[bug?]DeepLearningImageClassificationExample not getting the expected classification accuracy

1 次查看（过去 30 天）

khcy82dyc 2016-9-16

评论： khcy82dyc 2018-3-5

Hello, I've running the DeepLearningImageClassificationExample from MATLAB.

Unfortunately I keep getting unexpected classification accuracy. On the website the mean accuracy suppose to be 1 however the result I got was 0.3.

confMat =

         0    1.0000         0
         0    1.0000         0
    0.0213    0.9787         0

ans =

0.3333

label =

airplanes

I noticed for some reason the trainingFeatures are the same for all the images, after the following line:

trainingFeatures = activations(convnet, trainingSet, featureLayer, ... 'MiniBatchSize', 32, 'OutputAs', 'columns');

I'm using MATLAB 2016a and I have cuda GPU. Can someone please help to test on your machine seee if you also have the problem? Thanks a lot

Joss Knight 2016-9-19

Do you have a new Pascal GPU like the GeForce GTX 1080? If so, this is your issue:

I do apologise for this. We are waiting on a fix from NVIDIA.

Joss Knight 2018-3-3

Can you upgrade MATLAB?

khcy82dyc 2018-3-5

coming back to this question I'd say the best answer is to upgrade matlab...

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

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

Translated by