How to run Keras model inference x3 times faster with CPU and Intel OpenVINO
Branch: master
Clone or download
Latest commit 8bff7ae Jan 30, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data init Jan 27, 2019
.gitignore init Jan 27, 2019
LICENSE init Jan 27, 2019
README.md init Jan 27, 2019
keras-openvino-ImageNet.ipynb IENetwork Jan 30, 2019
requirements.txt init Jan 27, 2019

README.md

How to run Keras model inference x3 times faster with CPU and Intel OpenVINO | DLology Blog

System requirement

  • 6th-8th Generation Intel® Core™
  • Intel® Xeon® v5 family
  • Intel® Xeon® v6 family

Operating Systems

  • Ubuntu* 16.04.3 long-term support (LTS), 64-bit
  • CentOS* 7.4, 64-bit
  • Windows* 10, 64-bit

How to Run

Require Python 3.5+ and Jupyter notebook installed

Clone or download this repo

git clone https://github.com/Tony607/keras_openvino

Install OpenVINO

Setup OpenVINO on your machine, choose your OS on this page, follow the instruction to download and install it.

Install required libraries

pip3 install -r requirements.txt

Run the setupvars.bat before launching jupyter notebook.

C:\Intel\computer_vision_sdk\bin\setupvars.bat

Or in Linux add the following line to ~/.bashrc

source ~/intel/computer_vision_sdk/bin/setupvars.sh

In a terminal run,

jupyter notebook

In the opened browser window open

keras-openvino-ImageNet.ipynb