Different behavior of 'activations' function of Neural Network Toolbox between 2017b and 2018a.

1 次查看（过去 30 天）
HIDEYA MATSUDA
HIDEYA MATSUDA 2018-5-4
评论： HIDEYA MATSUDA 2018-5-4
If I tried CNN sample code obtained here, I got error on 2018a and not on 2017a. Is it a bug or expected behavior? How can I fixed it on 2018a?
  1. Obtained sample code here.https://jp.mathworks.com/matlabcentral/fileexchange/57280-cnn---transfer-learning-example
  2. Run classifyFlowers.m
  3. Hit following error
Error: classifyFlowers (line 39)
classifier = fitcsvm(trainingFeatures, trainingSet.Labels);
Findings:
I found that the size of matrix of returned value from 'activations' function was different.
trainingFeatures = activations(convnet, trainingSet, featureLayer, 'MiniBatchSize', 1);
2017b (Expected):
>> size(trainingFeatures)
ans =
112 4096
2018a (Not Expected):
>> size(trainingFeatures)
ans =
1 1 4096 112

请先登录，再回答此问题。

采纳的回答

Johannes Bergstrom
This is the expected behavior. Please see the release notes under 'Functionality Being Removed or Changed', https://www.mathworks.com/help/nnet/release-notes.html
Default output format of activations: In R2018a, the new default output format of activations is a 4-D array. To reproduce the old default behavior, set the 'OutputAs' value to 'rows'.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Install Products 的更多信息

标签

产品

Community Treasure Hunt

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

Start Hunting!

Translated by