HOW TO INCREASE TESTING ACCURACY IN CNN?
5 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
I have 5600 training images. I have extracted features using Principal Component Analysis (PCA). Now I am applying CNN on feature vector. Testing accuracy is 18%. How to increase testing accuracy?
Feature vector size: 640*1
Training code:
layers = [
imageInputLayer([1 640 1]);
reluLayer
fullyConnectedLayer(7);
softmaxLayer();
classificationLayer()];
options = trainingOptions('sgdm', 'Momentum',0.95, 'InitialLearnRate',0.0001, 'L2Regularization', 1e-4, 'MaxEpochs',20);
0 Commenti
Risposte (3)
vaibhav mishra
il 30 Giu 2020
Hi,
there can be different ways to increase the test accuracy.
If your training accuracy is good but test accuracy is low then you need to introduce regularization in your loss function, or you need to increase your training set.
if your training accuracy increased and then decreased and then your test accuracy is low, you are over training your model so try to reduce the epochs.
if your both training and testing accuracy are less then try to either change your model architecture, or increase the training data or decrease learning rate or increase the number of epochs.
Feel free to ask for any clarification.
o.cefet cefet
il 1 Set 2020
Hello, my dear.
I think you could insert two things: layer dropout and data augmentation.
It's fine with your regularization code, but now you have to change the value of these regularizations, and look for "the best value".
0 Commenti
Vedere anche
Categorie
Scopri di più su Image Data Workflows in Help Center e File Exchange
Prodotti
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!