The training and validation accuracy stuck in the value of 74% in Resnet 50

Question

Moetez 2024-4-27

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2112396-the-training-and-validation-accuracy-stuck-in-the-value-of-74-in-resnet-50

回答： Shantanu Dixit 2024-8-5

I'm new to the world of Deep Learning and I'm attempting to classify sequences of proteins into two classes using scalogram images [class1=192, class2=171] I've implemented Transfer Learning with ResNet 50 as my model architecture.the accuracy in The training and validation stuck in 73-78 %.Anyone can explain to me what happen because I confused

The sample data : [class1]:

The sample data : [class2]:

as you see the pictures in both groups look very similar

The code:

[imdsTrain,imdsVal]= splitEachLabel(imds,0.7,"Randomized");

aug= imageDataAugmenter("RandYReflection",true,"RandXReflection",true)

augTrain = augmentedImageDatastore([224,224],imdsTrain,"DataAugmentation",aug);

augVal = augmentedImageDatastore([224,224],imdsVal);

options =trainingOptions("sgdm",...

"InitialLearnRate",3e-4,...

"MaxEpochs",100,...

"Plots","training-progress",...

"Shuffle","every-epoch",...

"ValidationData",augVal,...

"ValidationFrequency",1,...

"MiniBatchSize",128,...

"L2Regularization",1e-4)

net = resnet50;

lgraph = layerGraph(net);

fclayer = lgraph.Layers(end-2);

newFclayer = fullyConnectedLayer(2,"Name","NewFc",'BiasL2Factor',10,"WeightL2Factor",10);

lgraph = replaceLayer(lgraph,fclayer.Name,newFclayer);

classlayer = lgraph.Layers(end);

newClassLayer = classificationLayer("Name","newClassLayer");

lgraph= replaceLayer(lgraph,classlayer.Name,newClassLayer);

net = trainNetwork(augTrain,lgraph,options);

The Training process:

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Shantanu Dixit 2024-8-5

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2112396-the-training-and-validation-accuracy-stuck-in-the-value-of-74-in-resnet-50#answer_1494691

Hi Moetez,

It seems that the model’s accuracy is stuck in a particular range. Although there’s no definitive answer to pinpoint the issue, the following could be potential workarounds or issues to consider:

Data Similarity: Since you mentioned that data from both samples are quite similar, this can make it difficult for the model to learn the underlying patterns from the data.
Small Data Size: Due to the small data size, you can try augmentation using ‘imageDataAugmenter’ to generate more variety.
Learning Rate: Instead of using a fixed learning rate throughout the training process, experiment with schedulers with different drop factors using ‘trainingOptions’.
Varying and Using Different Regularization Techniques: Vary the L2 regularization parameter and add dropout using ‘dropoutLayer’.