How to apply a trained CNN model on a test image set for prediction of its classes and obtaining test accuracy

11 Ansichten (letzte 30 Tage)
I have trained a CNN model using a set of 8000 data having 5 classes. I have split the dataset as 80% for training and 20% for validation. After training I have saved the trained model using 'save(filename)' function. Now in a another script I want to load this trained model and use it on a different set of 1000 test image data. I have stored the test dataset of 5 classes in a folder. Now how can I apply the trained CNN model on this test image dataset and obtain the confusion plot and accuracy on test dataset? Someone please help with a sample code for this. I will be thankful to you.

Antworten (1)

Muhammad
Muhammad am 19 Jul. 2023
You can simply load the model and then apply prediction.
[predictions, ~] = classify(model, imdsTest);

Kategorien

Mehr zu Pattern Recognition and Classification 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!

Translated by