How to increase the training and testing accuracy in CNN training?
1 view (last 30 days)
Show older comments
I am using MATLAB for CNN training. I have a data set of 27,000 images and angles corresponding to that images. My sample code is : %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
layers = [imageInputLayer([32 32 1])
convolution2dLayer(5,50)
reluLayer()
maxPooling2dLayer(2,'Stride',2)
fullyConnectedLayer(size(categories(trainAngle)))
softmaxLayer
classificationLayer];
options = trainingOptions('sgdm', 'MaxEpochs', 50,'InitialLearnRate', 0.0003);
convnet = trainNetwork(trainZ, trainAngle, layers,options);
% trainZ is my 4D matrix of images and trainAngle is 2D array of angles corresponding to images!
resultant_Train = classify(convnet,trainZ); %Training data
resultant_Valid = classify(convnet,validZ); %Validation data
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
My training accuracy is 70%
but test accuracy is only 2%;
I am completely blank what to do next. Do you have any suggestion? How can I improve my test accuracy?
Can someone also suggest how can i use adam in place of sgdm in optimizer?
1 Comment
MatlabUserN
on 21 Jun 2017
Well increase the number of layers. minimum number of network layers should be 7. Make the network denser as the name suggest deep CNN. increase the number of epochs.
Answers (1)
Salma Hassan
on 20 Nov 2017
hi sir did you find any solution for your problem , i have the same on
0 Comments
See Also
Categories
Find more on Image Segmentation and Analysis in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!