Add HGNetV2 to KerasHub

[harshaljanjani]

Description of the Change

It is an end-to-end image classification model which had to be implemented on KerasHub as a building block towards supporting D-FINE. A number of D-FINE's presets depend on derivatives of the HGNetV2Backbone, and this model sets any required infrastructure in place to serve them. Its addition unlocks and allows follow-on integration effort toward D-FINE on KerasHub. Concurrently, I am working on exploring the integration paradigm for D-FINE with HGNetV2 layers.

Closes the first half of #2271

Reference

Please read Page 15/18, Section A.1.1 of the D-FINE paper, and the HF config files to verify this point. The "backbone": null argument in the HuggingFace configuration translates to an HGNetV2 backbone.

Colab Notebook

Usage and Numerics Matching Colab

Checklist

• I have added all the necessary unit tests for my change.
• I have verified that my change does not break existing code and works with all backends (TensorFlow, JAX, and PyTorch).
• My PR is based on the latest changes of the main branch (if unsure, rebase the code).
• I have followed the Keras Hub Model contribution guidelines in making these changes.
• I have followed the Keras Hub API design guidelines in making these changes.
• I have signed the Contributor License Agreement.

[harshaljanjani]

A few nits might come up as I start using the HGNetV2Backbone within the D-FINE implementation, but for now, it looks solid, complete, and congruous with KH's integration expectations. You are welcome to take a look. I'll be keeping it as a draft PR until I get DFineBackbone integrated.
As for D-FINE, the layers are ready, and the backbone and task model are standalone written in Keras. What's left is to integrate them into the infra.