Having problem in giving .mat files as input to CNN for classification task.
Show older comments
I want to give .mat files each of size 27*27*100 as input to my CNN for classification task. When i am running my program, its giving following error:-
------------------------------------
Error using trainNetwork (line 150)
Unable to read file: 'D:\Matlab_Files\Convolution_Fusion_Initial\FusionFolder1\1\I1.mat'.
Error in NetworkAfterFusion2 (line 88)
netTransfer = trainNetwork(allImages,layers,options);
Caused by: Error using matlab.io.datastore.ImageDatastore/read (line 74)
Unable to read file: 'D:\Matlab_Files\Convolution_Fusion_Initial\FusionFolder1\1\I1.mat'.
Error using matlab.io.datastore.splitreader.WholeFileCustomReadSplitReader>iErrorOnReadFcn
(line 106)
Error using ReadFcn @readDatastoreImage function handle for file
D:\Matlab_Files\Convolution_Fusion_Initial\FusionFolder1\1\I1.mat.
Error using imread>get_format_info (line 543)
Unable to determine the file format.
Error in imread (line 391)
fmt_s = get_format_info(fullname);
Error in readDatastoreImage (line 12)
data = imread(filename);
----------------------------------------------------
The function trainNetwork is not able to accept the .mat format even if i am giving 'FileExtension' as '.mat' at the time of creating image datastore object.
allImages = imageDatastore('D:\Matlab_Files\Convolution_Fusion_Initial\FusionFolder1', 'IncludeSubfolders', true,'LabelSource', 'foldernames','FileExtensions','.mat');
Accepted Answer
More Answers (1)
virgile
on 3 Jan 2023
0 votes
Hello, I have a similar project and i don't know how to start. Could you plz post your notebook, It would really help me.
Categories
Find more on Preprocess Data for Deep Neural Networks in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!