Install OnxxRuntime on Windows

Video Version: https://youtu.be/Tiq_vea5Eqg

If youโ€™re running into this error when using OnnxRuntime in Python, itโ€™s because youโ€™re missing a Cuda dependency or something,

ImportError: cannot import name 'get_all_providers' from 'onnxruntime.capi._pybind_state

The OnnxRuntime doesnโ€™t make it super explicit, but to run OnnxRuntime on the GPU you need to have already installed the Cuda Toolkit and the CuDNN library.

First check your machine and make sure you have a Cuda Enabled Card. If you have a pretty recent NVIDIA card you are probably good, but go to the NVIDIA website and check the compatibility tables and make sure if you havenโ€™t already. If you ainโ€™t got the right hardware, all the tinkering and installing isnโ€™t gonna make it work. Make sure.

The Windows Device Manager can be opened via the following steps:
Open a run window from the Start Menu
Run:

control /name Microsoft.DeviceManager

Check under display adaptors to see your card

First install the Cuda Toolkit:

It opens a Window that looks like this:

--

--