Data augmentation_CNN

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%.

[Mohammad Sami]

Is the accuracy you mentioned, training accuracy. Training accuracy is not the best metric to measure the performance of your model. You should see either validation and test accuracy.

If the test accuracy is actually lower, you can also try and reduce the magnitude of augmentation you are doing. Example if you are rotating by 10 degrees, you can change it to 5 degrees e.t.c.

Answer 1

[Srivardhan Gadila]

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.