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

10 次查看（过去 30 天）
Sudheer Dunna
Sudheer Dunna 2020-4-27
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.

请先登录，再回答此问题。

采纳的回答

Srivardhan Gadila
Srivardhan Gadila 2020-4-29
编辑：Srivardhan Gadila 2020-4-29
[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
Sudheer Dunna
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
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。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Naive Bayes 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