How to create layers in CNN using trainNetwork?

How to create layers in CNN using trainNetwork?

Answer 1

[Tejas]

Hello Selva,

To add layers to a Neural Network, the Deep Learning Toolbox offers many built-in functions to assist in this process. Here is a comprehensive list of the available functions for adding layers: https://www.mathworks.com/help/deeplearning/ug/list-of-deep-learning-layers.html.

The size of layers, number of layers, and sequence of layers will vary depending on the type of Convolutional Neural Network (CNN) based architecture you want to build. For a better understanding of CNN architecture, refer to this documentation: https://www.mathworks.com/discovery/convolutional-neural-network.html.

MATLAB documentation recommends using the 'trainnet' function over the 'trainNetwork' function. Below is a simple example that shows how to create and train a simple Convolutional Neural Network (CNN) for deep learning classification using the 'trainnet' function: https://www.mathworks.com/help/deeplearning/ug/create-simple-deep-learning-network-for-classification.html.