caffe-android-demo
caffe-android-demo copied to clipboard
Predication running slow (more than 10 seconds)
I just run this demo and found that one predication can take more than 10 seconds. Just curious is it normal? As I also tested the Tensorflow and MXNet demo and they run pretty fast. I guess it's all because they use different models?
I just tested GoogleNet, which should be the same model of Tensorflow demo and it still runs slow... Did I miss anything here?