onnx-tensorflow VS com-rs

How to solve this? I found below github issue which they solved i think, but im not to able to find the solution https://github.com/onnx/onnx-tensorflow/pull/1022

Okay, maybe it worked some years ago. The issue currently is that the trainable weights get lost...which is by design https://github.com/onnx/onnx-tensorflow/issues/1002

TLDR: I'm using onnx-tf to convert an onnx model to tensorflow. During the conversion I lose important information such as inputs, outputs and the names of operators. Please read on if you have experience with this library or you've experienced similar issues. :)

We had a few small issues with ONNX. Export worked but when running with e.g. tflite stumbled for example across this https://github.com/onnx/onnx-tensorflow/issues/853 Also the support for sampling from distributions is generally still pretty weak, but we were able to work around that.

https://pytorch.org/tutorials/advanced/super\_resolution\_with\_onnxruntime.html https://github.com/onnx/onnx-tensorflow

https://github.com/onnx/onnx-tensorflow Haven’t tried it, let me know if it works.

regarding COM - check https://github.com/microsoft/com-rs

I'm building a crate to show a progress indicator in the icon of the taskbar of the app using it, I already began the implementation for Linux, but I want to support Windows also, for that I need to access ITaskBarList3, I don't knew anything about COM interfaces before find this. The point is that I'm pretty confused about what to do. They said I would implement the functions, but I want to call them, and this thing com-rs, I'm not sure if I would redefine the interface that is already defined in winapi.