%% Create Deep Learning Network Architecture
% Script for creating the layers for a deep learning network with:
%%
%
% Number of layers: 708
% Number of connections: 805
%
%%
% Run the script to create the layers in the workspace variable |lgraph|.
%
% To learn more, see <matlab:helpview('deeplearning','generate_matlab_code')
% Generate MATLAB Code From Deep Network Designer>.
%
% Auto-generated by MATLAB on 01-Oct-2019 12:55:49
%% Create the Layer Graph
% Create the layer graph variable to contain the network's layers.
% Copyright 2019-2020 The MathWorks, Inc.
lgraph = layerGraph();
%% Add the Layer Branches
% Add the branches of the network to the layer graph. Each branch is a linear
% array of layers.
tempLayers = [
imageInputLayer([224 224 3],"Name","input_1","Normalization","zscore")
convolution2dLayer([7 7],64,"Name","conv1|conv","BiasLearnRateFactor",0,"Padding",[3 3 3 3],"Stride",[2 2])
batchNormalizationLayer("Name","conv1|bn")
reluLayer("Name","conv1|relu")
maxPooling2dLayer([3 3],"Name","pool1","Padding",[1 1 1 1],"Stride",[2 2])];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv2_block1_0_bn")
reluLayer("Name","conv2_block1_0_relu")
convolution2dLayer([1 1],128,"Name","conv2_block1_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv2_block1_1_bn")
reluLayer("Name","conv2_block1_1_relu")
convolution2dLayer([3 3],32,"Name","conv2_block1_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv2_block1_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv2_block2_0_bn")
reluLayer("Name","conv2_block2_0_relu")
convolution2dLayer([1 1],128,"Name","conv2_block2_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv2_block2_1_bn")
reluLayer("Name","conv2_block2_1_relu")
convolution2dLayer([3 3],32,"Name","conv2_block2_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv2_block2_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv2_block3_0_bn")
reluLayer("Name","conv2_block3_0_relu")
convolution2dLayer([1 1],128,"Name","conv2_block3_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv2_block3_1_bn")
reluLayer("Name","conv2_block3_1_relu")
convolution2dLayer([3 3],32,"Name","conv2_block3_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv2_block3_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv2_block4_0_bn")
reluLayer("Name","conv2_block4_0_relu")
convolution2dLayer([1 1],128,"Name","conv2_block4_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv2_block4_1_bn")
reluLayer("Name","conv2_block4_1_relu")
convolution2dLayer([3 3],32,"Name","conv2_block4_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv2_block4_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv2_block5_0_bn")
reluLayer("Name","conv2_block5_0_relu")
convolution2dLayer([1 1],128,"Name","conv2_block5_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv2_block5_1_bn")
reluLayer("Name","conv2_block5_1_relu")
convolution2dLayer([3 3],32,"Name","conv2_block5_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv2_block5_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv2_block6_0_bn")
reluLayer("Name","conv2_block6_0_relu")
convolution2dLayer([1 1],128,"Name","conv2_block6_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv2_block6_1_bn")
reluLayer("Name","conv2_block6_1_relu")
convolution2dLayer([3 3],32,"Name","conv2_block6_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
depthConcatenationLayer(2,"Name","conv2_block6_concat")
batchNormalizationLayer("Name","pool2_bn")
reluLayer("Name","pool2_relu")
convolution2dLayer([1 1],128,"Name","pool2_conv","BiasLearnRateFactor",0)
averagePooling2dLayer([2 2],"Name","pool2_pool","Stride",[2 2])];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv3_block1_0_bn")
reluLayer("Name","conv3_block1_0_relu")
convolution2dLayer([1 1],128,"Name","conv3_block1_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv3_block1_1_bn")
reluLayer("Name","conv3_block1_1_relu")
convolution2dLayer([3 3],32,"Name","conv3_block1_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv3_block1_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv3_block2_0_bn")
