dividing groundtruth into training, testing and validation

Hi, I have 800 images and labels in data set and I wanted to divide it into test, train and validation set.
I am using following code:
load gTruth % load gTruth file of training data
[imds,pxds] = pixelLabelTrainingData(gTruth);
imdsTrain=imds(81:720);
pxdsTrain=pxds(81:720);
imdsTest=imds(1:80);
pxdsTest=pxds(1:80);
imdsVal=imds(721:800);
pxdsVal=pxds(721:800);
its not working, any possible solution....?

回答 (1 件)

yanqi liu
yanqi liu 2021 年 2 月 5 日

0 投票

[imds60, imds10, imds30] = splitEachLabel(imds,0.6,0.1)

2 件のコメント

Raza Ali
Raza Ali 2021 年 2 月 5 日
While using this command, I am getting following error:
Error using matlab.io.datastore.ImageDatastore/splitEachLabel (line 211)
splitEachLabel requires non-empty Labels property.
yanqi liu
yanqi liu 2021 年 2 月 5 日
can you upload the demo data, and we can make some test case.

サインインしてコメントする。

カテゴリ

ヘルプ センター および File ExchangeDeep Learning Toolbox についてさらに検索

質問済み:

2021 年 2 月 5 日

コメント済み:

2021 年 2 月 5 日

Community Treasure Hunt

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

Start Hunting!

Translated by