I'm getting the following error when trying to run inference using an ONNX model using the Windows.AI.MachineLearning package in a UWP app.
'The parameter is incorrect.
Non-zero status code returned while running Node: StatefulPartitionedCall/model/conv3d_transpose/conv3d_transpose Status Message: Input X must be 4-dimensional. X: {1,256,16,16,8}'
The model is using ONNX opset 9 and was converted from a tensorflow model using tf2onnx versions 1.12.1 and I'm running in VisualStudio 2019. I've had some issues with the Convolution 3D Transpose layer in a few other ML frameworks to run inference so I was wondering if it's possible this layer is not supported by Window.AI.MachineLearning? Or am I running into this because of some other issue?
I've tried using different opsets for the ML model, but 9 seems to be the only one working in my environment. I've gotten a different model working, so I am able to run inference. It seems to be a particular problem with this model (specifically the conv3d_transpose layer).
I've tried looking for what operations are supported, but have only found what ONNX opsets as a whole are supported.
