MATLAB: Data augmentation_CNN

https://in.mathworks.com/matlabcentral/fileexchange/68728-image-classification-using-data-augmentation

Iam working on a dataset of total 300 images including 150 pothole images and remaining 150 non-pothole images. Using Data Augmentation method i have classified the images but the accuracy is decreasing. Could anyone please help me in understanding this?

Before data agumentation the accuracy is 96% but after performing the data augmentation the accuracy is decreased to 87%.

Best Answer

As @Mohammad Sami already mentioned, evaluating the performance of the neural network based on training accuracy/loss only is not a good idea.

If the accuracy you mentioned is the training accuracy then it may happened that the network simply memorized the training data, rather than learning general features that enable the network to make accurate predictions for new data. To check if your network is overfitting, compare the training loss and accuracy to the corresponding validation metrics. If the training loss is significantly lower than the validation loss, or the training accuracy is significantly higher than the validation accuracy, then your network is overfitting.

Refer to Deep Learning Tips and Tricks, Set Up Parameters and Train Convolutional Neural Network & Preprocess Images for Deep Learning.

Related Solutions

MATLAB: How to get percentage of training loss

While using the trainNetwork function, mention the info output argumetn along with the net as follows:

[net,info] = trainNetwork(___)

Training information, returned as a structure info , where each field is a scalar or a numeric vector with one element per training iteration.

For classification problems, info contains the following fields:

TrainingLoss — Loss function values
TrainingAccuracy — Training accuracies
ValidationLoss — Loss function values
ValidationAccuracy — Validation accuracies
BaseLearnRate — Learning rates
FinalValidationLoss — Final validation loss
FinalValidationAccuracy — Final validation accuracy

For regression problems, info contains the following fields:

TrainingLoss — Loss function values
TrainingRMSE — Training RMSE values
ValidationLoss — Loss function values
ValidationRMSE — Validation RMSE values
BaseLearnRate — Learning rates
FinalValidationLoss — Final validation loss
FinalValidationRMSE — Final validation RMSE

Refer to documentation of trainNetwork.

MATLAB: Pretrained Neural network ALEX-NET training process.

I think the model is not overfitting. The validation loss normally decreases during the initial phase of training, as does the training loss. However, when the network begins to overfit the data, the loss on the validation set typically begins to rise and clearly there is not much difference between the training loss and validation loss. You can refer to Improve Shallow Neural Network Generalization and Avoid Overfitting for more understanding of Overfitting and steps to avoid overfitting.

The Validation accuracy can be higher than the training (mini-batch) accuracy, one possible situtation is when the network has layers that behave differently during prediction than during training for example, dropout layers. It also depends on how the training & validation data are split.

Best Answer

Related Solutions

MATLAB: How to get percentage of training loss

MATLAB: Pretrained Neural network ALEX-NET training process.

Related Question