making layers block, adding layers

hi, i'm trying to make (a) structure, and each U, D, R, S blocks are (b)~(d)
and i don't know how to build it, i mean should i make a function for each blocks ? if i have to, how should i set the element of function?
+ i was making (b) block and it's like
Downsampling = [
batchNormalizationLayer('Name','batchnorm_1')
reluLayer('Name','relu_1')
convolution2dLayer(3, 32, 'Stride', 2, 'Name','conv_1')
batchNormalizationLayer('Name','batchnorm_2')
reluLayer('Name','relu_2')
convolution2dLayer(3, 32, 'Stride', 1, 'Name','conv_2')
additionLayer(2,'Name','add')
];
lgraph = layerGraph(Downsampling);
skipConv = convolution2dLayer(3, 32,'Stride', 2,'Name','skipConv');
lgraph = connectLayers(lgraph,'skipConv','add');
i don't know where to put skipConv layer....

回答(0 个)

类别

帮助中心File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by