17-卷积神经网络实例.pptxVIP

DeepLearninganditsApplicationConvolutionalneuralnetworks

CNNArchitectures59CaseStudiesAlexNetVGGGoogLeNetResNetAlso....NiN(NetworkinNetwork)WideResNetResNeXTStochasticDepthSqueeze-and-ExcitationNetworkDenseNetFractalNetSqueezeNetNASNetSJTUDeepLearningLecture.

Review:LeNet-5[LeCunetal.,1998]Convfilterswere5x5,appliedatstride1Subsampling(Pooling)layerswere2x2appliedatstride2i.e.architectureis[CONV-POOL-CONV-POOL-FC-FC]60SJTUDeepLearningLecture.[1]Gradient-basedlearningappliedtodocumentrecognition,ProceedingsoftheIEEE,86(11)1998

CaseStudy:AlexNet[Krizhevskyetal.2012]61Architecture:CONV1MAXPOOL1NORM1CONV2MAXPOOL2NORM2CONV3CONV4CONV5MaxPOOL3FC6FC7FC8Input:227x227x3imagesFirstlayer(CONV1):9611x11filtersappliedatstride4=Q:whatistheoutputvolumesize?Hint:(227-11)/4+1=55Outputvolume[55x55x96]Q:Whatisthetotalnumberofparametersinthislayer?Parameters:(11*11*3)*96=35KSJTUDeepLearningLecture.[1]ImageNetClassificationwithDeepConvolutionalNeuralNetworks,NIPS2012

CaseStudy:AlexNetArchitecture:CONV1MAXPOOL1NORM1CONV2MAXPOOL2NORM2CONV3CONV4CONV5MaxPOOL3FC6FC7FC8Input:227x227x3imagesAfterCONV1:55x55x9662Secondlayer(POOL1):3x3filtersappliedatstride2Outputvolume:27x27x96Parameters:0!SJTUDeepLearningLecture.

CaseStudy:AlexNetFull(simplified)AlexNetarchitecture:[227x227x3]INPUT[55x55x96]CONV1:9611x11filtersatstride4,pad0[27x27x96]MAXPOOL1:3x3filtersatstride2[27x27x96]NORM1:Normalizationlayer[27x27x256]CONV2:2565x5filtersatstride1,pad2[13x13x256]MAXPOOL2:3x3filtersatstride2[13x13x256]NORM2:Normalizationlayer[13x13x384]CONV3:3843x3filtersatstride1,pad1[13x13x384]CONV4:3843x3filtersatstride1,pad1[13x13x256]CONV5:2563x3filtersatstride1,pad1[6x6x256]MAXPOOL3:3x3filtersatstride2[4096]FC6:4096neurons[4096]FC7:4096neurons[1000]FC8:1000neurons(classs