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
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