Hi dear,
My model is divided into two DLC processes, encoder and decoder. The encoder process input is images. The output of the encoder is [1,256,128,128] (b, c, h, w) tensor.
May I ask what is the quantized input_list of the DLC model for the decoder process?
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,
Per my understanding, you have two models which named as encoder and decoder. So that you need to request two SNPE instance for your application.
BR.
Wei