reluLayer("Name","conv3_block2_0_relu")
convolution2dLayer([1 1],128,"Name","conv3_block2_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv3_block2_1_bn")
reluLayer("Name","conv3_block2_1_relu")
convolution2dLayer([3 3],32,"Name","conv3_block2_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv3_block2_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv3_block3_0_bn")
reluLayer("Name","conv3_block3_0_relu")
convolution2dLayer([1 1],128,"Name","conv3_block3_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv3_block3_1_bn")
reluLayer("Name","conv3_block3_1_relu")
convolution2dLayer([3 3],32,"Name","conv3_block3_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv3_block3_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv3_block4_0_bn")
reluLayer("Name","conv3_block4_0_relu")
convolution2dLayer([1 1],128,"Name","conv3_block4_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv3_block4_1_bn")
reluLayer("Name","conv3_block4_1_relu")
convolution2dLayer([3 3],32,"Name","conv3_block4_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv3_block4_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv3_block5_0_bn")
reluLayer("Name","conv3_block5_0_relu")
convolution2dLayer([1 1],128,"Name","conv3_block5_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv3_block5_1_bn")
reluLayer("Name","conv3_block5_1_relu")
convolution2dLayer([3 3],32,"Name","conv3_block5_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv3_block5_concat");
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
batchNormalizationLayer("Name","conv3_block6_0_bn")
reluLayer("Name","conv3_block6_0_relu")
convolution2dLayer([1 1],128,"Name","conv3_block6_1_conv","BiasLearnRateFactor",0)
batchNormalizationLayer("Name","conv3_block6_1_bn")
reluLayer("Name","conv3_block6_1_relu")
convolution2dLayer([3 3],32,"Name","conv3_block6_2_conv","BiasLearnRateFactor",0,"Padding","same")];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = depthConcatenationLayer(2,"Name","conv3_block6
matlab2022a
添加Deep Learning DeepLearnToolbox
mapminmax （2000个子文件） 
main.css 1.15MB main.css 1.13MB main.css 1.12MB main.css 1.09MB main.css 1.09MB main.css 1.04MB generatedCss.css 1.03MB liveeditor.css 1.02MB main.css 1MB index-css.css 945KB main.css 940KB main.css 939KB main.css 924KB main.css 923KB main.css 902KB main.css 902KB main.css 902KB main.css 897KB main.css 852KB main.css 852KB main.css 844KB main.css 843KB main.css 840KB main.css 832KB main.css 832KB main.css 825KB main.css 824KB main.css 823KB main.css 818KB main.css 793KB main.css 782KB main.css 758KB main.css 753KB main.css 753KB main.css 751KB main.css 734KB main.css 680KB main.css 665KB main.css 664KB main.css 585KB main.css 543KB main.css 534KB wizard.css 533KB cloud-check.css 529KB main.css 529KB main.css 466KB main.css 462KB main.css 460KB main.css 460KB export.css 193KB RichTextComponentDefaultVisualFamily.css 193KB RichTextComponentBase.css 193KB webwidget.css 183KB bootstrap.css 129KB bootstrap.min.css 118KB webwidget.dojoRelease.css 109KB webwidget.dojo.css 109KB deepapp-editor.css 103KB inspector_peer.css 81KB inspector_client.css 81KB main.css 66KB main.css 58KB main.css 58KB main.css 58KB main.css 58KB desktop_importtool.css 49KB importtool_peer.css 49KB importtool_client.css 49KB export.css 49KB main.css 45KB desktop_workspacebrowser.css 39KB table.css 37KB desktop_variableeditor.css 37KB embedded.css 36KB variableeditor_peer.css 35KB embedded.min.css 33KB AutoCompletion.css 32KB variableeditor_client.css 30KB export.css 30KB rendererseditors.css 27KB export.css 27KB FunctionAssistant.css 26KB main.css 24KB bootstrap-theme.css 24KB bootstrap-theme.min.css 23KB export.css 21KB LiveControls.css 21KB DropDownButtonSplitButtonToggleSplitButton.css 19KB app.css 18KB main.css 18KB theme.css 18KB export.css 17KB main.css 16KB theme_dark.css 15KB main.css 15KB analysis_report.css 14KB export.css 14KB main.css 14KB main.css 14KB main.css 14KB共 2000 条
- 1
- 2
- 3
- 4
- 5
- 6
- 20
资源评论
