Can anyone help me to use .mat for validation in CNN classification?
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
Sulochana S
am 3 Aug. 2019
Kommentiert: Sulochana S
am 13 Aug. 2019
close all;
clear all;
clc;
mynet = open('Gnet.mat');
% mynet = disp(mynet);
%test classifier using train samples
imdsTest=imageDatastore('E:\Postmanpack\Ppimplementation\Myxraytesting/',...
'IncludeSubfolders', true,...
'LabelSource', 'foldernames');
inputSize= [227 227 3];
augimdsTest=augmentedImageDatastore(inputSize, imdsTest, 'ColorPreprocessing', 'gray2rgb');
% %test classifier using test samples
[YPred, scores]=classify(mynet.Gnet, augimdsTest);
YTest=imdsTest.Labels; %expected result
accuracy=mean(YPred==YTest)
error
Reference to non-existent field 'Gnet'.
Error in TESTALEXNET1 (line 14)
[YPred, scores]=classify(mynet.Gnet, augimdsTest);
2 Kommentare
Akzeptierte Antwort
Srivardhan Gadila
am 6 Aug. 2019
mynetstrcut = load('Gnet.mat’'); %loads the structure
mynet = mynetstruct.Gnet; % here Gnet = name of your network (Gnet) and the network “Gnet” is stored in mynet
[YPred, scores] = classify(mynet,augimdsTest);
Alternatively
load Gnet; %provided only Gnet is saved in 'Gnet.mat'
[YPred, scores] = classify(Gnet,augimdsTest);
Weitere Antworten (0)
Siehe auch
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!