HI,
I converted ssd mobilenet inception v2 (only person detection )model to dlc.
I run android appliction on 820 board on CPU.
I given image which have two persons to android appliaction,the ouput gives like PERSON:1
when i given more persons(9) image ,output gives like PERSON:38
when i am trying to run on GPU ,the app gets closed.
and i have question ,snpe can supports the object detection or not ?or it supports only classification?
Can you please suggest me
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.
Hi,
It is not that SNPE supports only classification or object detection. All matter is which layer we are using to build the model (layers which are supported by SNPE tool). So please make sure, you are using the layers which are mentioned in SNPE Docs (supported layers) provided in below link
https://developer.qualcomm.com/docs/snpe/network_layers.html