與Deep CNNs共享ImageNet分類(lèi)的細(xì)節(jié)_第1頁(yè)
與Deep CNNs共享ImageNet分類(lèi)的細(xì)節(jié)_第2頁(yè)
與Deep CNNs共享ImageNet分類(lèi)的細(xì)節(jié)_第3頁(yè)
與Deep CNNs共享ImageNet分類(lèi)的細(xì)節(jié)_第4頁(yè)
與Deep CNNs共享ImageNet分類(lèi)的細(xì)節(jié)_第5頁(yè)
已閱讀5頁(yè),還剩27頁(yè)未讀, 繼續(xù)免費(fèi)閱讀

下載本文檔

版權(quán)說(shuō)明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權(quán),請(qǐng)進(jìn)行舉報(bào)或認(rèn)領(lǐng)

文檔簡(jiǎn)介

SharingdetailofImageNetClassificationwithDeepCNNs林木得OutlineOverviewGoalDatasetModelMotivationArchitectureResultsPartIBasicProblemsActivationFunctionLossFunctionLearningMethodPartIIModelFeaturesReLUNonlinearityTrainingonMultipleGPUsLocalResponseNormalizationOverlappoolingReduceOverfittingDataAugmentationDropoutPartIIIMainphasesPreprocessInitializationStochasticgradientdescentTestReferencesOverviewGoalDatasetModelResultsGoalImageclassificationClassify

theImageNetLSVRC-2010contestimagesinto1000differentclasses.DataSetroughly1.2milliontrainingimages50,000validationimages150,000testingimagesModelMotivation利用自然圖像性質(zhì)

stationarity

of

statistics

locality

of

pixel

independencies模擬神經(jīng)網(wǎng)絡(luò)工作機(jī)理

receptivefieldModelArchitectureResultsTesterrorinILSVR-2010testsetResultsTesterrorinILSVR-2012testsetsPartIBasicProblemsActivationFunctionLostFunctionLearningMethodActivationFunctionForalllayersexceptoutputlayer: RectifiedLinearUnit(ReLU)TobeconfirmedForoutputlayer:

ReLUandLossFunctionmultinomiallogisticregressionobjective:

tobeconfirmed

LearningMethodGradientDescentTobemorespecific,StochasticGradientDescentwithbatchof128images.PartIIModelFeaturesReLUNonlinearityTrainingonMultipleGPUsLocalResponseNormalizationOverlappoolingReduceOverfittingDataAugmentationDropoutReLUNonlinearityStandardactivationfunction:f(x)=tanh(x)orf(x)=(1+ex)-1

Newinthispaper:

RectifiedLinearUnit(ReLU):

f(x)=max(0,x)

CIFAR-10PerformancecompariseTrainingonMultipleGPUsputshalfofthekernels(orneurons)oneachGPUtheGPUscommunicateonlyincertainlayers.readfromandwritetooneanother’smemorydirectly,Withouthostmachinememoryreducesourtop-1andtop-5errorratesby1.7%and1.2%LocalResponseNormalizationOnvalidationset

k=2,n=5,alpha=10-4,andbeta=0.75

In

realneurons,

橫向抑制reducesourtop-1andtop-5errorratesby1.4%and1.2%,respectively.OverlappoolingTraditionally,

non-overlappoolingNewinthispaper:Overlappoolings=2andz=3.educesthetop-1andtop-5errorratesby0.4%and0.3%,respectivelyWhypooling:

1,reducenumberofneuron 2,translateinvarianceOverallarchitectureOverallArchitectureNeuronineachlayers:224x224x3,55x55x96,27x27x256,13x13x394,13x13x394,13x13x256,4096,4096,1000.Almost:650,000neuronsParameterineachlayers:11x11x3x96,5x5x48x256,3x3x256x384,3x3x192x384,3x3x192x256,43264x4096,4096x4096,4096x1000Almost:60millionparametersReduceOverfittingReduceoverfittingisthemostimportantproblemforthismodelDataArgumentationgeneratingimagetranslationsandhorizontalreflec-tions.Train:Afactorof2048moreimagesTest:5x2imagesaveragepredictalteringtheintensitiesoftheRGBchannelsintrainingimages.toeachRGBimagepixelIxy=[IR,IG,IB]Tweaddthefollowingquantity:xyxyxyreducesthetop-1errorratebyover1%.

ReduceOverfittingDropoutMotivation:

Tooexpensivetocombinemanyabovemodelsthattakes5daystotrain

ReduceOverfittingDropoutHOW:

train:settingtozerotheoutputofeachhiddenneuronwithprobability0.5inthefirst2fully-connectlayers.

test:usealltheneuronsbutmultiplytheiroutputsby0.5ReduceOverfittingDropoutCost:

roughlydoublesthenumberofiterationsrequiredtoconverge

PartIIIMainphasesPreprocessInitializationStochasticgradientdescentTestPreprocessdown-sampledtheimagestoafixedresolutionof256x256rescaledtheimagesuchthattheshortersidewasoflength256croppedoutthecentral256x256patchfromtheresultingimagesubtractingthemeanactivityoverthetrainingsetfromeachpixel.Thustrainnetworkonthe(centered)rawRGBvaluesofthepixels.Initializationinitializedtheweightsineachlayerfromazero-meanGaussiandistributionwithstandardde-viation0.01.initializedtheneuronbiasesinthesecond,fourth,andfifth

convolutionallayers,aswellasinthefully-connectedhiddenlayers,withtheconstant1

initializedtheneuronbiasesintheremaininglayerswiththeconstant0learningratewasinitializedat0.01Stochasticgradientdescentwithabatchsizeof128examplesdecayof0.0005Updaterulesdividethelearningrateby10whenthevalidationerrorratestoppedimprovingwiththecurrentlearningrate.learningratereducedthreetimespriortotermination90cyclesthrough1.2millionimages

,took5to6daysTestAttesttime,thenetworkmakesapredictionbyextracting5x2224x224patchesaswellastheirhorizontalreflections(hencetenpatchesinall),andaveragingthepredictionsmadebythenetwork’ssoftmaxlayeronthetenpatches.Attesttime,weusealltheneuronsbutmultiplytheiroutputsby0.5

inthefirsttwofully-connectedlayers.References1,ImageNetClassifi

溫馨提示

  • 1. 本站所有資源如無(wú)特殊說(shuō)明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請(qǐng)下載最新的WinRAR軟件解壓。
  • 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請(qǐng)聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
  • 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁(yè)內(nèi)容里面會(huì)有圖紙預(yù)覽,若沒(méi)有圖紙預(yù)覽就沒(méi)有圖紙。
  • 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
  • 5. 人人文庫(kù)網(wǎng)僅提供信息存儲(chǔ)空間,僅對(duì)用戶上傳內(nèi)容的表現(xiàn)方式做保護(hù)處理,對(duì)用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對(duì)任何下載內(nèi)容負(fù)責(zé)。
  • 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容,請(qǐng)與我們聯(lián)系,我們立即糾正。
  • 7. 本站不保證下載資源的準(zhǔn)確性、安全性和完整性, 同時(shí)也不承擔(dān)用戶因使用這些下載資源對(duì)自己和他人造成任何形式的傷害或損失。

評(píng)論

0/150

提交評(píng)論