Fix missing image_shape in YOLOv8 prediction_decoder

[takumiohym]

What does this PR do?

Fixed the missing image_shape argument in YOLOv8 prediction_decoder() which leads to a ValueError from bounding_box.convert_format when bounding box format uses relative ones ("REL_...").

The added code corresponds with the prediction_decoder() function of RetinaNet.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue? Please add a link
  to it if that's the case.
• Did you write any new necessary tests?
• If this adds a new model, can you run a few training steps on TPU in Colab to ensure that no XLA incompatible OP are used?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.