Add fuse for RepConv

[KangGrandesty]

Description

Summary

Add fuse function for RepConv

Motivation and Context

Fuse the multiple conv and bn layer, give me less latency and smaller model size

Dependencies

None

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

An unit test function is added in official/projects/yolo/modeling/layers/nn_blocks_test.RepConvTest, named test_fuse_and_unfuse_result.

The test function checks the different of the two output values.

Test Configuration:

OS: ubuntu 16
Env：Python=3.10 TensorFlow=2.12.0

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.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.