How do I create training data set for deep learning?

2 次查看（过去 30 天）
Casey
Casey 2022-12-22
回答： Aastha 2025-5-15
I am trying to create a convolutional neural network from a unsupervised learning.
The training data set I want to create contains 10 examples (x_i, y_i) , i=1,2,...10 .
the x_i and y__i are both certain types of images.
So when using the convolutional neural network, I would like to input x_i and train the output as y_i.
Is it possible to create this training data set on matlab, and if so, how can I do that?
  2 个评论
KSSV
KSSV 2022-12-22
What exactly are the images? What do you want to train? What is input and what you are targetting?
Casey
Casey 2022-12-22
编辑：Casey 2022-12-22
@KSSV Thank you for your comment.
My images are propagated light beam wavefront's intensity distribution(x) and phase distribution(y), which involves the atmospheric turbulence.
So the input would be the intensity distribution, and through the training of CNN, I would like to predict its phase distribution.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Aastha
Aastha 2025-5-15
Hi @Casey,
To create a training dataset for an image-to-image machine learning task using a CNN. You can use the "imageDatastore" function in MATLAB to organize your data into a training set. Kindly refer to the steps mentioned below:
1. Define two image datastores using the "imageDatastore" function in MATLAB; one for the input images and one for the output (target) images. Then, combine them into a single paired datastore using the combine function:
% Create image datastores
inputDS = imageDatastore(inputFolderPath, ...
'IncludeSubfolders', true, ...
'LabelSource', 'none');
outputDS = imageDatastore(outputFolderPath, ...
'IncludeSubfolders', true, ...
'LabelSource', 'none');
% Combine input and output into a single paired datastore
combinedDS = combine(inputDS, outputDS);
2. You can then use the "trainnetwork" function in MATLAB to train your CNN model. For more information on the training procedure and available parameters, refer to the MathWorks documentation of the "trainnetwork" function:
https://www.mathworks.com/help/releases/R2022a/deeplearning/ref/trainnetwork.html
For additional details on using image datastores, you can refer to the MathWorks documentation of "imageDatastore" function:
https://www.mathworks.com/help/releases/R2022a/deeplearning/ref/imageDatastore.html
Hope this is helpful!

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品


版本

R2022a

Community Treasure Hunt

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

Start Hunting!

Translated by