Error forming mini-batch for network input

2026 3 1
1 个回答
更新时间：2026 3 4
92 次查看（30 天）

0 个投票

i want to train a cnn with a folder of images with the size [h w c], the imageInputLayerargument is the same size of the images (h w c), but when training the network matlab says:
Error using trainnet (line 46)
Error forming mini-batch for network input "imageinput". Data interpreted with format "SSCB". To specify a
different format, use the InputDataFormats option.
Caused by:
Dimensions of arrays being concatenated are not consistent.

2 个评论
显示 无 隐藏 无

Matt J
Matt J 2026-3-1，23:49
编辑：Matt J 2026-3-1，23:50
We c have no way of knowing what you did. Please attach materials needed to reproduce it.
Walid
Walid 2026-3-2，0:18
Thanks for the replay, this is my code for multiclass (3 classes) classification using CNN based on image files stored in three subfolders in the main folder: data.:
clear all; close all; clc
% Define the path to your main data folder
dataFolder = 'C:\data';
% Create an image datastore
imds = imageDatastore(dataFolder, ...
'IncludeSubfolders', true, ...
'LabelSource', 'foldernames');
% View the class names and the number of images per class
%imds=aug_imds;
labelCount = countEachLabel(imds);
disp(labelCount);
% Split the datastore into training and validation sets (e.g., 70% for training, 30% for validation)
[imdsTrain, imdsValidation] = splitEachLabel(imds, 0.7, 'randomized');
inputSize = [570 714 3];
augimdsT = augmentedImageDatastore(inputSize,imdsTrain,'ColorPreprocessing','rgb2gray');
augimdsV = augmentedImageDatastore(inputSize,imdsValidation,'ColorPreprocessing','rgb2gray');
numClasses = 3;
layers = [
imageInputLayer(inputSize)
convolution2dLayer(5,5)
batchNormalizationLayer
reluLayer
fullyConnectedLayer(numClasses)
softmaxLayer];
%
options = trainingOptions("sgdm", ...
MaxEpochs=4, ...
ValidationData=imdsValidation, ...
ValidationFrequency=30, ...
Plots="training-progress", ...
Metrics="accuracy", ...
Verbose=false);
% train
net = trainnet(augimdsT,layers,"crossentropy",options);
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
I receive the following message:
Error forming validation data mini-batch.
Caused by:
Error forming mini-batch for network input "imageinput". Data interpreted with format "SSCB". To specify
a different format, use the InputDataFormats option.
Dimensions of arrays being concatenated are not consistent.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Matt J
Matt J 2026-3-2，3:23

2 个投票

This is not enough to reproduce the error. You haven't provided input images. My guess, however, is that there are some files in C:\data that are not 570x714x3.

5 个评论
显示 3更早的评论 隐藏 3更早的评论

Walid
Walid 2026-3-2，11:40
there is some image with different size, so i used augmentedImageDatastore function to resize them to a unique size !
Matt J
Matt J 2026-3-2，16:25
编辑：Matt J 2026-3-2，16:47
You need,
inputSize = [570 714 1];
and
ValidationData=augimdsV,...
Matt J
Matt J 2026-3-4，1:52
编辑：Matt J 2026-3-4，1:55
your link goes to new code. However, your original code, as presented in your question, should be working now with the changes I propose above. If the code is working for you as well, please Accept-click the answer to indicate that the question is resolved.
As for the new code, it is pretty clear why it doesn't work. You removed the resizing done by the augmentedDatastores so, per our discussion above, it is not going to be possible to concatenate them.
Walid
Walid 2026-3-4，4:48
the original code does'nt work ! the same error !
Matt J
Matt J 2026-3-4，10:46
编辑：Matt J 2026-3-4，10:46
It works for me. Did you incorporate my fixes?

请先登录，再进行评论。

类别

在 帮助中心 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

产品

版本

R2024a

标签

提问:

Walid
Walid
2026-3-1，22:56

编辑：

Matt J
Matt J
2026-3-4，10:46

Community Treasure Hunt

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

Start Hunting!

Translated by