Train Stacked Auto encoders for potholes datasets classification

1 次查看（过去 30 天）
Srinidhi Gorityala
Srinidhi Gorityala 2020-6-18
Helo, iam working on pothole dataset image classification using train stacked auto encoders. Iam gettin few errors and iam unable to load the dataset . Could any one please help me in solving this error.
clc;
clear all;
close all;
myTrainingFolder = 'C:\Users\Admin\Desktop\Major Project\dataset';
imds = imageDatastore(myTrainingFolder,'IncludeSubfolders', true, 'LabelSource', 'foldernames');
labelCount = countEachLabel(imds);
numClasses = height(labelCount);
numImagesTraining = numel(imds.Files);
%% Create training and validation sets
[imdsTrainingSet, imdsValidationSet] = splitEachLabel(imds,0.7,'randomized');
rng('default');
hiddenSize1 = 100;
autoenc1 = trainAutoencoder(imdsTrainingSet,hiddenSize1, ...
'MaxEpochs',400, ...
'L2WeightRegularization',0.004, ...
'SparsityRegularization',4, ...
'SparsityProportion',0.15, ...
'ScaleData', false);
view(autoenc1);
figure()
plotWeights(autoenc1);
ERROR:
Error in Autoencoder.train (line 510)
[X,visualizationDimensions, trainedOnImages] = iConvertToDouble(X);
Error in trainAutoencoder (line 109)
autoenc = Autoencoder.train(X, autonet, paramsStruct.UseGPU);
Error in encoder (line 15)
autoenc1 = trainAutoencoder(myTrainingFolder,hiddenSize1, ...

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Pattern Recognition and Classification 的更多信息

标签

产品


版本

R2019b

Community Treasure Hunt

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

Start Hunting!

Translated by