I have 2 classes for my image classification problem, say class A and class B, and I am using tensorflow and keras for the same. One of them have around 5K images while the other have just around 2K images. Is it possible to increase the number of images in class B to get them near to 5K using data augmentation? I have looked for more images to include under class B, but all I could find were already among the 2k images.

I only see articles which say that data augmentation is done on the dataset, but I need it to be done on one of the classes alone, without affecting the other class in the same dataset

I am using image_dataset_from_directory for loading the dataset. If there are any alternatives for loading the data which aids in the above mentioned situation, please suggest me.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.