版权说明:本文档由用户提供并上传,收益归属内容提供方,若内容存在侵权,请进行举报或认领
文档简介
GenerativeAdversarialNetwork(GAN)RestrictedBoltzmannMachine:://.tw/~tlkagk/courses/MLDS_2015_2/Lecture/RBM%20(v2).ecm.mp4/index.htmlGibbsSampling:://.tw/~tlkagk/courses/MLDS_2015_2/Lecture/MRF%20(v2).ecm.mp4/index.htmlOutlook:NIPS2016Tutorial:GenerativeAdversarialNetworksAuthor:IanGoodfellowPaper:s:///abs/1701.00160Video:YoucanfindtipsfortrainingGANhere:s://github/soumith/ganhacksReviewGenerationDrawing?WritingPoems?Review:Auto-encoderAscloseaspossibleNNEncoderNNDecodercodeNNDecodercodeRandomlygenerateavectorascodeImage?Review:Auto-encoderNNDecodercode2D-1.51.5
NNDecoder
NNDecoderReview:Auto-encoder-1.51.5NNEncoderNNDecodercodeinputoutputAuto-encoderVAENNEncoderinputNNDecoderoutputm1m2m3
Fromanormaldistribution
X+Minimizereconstructionerror
exp
MinimizeAuto-EncodingVariationalBayes,s:///abs/1312.6114ProblemsofVAEItdoesnotreallytrytosimulaterealimagesNNDecodercodeOutputAscloseaspossibleOnepixeldifferencefromthetargetOnepixeldifferencefromthetargetRealisticFakeTheevolutionofgenerationNNGeneratorv1Discri-minatorv1Realimages:NNGeneratorv2Discri-minatorv2NNGeneratorv3Discri-minatorv3BinaryClassifierTheevolutionofgenerationNNGeneratorv1Discri-minatorv1Realimages:NNGeneratorv2Discri-minatorv2NNGeneratorv3Discri-minatorv3GAN-DiscriminatorNNGeneratorv1Realimages:Discri-minatorv1image1/0(realorfake)SomethinglikeDecoderinVAERandomlysampleavector11110000GAN-GeneratorDiscri-minatorv1NNGeneratorv1Randomlysampleavector0.13UpdatingtheparametersofgeneratorTheoutputbeclassifiedas“real”(ascloseto1aspossible)Generator+Discriminator=anetworkUsinggradientdescenttoupdatetheparametersinthegenerator,butfixthediscriminator1.0v2GAN
–二次元人物頭像鍊成DCGAN:s://github/carpedm20/DCGAN-tensorflowGAN
–二次元人物頭像鍊成100roundsGAN
–二次元人物頭像鍊成1000roundsGAN
–二次元人物頭像鍊成2000roundsGAN
–二次元人物頭像鍊成5000roundsGAN
–二次元人物頭像鍊成10,000roundsGAN
–二次元人物頭像鍊成20,000roundsGAN
–二次元人物頭像鍊成50,000roundsBasicIdeaofGANMaximumLikelihoodEstimation
Likelihoodofgeneratingthesamples
MaximumLikelihoodEstimation
Itisdifficulttocomputethelikelihood.
BasicIdeaofGANGeneratorGGisafunction,inputz,outputxGivenapriordistributionPprior(z),aprobabilitydistributionPG(x)isdefinedbyfunctionGDiscriminatorDDisafunction,inputx,outputscalarEvaluatethe“difference”betweenPG(x)andPdata(x)ThereisafunctionV(G,D).
HardtolearnbymaximumlikelihoodBasicIdea
GivenG,whatistheoptimalD*maximizingGivenx,theoptimalD*maximizing
AssumethatD(x)canhaveanyvaluehere
Givenx,theoptimalD*maximizingFindD*maximizing:
aDbD0<<1
22
Jensen-Shannondivergence
Intheend……
0<<log2
Algorithm
Algorithm
DecreaseJS
divergence(?)DecreaseJS
divergence(?)Algorithm
DecreaseJS
divergence(?)
smaller
……
Don’tupdateGtoomuchInpractice…
Maximize
MinimizeCross-entropyBinaryClassifierOutputisD(x)Minimize–logD(x)IfxisapositiveexampleIfxisanegativeexampleMinimize–log(1-D(x))
PositiveexamplesNegativeexamples
MaximizeMinimize
MinimizeCross-entropyBinaryClassifierOutputisf(x)Minimize–logf(x)IfxisapositiveexampleIfxisanegativeexampleMinimize–log(1-f(x))
AlgorithmRepeatktimesLearningDLearningG
CanonlyfindlowerfoundofOnlyOnceObjectiveFunctionforGenerator
inRealImplementation
Realimplementation:labelxfromPGaspositive
SlowatthebeginningDemoThecodeusedindemofrom:s://github/osh/KerasGAN/blob/master/MNIST_CNN_GAN_v2.ipynbIssueaboutEvaluatingtheDivergenceEvaluatingJSdivergenceMartinArjovsky,
LéonBottou,TowardsPrincipledMethodsforTrainingGenerativeAdversarialNetworks,
2017,arXivpreprintEvaluatingJSdivergenceJSdivergenceestimatedbydiscriminatortellinglittleinformations:///abs/1701.07875WeakGeneratorStrongGeneratorDiscriminator
Reason1.Approximatebysampling
10=0
log2Weakenyourdiscriminator?CanweakdiscriminatorcomputeJSdivergence?Discriminator
Reason2.thenatureofdata
10=0
log2
UsuallytheydonothaveanyoverlapEvaluationBetterEvaluation
Better…………Notreallybetter……AddNoiseAddsomeartificialnoisetotheinputsofdiscriminatorMakethelabelsnoisyforthediscriminator
DiscriminatorcannotperfectlyseparaterealandgenerateddataNoisesdecayovertimeModeCollapseModeCollapseDataDistributionGeneratedDistributionModeCollapse
Whatwewant…Inreality…FlawinOptimization?
ModifiedfromIanGoodfellow’stutorial
Thismaynotbethereason(basedonIanGoodfellow’stutorial)SomanyGANs……ModifyingtheOptimizationofGANfGANWGANLeast-squareGANLossSensitiveGANEnergy-basedGANBoundary-seekingGANUnrollGAN……DifferentStructurefromtheOriginalGANConditionalGANSemi-supervisedGANInfoGANBiGANCycleGANDiscoGANVAE-GAN……ConditionalGANMotivationGeneratorScottReed,ZeynepAkata,XinchenYan,LajanugenLogeswaran,BerntSchiele,HonglakLee,“GenerativeAdversarialText-to-ImageSynthesis”,ICML2016TextImageScottReed,
ZeynepAkata,
SantoshMohan,
SamuelTenka,
BerntSchiele,
HonglakLee,“LearningWhatandWheretoDraw”,NIPS2016HanZhang,
TaoXu,
HongshengLi,
ShaotingZhang,
XiaoleiHuang,
XiaogangWang,
DimitrisMetaxas,“StackGAN:TexttoPhoto-realisticImageSynthesiswithStackedGenerativeAdversarialNetworks”,arXivprepring,2016MotivationChallengeNNTextImage(apoint,notadistribution)Text:“train”NN
output
ConditionalGANG
conditionPriordistributionLearntoapproximateP(x|c)D(
温馨提示
- 1. 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。图纸软件为CAD,CAXA,PROE,UG,SolidWorks等.压缩文件请下载最新的WinRAR软件解压。
- 2. 本站的文档不包含任何第三方提供的附件图纸等,如果需要附件,请联系上传者。文件的所有权益归上传用户所有。
- 3. 本站RAR压缩包中若带图纸,网页内容里面会有图纸预览,若没有图纸预览就没有图纸。
- 4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
- 5. 人人文库网仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对用户上传分享的文档内容本身不做任何修改或编辑,并不能对任何下载内容负责。
- 6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
- 7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。
最新文档
- 乒乓球活动策划方案
- 大学生学生会工作总结集锦15篇
- 幼儿园儿童节邀请函四篇
- 区道路及雨污水管网工程给排水工程、电气工程施工方法
- 学期末教师教学工作总结参考范本
- 《探索传统文化类栏目的创新发展新优势》
- 《基于工业4.0的汽车企业供应链协同管理研究》
- 教师辞职报告范文
- 新员工自我介绍合集15篇
- 《基于电动汽车变速箱降噪的齿轮修形技术研究》
- 案例分析 长沙望城区自建房倒塌事23课件讲解
- 管道巡护管理
- 第17课《猫》课件+【知识精研】统编版语文七年级上册
- 《程序化成功案例》课件
- 2025年中考道德与法治一轮教材复习-九年级下册-第一单元 我们共同的世界
- 【MOOC】中国电影经典影片鉴赏-北京师范大学 中国大学慕课MOOC答案
- 专题01:新闻作品-2023-2024学年八年级语文上册单元主题阅读(统编版)(原卷版+解析)
- 陕西省西安市长安区2024-2025学年八年级上学期期中地理试卷
- 企业破产律师服务协议
- 【MOOC】遗传学-中国农业大学 中国大学慕课MOOC答案
- 预防火灾消防安全培训
评论
0/150
提交评论