How do I enable 3D deep learning support for convolution layer?

2019 8 19
1 个回答
回答已采纳
更新时间：2025 2 7
9 次查看（30 天）

0 个投票

I am trying to implement a point cloud classification network (3DmFV-Net) using MATLAB's new 3D layers support and was unable to find a 3D concatenation layer.
For 2D there is depthConcatenationLayer(), is there a 3D equivalent?
 

请先登录，再回答此问题。

 采纳的回答

MathWorks Support Team
编辑：MathWorks Support Team 2025-2-7

0 个投票

You can use the 'concatenationLayer' by passing the depth dimension as 'Dim' to concatenate along depth. The 'Dim' is 4 for 3D data and 3 for 2D data. For more information, you can access the specific documentation by executing the following command in the MATLAB R2019b command window:
>> web(fullfile(docroot, 'deeplearning/ref/nnet.cnn.layer.concatenationlayer.html'))
Please follow the link below to search for the required information regarding the current release:
https://www.mathworks.com/help/

更多回答（0 个）

类别

在 帮助中心 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