How to reshape (digitTrain4DArrayData) inbuilt number dataset provided in MATLAB ?

Question

Sudheer Dunna 2020-4-27

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/521050-how-to-reshape-digittrain4darraydata-inbuilt-number-dataset-provided-in-matlab

评论： debojit sharma 2023-6-9

digitTrain4DArrayData data set is having dimension of 28 * 28 * 1 * 5000 (5000 samples) . How can we reshape it into 784 * 5000, to train it using neural network pattern recognizer in matlab for ANN.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Srivardhan Gadila 2020-4-29

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/521050-how-to-reshape-digittrain4darraydata-inbuilt-number-dataset-provided-in-matlab#answer_429141

编辑：Srivardhan Gadila 2020-4-29

在 MATLAB Online 中打开

[XTrain,YTrain] = digitTrain4DArrayData;

Use the reshape function as follows:

reshapedXTrain = reshape(XTrain,784,5000);

3 个评论
显示 1更早的评论隐藏 1更早的评论

Sudheer Dunna 2020-4-30

Sir, do you have any idea of training digitTrain4DArrayData (Inbuilt matlab digit data) using Naive bayesian (fitcnb).

inputNaive=fitcnb(inputs,targets)

inputs ( 60000*784) double

targets (6000*1) (tried with double and categorial type)

While training it is showing some error like : A normal distribution cannot be fir for the combination of class 1 and predictor X1. The data has zero variance.

debojit sharma 2023-6-9

With reference to this link https://in.mathworks.com/help/deeplearning/ug/train-stacked-autoencoders-for-image-classification.html

I am trying to implement stacked autoencoder for image classification. But I am not able to understand how can I prepare my dataset to fed into a autoencoder. As it is being said in this link that we need to reshape the training images into a matrix, how can it be done? Please provide a sample code.

请先登录，再进行评论。