Overfitting problem of number recognition in convolutional neural networks
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
Hello, everyone!I'm a beginner in convolutional neural networks.I used Convolutional Neural Network to do simple number recognition.I used MNIST as the data set and took 10,000 pieces from the 60,000 pieces of training set as the validation set.batch_sizes=128,epoch=30,InitialLearnRate=0.01.I get two results, one is accuracy and the other is loss.I don't know if this is an overfitting.I wish someone could give me an answer,thank you!
0 Kommentare
Antworten (0)
Siehe auch
Kategorien
Mehr zu Sequence and Numeric Feature Data Workflows finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!