Data Augmentation in Tensorflow Object Detection A

Question

In config file, we are given the default Augmentation option as shown below.

data_augmentation_options {
    random_horizontal_flip {
    }
  }

But I wondered how it works with the bounding box(ground truth box) values given with the training images. so I looked at preprocessor.py, random_horizontal_flip() takes 'boxes=None' parameter. Since no argument is given in the config file, I assume this flip does not account bounding box when it does the random horizontal flip.

My question is what arguments do I use to add the value of bounding box in the config file in the code snippet section shown above.

Answer 1

The boxes will get flipped too. If you look down in the preprocessor file, you'll notice a map that defines what inputs of the tensor dictionary will get passed into the preprocessing function. The groundtruth boxes are passed into random_horizontal_flip.