CreateML Object Detection Image Augmentation

If you use the augmentation options in Create ML when training you're model, everything is handled automatically for you. That is, for each of your training images additional augmented versions (flipped, rotated, blurred, etc.) will be generated in memory and included in the training iterations. You do not need to prepare specific augmented versions of each image. The important thing to consider, however, is the general diversity of your image set. Depending on the specific training goal, you may need to consider including images that are captured in different lighting and with a wide variety of backgrounds as those are things that augmentation can't handle for you automatically. Hope that helps.

The one posted answer doesn't really answer the original question. The issue is that there are not augmentation options available when creating an object detection model in Create ML (only when creating an image classifier model). I did some tests and it seems that Create ML does not do any augmentation by itself. That means we do need to provide our own augmentations.

But I'd love to know why the augmentation options are not present for the object detection models...

I think one possible explanation of why in CreateML is not possible to have an augmentation option in object detection model, is the fact that, under some circumstances, you would need to re-elaborate bounding boxes (in image classification you don't have bounding boxes locating objects). In some cases like color/saturation changes there should not be any re-elaboration of boxes and on other image transformations (e.g. flip) it could be very simple and not cpu intensive. But for streching, cropping and so on, it could rather difficult to re-annotate correctly the objects and may be cpu expensive... This is the answer I gave to myself... but I think, at the same time, I would like to have this option... because I'm doing Image augmentation by my self....and it's annoying!