im试图使用excel文件作为数据库来训练此CNN,并idk如何将其设置为适当的数据库。我也无法设置这些参数来训练我的网络。我的Excel是160x2的两倍。 所以我整理好了并运行了代码,但它向我展示了这一点: net = trainNetwork(trainD,targetD,layers,options);
Caused by:
Layer 9: Input size mismatch. Size of input to this layer is different
from the expected input size.
Inputs to this layer:
from layer 8 (80×1×16 output)
这是我的损坏代码:
addpath('C:\Users\HP\Desktop\CNN Data');
trainD =xlsread('Recie_1'); %my trainning data saved as Recie_*
targetD= xlsread('Trans_1');
layers = [ imageInputLayer([160 2])
convolution2dLayer(2,16,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(2,16,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(2,32,'Padding','same')
batchNormalizationLayer
reluLayer
fullyConnectedLayer(100)
fullyConnectedLayer(50)
fullyConnectedLayer(7)
softmaxLayer
classificationLayer];
options = trainingOptions('adam', ...
'Shuffle','every-epoch', ...
'InitialLearnRate',0.01, ....
'MaxEpochs',550, ...
'MiniBatchSize',64, ...
'ValidationFrequency',30, ...
'Verbose',true, ...
'Plots','training-progress');
%%Train ConvNet:
net = trainNetwork(trainD,targetD,layers,options);
predictedLabels = classify(net,trainD)';
accuracy = sum(predictedLabels == targetD)/numel(targetD);