Mitchell Doughty

Have you performed camera calibration of the HoloLens RGB camera that you're using for tracking? If not, check out the code to calibrate the RGB camera [here](https://github.com/qian256/HoloLensCamCalib/tree/c953b85ebc21234c0f2b163e5f0d40257b7bae02). You need to...

Try out this package (https://atom.io/packages/platformio-ide-terminal). You can install through the Atom package manager as **platformio-ide-terminal**.

Hi @Patsufr, sorry for the delayed response. I think this error was caused by the `measurements` vector not being correctly initialized in the code. The change is at line: https://github.com/doughtmw/HoloLensForCV/blob/ea1c94b395065231276afb9498468609c0467d1a/Shared/HoloLensForCV/MediaFrameSourceGroup.cpp#L247...

This sounds like it could be from not adding the ONNX model to your Visual Studio solution and correctly setting the formatting. Make sure to follow the steps in the...

Hi @arsiboo, thanks for your interest in the sample. The easiest thing to do is just delete the old `WSATestCertificate.pfx` files present in the repo which should allow the project...

Hi @Avinash0795 and @NTUZZH, the HL2 build version could be a factor but a more likely issue could be due to incorrect formatting of the ONNX model in Visual Studio....

Hi @Avinash0795, the GPU support for ONNX model inference on the HL2 is a bit strange—I haven't had much success with getting it to work correctly or achieving better performance...

I experienced some similar issues as yourself which ended up being due to the compatibility of Keras, Tensorflow and CoreML installations. Try the following configuration: ``` coremltools==3.2 Keras==2.2.4 tensorflow==1.14.0 ```