Mosaic Augmentation for Object Detection about keras-cv HOT 7 CLOSED

This is the old long story about where to collect reusable CV components.
I suppose that we could port these from the model garden to keras-cv.

from keras-cv.

Think this looks like another good preprocessing layer.

I suppose that we could port these from the model garden to keras-cv.

yeah I agree, it's beginning to look like we are probably going to have a lot of code duplication between keras-cv and model garden. In my opinion this is to be expected - We do not want keras-cv to depend on model garden, but some of the functionality is the same.

@bhack thank you for continuing to point out the existing model garden implementations. They're extremely helpful to me.

from keras-cv.

Good question, probably corners? This can have its own issue to discuss. I'll re-open!

from keras-cv.

I think we have this already in the official model garden:
https://github.com/tensorflow/models/blob/master/official/vision/beta/projects/yolo/ops/preprocessing_ops.py#L236
https://github.com/tensorflow/models/blob/master/official/vision/beta/projects/yolo/ops/mosaic.py

from keras-cv.

Oh, I see. Does it mean that we should use these from the tensorflow/models garden or all those relevant operations will be moved here to strengthen the high-level api? Also why the mosaic.py file is under /yolo/ops/ directory? Shouldn't it be more general for all object detection models?

from keras-cv.

@bhack @LukeWood @qlzh727
What should be the default target format (BoxMode) for object detection tasks? Will it be pascal format or coco format? In the object detection preprocessing layer, is it expected that the layer should support both formats as input?

from keras-cv.

@LukeWood could you please see the above query? I would most likely send a PR for mosaic if possible.

from keras-cv.