Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original Caffe architecture which users deploy their applications seamlessly.

Heterogeneous Run Time version of MXNet. Added heterogeneous capabilities to the MXNet, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original MXNet architecture which users deploy their applications seamlessly.

Heterogeneous Run Time version of TensorFlow. Added heterogeneous capabilities to the TensorFlow, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original TensorFlow architecture which users deploy their applications seamlessly.

Implement vgg16 model by ARM Compute Library

arm compute library implementation of efficient low precision neural network

I deleted fullconnectlayer6 and 7 in order to make a small model so that I can load this model to my phone. The purpose of this program is to compare performanc between tensorflow and arm compute library in android phone

This is a fork of the original library to be able to be run on Hikey 970 board using a makefile on top of scons for analyzing bottlenecks and improving performance on it.