Hello,
I have a custom layer MatrixMul that internally uses tf.matmul.
It seems that SNPE supports conversion of tf.matmul operation in Dense layer (fully connected) but not in the custom layer. What is the right way to map/model matrix mulplication operation in tensorflow for successful conversion to dlc ?
Thanks & Regards,
Jagmohan
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.
