add CIOU/DIOU/GIOU losses (from efficientdet library)

[johnpjust]

Description

📝 Please include a summary of the change.

• Please also include relevant motivation and context.
• List any dependencies that are required for this change.

Type of change

For a new feature or function, please create an issue first to discuss it
with us before submitting a pull request.

Note: Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• Documentation update
• TensorFlow 2 migration
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• A new research paper code implementation
• Other (Specify)

Tests

📝 Please describe the tests that you ran to verify your changes.

• Provide instructions so we can reproduce.
• Please also list any relevant details for your test configuration.

Test Configuration:

Checklist

• I have signed the Contributor License Agreement.
• I have read guidelines for pull request.
• My code follows the coding guidelines.
• I have performed a self code review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added tests that prove my fix is effective or that my feature works.

[johnpjust]

Note -- the autoaugment changes were upgrades for TF2 compatibility. They have also been verified (also taken from automl efficientdet repository), but not sure why they got added to this PR. I tried to separate them into a different pull request but no luck....

[johnpjust]

Also a note for a TODO for down the road....when using the autoaugment policy with augmix=True (default is False), the bbox returned on the transformations is not correct when image gets blended with rotates and translates. I didn't modify the code from the automl repository so its a carryover from there.

[bhack]

tensorflow/addons#914 (comment)

[bhack]

I don't know if these could go in the new folder https://github.com/tensorflow/models/tree/master/official/vision/keras_cv/losses /cc @tanzhenyu

[b04505009]

Will this PR be checked? I think ciou is a great feature to add