AM69A: Is it able to transpose data using TIDL_ShuffleChannelLayer?

Hi,

In my model I would like to transpose the output after a convolutional layer. from shape of BCHW and I would like the transpose it as BWHC.

However, the TIDL is not supporting the Transpose op, I found that it has a TIDL_ShuffleChannelLayer, described as Reshape + Transpose + Reshape ops in ONNX.

I tried to implement TIDL_ShuffleChannelLayer using reshape + transpose + reshape in my model, but I failed to generate this layer and get following results after model complilaion:

Could you please explain what should be done to exploit the TIDL_ShuffleChannelLayer or suggest another way to perform a Transpose op in TIDL.

By the way, We will be using TIDL-RT to run imported model, so might not be considering delegate layers to ARM.

Thanks!