Hello everyone,
Since SNPE2.x is now supporting conv3d layers, I have built a simple model to test the speed of the procedure.
However, SNPE keeps on givng an error saying that the output has an incorrect rank 5 (on my project and also on snpe-net-run).
Since conv3d is a 3d operation, it requires 5d (batch, height, width, depth, channel).
How do i utilize conv3d?
Please help.
Thank you
Dear developer,
I checked the snpe documentation, it says 'SNPE currently supports 4D input data, where the first dimension is batch.'
BR.
Yunxiang
Hello,
So currenlty, it is not possible to run conv3d since SNPE supports 4D input data even though the operation itself is supported.
Thank you