Different results in training a CNN with Matlab 2018a and Matlab 2019a

4 次查看（过去 30 天）
María Begoña Rojas
回答： Faraz Naqvi 2019-7-26
Hi, I am training a CNN of classification.
I have trained it with the same seed in Matlab 2018a and Matlab 2019a, after adapting the initialization algorithm in the convolutional layers and the fully connected layer to 'narrow-nomal' in Matlab 2019a, in order to make it comparable. As well, I have set the validation patience in 12 for both releases.
However, I am still getting far different results. Is there anything else that I should take into account to have the same training results? Are there others updates in Matlab 2019a that I should consider?
Thank you in advance

请先登录，再回答此问题。

回答（2 个）

Greg Heath
Greg Heath 2019-7-20
You are making the task difficult by going backwards.
Start with a single hidden node and add nodes one at a time.
Hope this helps
Greg
Faraz Naqvi
Faraz Naqvi 2019-7-26
I also had this problem. In Matlab 2019 there are additional settings, if you see the properties of layers and compare them with the layer properties from previous version i.e. Matlab 2018 you will observe some extra fields in Matlab 2019.
For me, model model had 'WeightsInitializer' 'narrow-normal' is previous and 'glorot' in newer version. You can look at there aforemention link.
https://www.mathworks.com/help/deeplearning/examples/compare-layer-weight-initializers-example.html

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by