How to solve Unable to read file: 'E:\TIME-IQ\128QAM\frame_snr30iq_128QAM_100.mat'?

1 次查看（过去 30 天）

john karli 2021-11-8

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1581219-how-to-solve-unable-to-read-file-e-time-iq-128qam-frame_snr30iq_128qam_100-mat

I have dataset in .mat file and shape of dataset is [2,1280,2]. I have change the inpu layer of the model by using the deepNetworkDesigner app of matlab. All code works good but when i run below command i got the following error.

net = trainNetwork(imdsTrain,lgraph,options);

error

Error using trainNetwork (line 184)
Unable to read file: 'E:\TIME-IQ\128QAM\frame_snr30iq_128QAM_100.mat'.
Caused by:
    Error using matlab.io.datastore.ImageDatastore/read (line 77)
    Unable to read file: 'E:\TIME-IQ\128QAM\frame_snr30iq_128QAM_100.mat'.
        Error using matlab.io.datastore.exceptions.decorateCustomFunctionError>generateReadFcnError (line 103)
        Error using ReadFcn @readDatastoreImage for file:
            E:\TIME-IQ\128QAM\frame_snr30iq_128QAM_100.mat
        Error using imread>get_format_info (line 545)
        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);

full code

imds = imageDatastore('E:\TIME-IQ\', ...
    'IncludeSubfolders',true, 'FileExtensions','.mat',...
    'LabelSource','foldernames');
[imdsTrain,imdsValidation] = splitEachLabel(imds,0.7,'randomized');%%
net = lgraph_2;
net(1)
inputSize = lgraph_2.Layers(1).InputSize;
[learnableLayer,classLayer] = findLayersToReplace(lgraph_2);
[learnableLayer,classLayer] 
numClasses = numel(categories(imdsTrain.Labels));
if isa(learnableLayer,'nnet.cnn.layer.FullyConnectedLayer')
    newLearnableLayer = fullyConnectedLayer(numClasses, ...
        'Name','new_fc', ...
        'WeightLearnRateFactor',10, ...
        'BiasLearnRateFactor',10);
    
elseif isa(learnableLayer,'nnet.cnn.layer.Convolution2DLayer')
    newLearnableLayer = convolution2dLayer(1,numClasses, ...
        'Name','new_conv', ...
        'WeightLearnRateFactor',10, ...
        'BiasLearnRateFactor',10);
end
lgraph_2 = replaceLayer(lgraph_2,learnableLayer.Name,newLearnableLayer);
newClassLayer = classificationLayer('Name','new_classoutput');
lgraph = replaceLayer(lgraph_2,classLayer.Name,newClassLayer);
miniBatchSize = 128;
valFrequency = floor(numel(imdsTrain.Files)/miniBatchSize);
checkpointPath = pwd;
options = trainingOptions('sgdm', ...
    'MiniBatchSize',miniBatchSize, ...
    'MaxEpochs',100, ...
    'InitialLearnRate',1e-3, ...
    'Shuffle','every-epoch', ...
    'ValidationData',imdsValidation, ...
    'ValidationFrequency',valFrequency, ...
    'Verbose',false, ...
    'Plots','training-progress', ...
    'CheckpointPath',checkpointPath);
net = trainNetwork(imdsTrain,lgraph,options); 