How to develop a mini-batch datastore of images?
1 次查看(过去 30 天)
显示 更早的评论
Hello,
I would like to see an example of defining a custom mini-batch datastore that uses images (for the purpose of deep learning). Labels of images are subfolder names.
Thanks!
0 个评论
回答(1 个)
yanqi liu
2022-3-3
yes,sir,may be consider view 《Create Simple Deep Learning Network for Classification》
the data with subfoler can get by
unzip('MerchData.zip');
imds = imageDatastore('MerchData', ...
'IncludeSubfolders',true, ...
'LabelSource','foldernames');
[imdsTrain,imdsValidation] = splitEachLabel(imds,0.7);
and set trainingOptions by MiniBatchSize can make mini-batch parameter
0 个评论
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!