Hello everyone,
I am trying to run conv3d unet architecture on htp however, decoder part does not work on snpe due to conv3dTranspose.
Thus, I have tried to mimic conv3dtranspose by using operation similar to pixelshuffle (by increasing channel and reshape to increase width, height, depth).
However, this also gives error about the rank. It seems like reshape of 5d tensor not supported on snpe.
Is there way to use conv3d transpose or reshape 5d tensor?
thank you
Dear developer,
What's the SNPE version you used?
BR.
Wei
I am currently using SNPE2.12 version.
I am testing conv3d on AI Engine Direct 2.12 version as well.
However, 5d tensor reshape does not work on both snpe and qnn.
Please help.
Thank you