Object detection and recognition on mobile device
and x86 platform. However, there are some performance issue needed to resolve. For example, it takes a long to
recognize all bounding boxes and use too much memory on mobile platforms. I have tried openCL on my
Android phone, but it won't be better. So I am going to remove some layers of Convolution Neural Network to
improve speed and memory, but I am not sure of how much accuracy will drop down. I am also
going to try pruning methods and other BLAS like MKL to speed up forwarding on mobile device.
Object detection on HTC Desire Eye