I have to design a segmentation network with input image size [512 78 1]. I have set the layers in the encoder path but don't know how to design the decoder part. Code for Encoder part is given below. Kindly tell me the instruction to construct a similar decoder part for segmentation.segnetLayers() is not working. Your help will be highly appreciated.
layers = [
imageInputLayer([512 78 1])
convolution2dLayer(3,16,'Padding',1)
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(3,32,'Padding',1)
batchNormalizationLayer
reluLayer
fullyConnectedLayer(10)
softmaxLayer
classificationLayer
];
0 件のコメント
サインインしてコメントする。