C++ and onnx

## 🚀 Feature
A clear and concise description of the feature proposal.
For easying the distribution of my programs with detectron2 on windows platforms I want to can launch predictions of detectron2 with C++ DLLs and onnx converted models

## Motivation & Examples

Tell us why the feature is useful.
onnx speeds up prediction and C++ Dlls are more distributables than entire Python environments

Describe what the feature would look like, if it is implemented.
Best demonstrated using **code examples** in addition to words.
a complete example of code source with detectron2 all models compatible examples sources in Visual Studio C++

## Note

We only consider adding new features if they are relevant to many users.

If you request implementation of research papers -- we only consider papers that have enough significance and prevalance in the object detection field.

We do not take requests for most projects in the `projects/` directory, because they are research code release that is mainly for other researchers to reproduce results.

"Make X faster/accurate" is not a valid feature request. "Implement a concrete feature that can make X faster/accurate" can be a valid feature request.

Instead of adding features inside detectron2,
you can implement many features by [extending detectron2](https://detectron2.readthedocs.io/tutorials/extend.html).
The [projects/](https://github.com/facebookresearch/detectron2/tree/main/projects/) directory contains many of such examples.

No implementation files, tests, or entry points are named. Start by determining the scope of Windows C++ DLL and ONNX model support requested for Detectron2, then identify compatible models and the Visual Studio example structure; done would require a complete working example covering the requested Detectron2 models.

Written by the indexing model from the issue text.