deep network designer, how do I test a trained network against a new dataset? I am able to see the predictions for all the images?
1 view (last 30 days)
So first of all I am not a computer scientist, just starting to use MatLab.
I have tried deep network designer to classify between 3 classes. Saved the script, the results etc. Now I want to use this trained network on a new dataset and also I really need to see the results for each imagine in the dataset. Is this possible and is anyone able to help?
Thanks a lot
David Willingham on 13 May 2022
Firstly, glad to hear your starting your journey of deep learning in MATLAB!
Your code will likely look like this:
imds = imageDatastore('MyImageFolder', ...
[YPred,scores] = classify(mytrainedNet,imds);
idx = randperm(numel(imds.Files),4);
for i = 1:4
I = readimage(imds,idx(i));
label = YPred(idx(i));
I would also recommend studying this example. It shows the suggested workflow for performing transfer learning :