GeorgeS2019

I will invite the dotnet PM here (if she is interested) to invite more users HERE to join the testing of the new PolyGlot WIP features.

#### [TORCHVISION.OPS](https://github.com/pytorch/vision/tree/main/torchvision/ops) suggestion: Need to approach this **ALSO** from the perspective of Onnx contributed Ops e.g. [**com.microsoft.vision**](https://github.com/microsoft/onnxruntime/issues/13084) ```mermaid flowchart TD image-->|com.microsoft.vision\nops| TorchSharp\nmodel-->|com.microsoft.vision\nops| output\nimage ```

@kaiidams Why there are no Torchaudio.ops? Are they in here? https://github.com/pytorch/audio/tree/main/torchaudio/csrc e.g. com.microsoft.audio ```mermaid flowchart TD audio-->|com.microsoft.audio\nops| TorchSharp\nmodel-->|com.microsoft.audio\nops| output\naudio ```

Most of the Torchtext.ops are here https://github.com/pytorch/text/tree/main/torchtext/csrc com.microsoft.nlp ```mermaid flowchart TD text-->|com.microsoft.nlp\nops| TorchSharp\nmodel-->|com.microsoft.nlp\nops| output\ntext ```

> I try to call the native method from torchvision, torch.ops.torchvision.nms > https://github.com/pytorch/vision/blob/main/torchvision/csrc/ops/nms.cpp > https://github.com/pytorch/vision/blob/main/torchvision/ops/_register_onnx_ops.py For Onnxruntime, here is some preliminary discussion how to register Onnx Ops [WIP [Documentation]: C#...

Instead of loading a native dll, the latest way is to embedded a static library *.lib through *.csproj and compile that into a normal c# dll. More and more of...

The Godot c# library attaches a c++ Shared Library _internal ( or _internal.lib ) 

@xhuan8 An interesting MIT License Visual Programming approach with [pre/post vision processing node(Ops)](https://github.com/fel88/Dendrite) around ONNX FYI: could be interesting and the [example involves TorchScript](https://github.com/fel88/Dendrite/issues/10), however not related to TorchSharp, more...

https://github.com/pytorch/pytorch/issues/13130 As long as the PyTorch community is considering Arm64 an open issue, it will not be VERY VERY trivial for TorchSharp

https://pytorch.org/get-started/locally/ This is where official ARM64 support is needed before TorchSharp (I assume) will remotely consider ARM64