Dear Experts,
I am looking for the support for adding custom layer(learnable) as UDL to the network.
If someone has tried to do so, please let me know.
Complications lies at passing the trained weights to UDL and also mapping from UDL to further part of network.
Any suggestion is highly appreciable.
Thanks and Regards,
Vyom Mishra
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 customer,
You can review more helpful messages from SNPE-UDL guidance. Absolutely, I will illustrate the difference between UDL and UDO briefly.
SNPE-UDL: Impact the model layer
SNPE-UDO: Affect the model ops, which will impact multiple layer.
BR.
Wei
Dear Sir,
I have gone through the sample availble in the snpe UDO UDL guide.
The difference in the sample and our usecase is that
SNPE SDK has non-learnable layers examples whereas we are looking for the support for learnable layer like 3-D convolution for our model.
If you have any sample for any learnable layer, please share to us as zip.
Thanks and Regards,
Vyom Mishra