I have tried android demo of tensorflow on my phone, And successfully used my own ssd_mobilenets model trained by object_detection API. It said ssd_mobilenets can run on android phone in real time, But it runs a little slow on my mobile phone. It cost nearly 1 seconds to detect object. I wonder if it possible to use the gpu of my phone to accelerate the configuration.
Asked
Active
Viewed 388 times
2
-
I suppose it is technically possible, but even if you manage to compile it presumably it would only work on [Android devices with a Tegra GPU](https://www.nvidia.com/object/tegra-phones-tablets.html) with [support for CUDA](https://developer.nvidia.com/cuda-gpus). – jdehesa Aug 25 '17 at 09:19