I have a large set of images with 6 classes where the class distribution is imbalanced. Looked into balancing it by adding weight for each class but as I read in tensorflow docs the weight property is not taken into account i.e. any attribute beyond the set in use is simply ignored by TF2.
Since I am not using a custom written loop and would like to use training scripts present in TF2 models repository, I cant find any update info.
I already looked into the topic extensively on the web and found either outdated info or systems for integrating class weights into the training loop. Ideally I would like to add them either through pipeline.config or through the TF record formation process.
Can you help ?