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
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
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