Can you please guide utilizing Validation Data along with an image data store?
2 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Matthieu
le 5 Juin 2023
Commenté : Amanjit Dulai
le 12 Juin 2023
I'm using a data store of 50 k images of Breast Cancer.
I want to verify if my training learning is susceptible to overfitting.
But I don't understand, How to use validation data.
This my script without validation data:
0 commentaires
Réponse acceptée
Amanjit Dulai
le 5 Juin 2023
You can specify validation data in the training options with the ValidationData option. Below I've used your test data set, but you probably might want to create a separate validation set from your original data:
opts = trainingOptions("sgdm", ...
"InitialLearnRate", 0.0001, ...
"MaxEpoch", 10, ...
"Plots", "training-progress", ...
"ValidationData", resizeBreastCancerTest);
4 commentaires
Amanjit Dulai
le 12 Juin 2023
There are a few things you could try.
- The initial learning rate of 0.0001 is quite low. You could try increasing it.
- Alternatively, you could try using the ADAM algorithm for training, which tends to be less sensitive to hyperparameters. You can do this by changing "sgdm" in the call to trainingOptions to "adam".
- You could train for more epochs. 10 epochs is a fairly low number.
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Annotations dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!