why my classification results are not correct

1 次查看（过去 30 天）
Aiman Zara
Aiman Zara 2023-1-2
回答： Image Analyst 2023-1-2
net = googlenet;
inputSize = net.Layers(1).InputSize
classNames = net.Layers(end).ClassNames;
numClasses = numel(classNames);
disp(classNames(randperm(numClasses,10)))
im = imread("D:\cotton\dataset\Alternaria fliph\(9).jpeg");
figure
imshow(im)
size(im)
im = imresize(im,inputSize(1:2));
figure
imshow(im)
[label,scores] = classify(net,im);
label
figure
imshow(im)
title(string(label) + ", " + num2str(100*scores(classNames == label),3) + "%");
[~,idx] = sort(scores,'descend');
idx = idx(5:-1:1);
classNamesTop = net.Layers(end).ClassNames(idx);
scoresTop = scores(idx);
figure
barh(scoresTop)
xlim([0 1])
title('Top 5 Predictions')
xlabel('')
yticklabels(classNamesTop)

请先登录，再回答此问题。

回答（1 个）

Image Analyst
Image Analyst 2023-1-2
It was probably not trained with enough examples of the class it's getting wrong.

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2019a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by