.05192 对抗性特征学习和对抗学习推论 https://arxiv.org/abs/1605.09782 https://arxiv.org/abs/1606.00704 BEGAN https://arxiv.org/abs/1703.10717 Improved Training of Wasserstein GANs https://arxiv.org/abs/1704.00028 DualGAN:Unsupervised Dual Learning for Image-to-Image Translation https://arxiv.org/abs/1704.02510 MAGAN:Margin Adaptation for Generative Adversarial Networks https://arxiv.org/abs/1704.03817 Softmax GAN https://arxiv.org/abs/1704.06191
二、变形自动编码器（VAE） Auto-Encoding Variational Bayes https://arxiv.org/abs/1312.6114 Semi-Supervised Learning with Deep Generative Models https://arxiv.org/abs/1406.5298 Denoising Criterion for Variational Auto-Encoding Framework https://arxiv.org/abs/1511.06406 Adversarial Autoencoders https://arxiv.org/abs/1511.05644 Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks https://arxiv.org/abs/1701.04722
https://github.com/LMescheder/AdversarialVariationalBayes 重要模型