-
Notifications
You must be signed in to change notification settings - Fork 2
New issue
Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? # to your account
Provide Dagre unit tests and onnx model used #1
Comments
There is a .NET graphlayout methods used here to layout deep learning model. Perhaps this could be incorporated into your project? Seq2Seq transformer model layout |
Dagre layout is not finished yet. I'm working on it right now. Hope it will be ready soon (maybe in 3-7 days) |
@fel88 U are attempting to port a Javascript Dagre graph layout engine for .NET community. This is not trivial and thank you for your contribution. Also thank you for your vision that the .NET community needs an ONNX viewer and editor. Great job!!! FYI: We work hard to persuade the TorchSharp team to make it easy for .NET community to port python pytorch code to c#. Likewise, I urge you to consider that (eventually) in your Dagre implementation (make it a reusable standalone library). This will get more .NET users to use your Dagre implementation and speed up the quality of the implementation. Reference |
I haven't finished porting completely yet, but your model (squeezenet1.0-9) should work now. |
@fel88 Impressive |
and the discussion associated with it |
I tried using squeezenet.onnx
The Dagre layout crashes!.
Need unit test project to sort out the Dagre layout. Keep it up!
Table layout of squeezenet.onnx
The text was updated successfully, but these errors were encountered: