Setup Intel OpenVINO and AWS Greengrass on Ubuntu

Setup Intel OpenVINO and AWS Greengrass on Ubuntu 
  1. First set the conversion tool ModelOptimizer: https://software.intel.com/en-us/articles/OpenVINO-ModelOptimizer
  2. Command : `source /bin/setupvars.sh`
  3. Command : `cd /deployment_tools/model_optimizer/install_prerequisites`
  4. Command : `sudo -E ./install_prerequisites.sh`
  5. Model Optimizer uses Python 3.5, whereas Greengrass samples use Python 2.7. In order for Model Optimizer not to influence the global Python configuration, activate a virtual environment as below:
  6. Command : `sudo ./install_prerequisites.sh venv`
  7. Command : `cd /deployment_tools/model_optimizer`
  8. Command : `source venv/bin/activate`
  9. For CPU, models should be converted with data type FP32 and for GPU/FPGA, it should be with data type FP16 for the best performance.
  10. For classification using BVLC Alexnet model:
    Command : `python mo.py --framework caffe --input_model /bvlc_alexnet.caffemodel --input_proto /deploy.prototxt --data_type --output_dir --input_shape [1,3,227,227]`
  11. For object detection using SqueezeNetSSD-5Class model:
    Command : `python mo.py --framework caffe --input_model /SqueezeNetSSD-5Class.caffemodel --input_proto /SqueezeNetSSD-5Class.prototxt --data_type --output_dir `
  12. where is the location where the user downloaded the models, is FP32 or FP16 depending on target device, and is the directory where the user wants to store the IR. IR contains .xml format corresponding to the network structure and .bin format corresponding to weights. This .xml should be passed to mentioned in the Configuring the Lambda Function section. In the BVLC Alexnet model, the prototxt defines the input shape with batch size 10 by default. In order to use any other batch size, the entire input shape needs to be provided as an argument to the model optimizer. For example, if you want to use batch size 1, you can provide --input_shape [1,3,227,227].
Greengrass sample is in : 
/opt/intel/computer_vision_sdk/inference_engine/samples/python_samples/greengrass_samples/

However, there are some changes in the openvino_toolkit_p_2018.3.343 version of the path that need to be modified (python2):

LD_LIBRARY_PATH : 
/opt/intel/computer_vision_sdk/opencv/share/OpenCV/3rdparty/lib:/opt/intel/computer_vision_sdk/opencv/lib:/opt/intel/opencl:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/external/cldnn/lib:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/external/mkltiny_lnx/lib:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/lib/ubuntu_16.04/intel64:/opt/intel/computer_vision_sdk/deployment_tools/model_optimizer/model_optimizer_caffe/bin:/opt/intel/computer_vision_sdk/openvx/lib

PYTHONPATH : 

/opt/intel/computer_vision_sdk/python/python2.7/ubuntu16/

PARAM_CPU_EXTENSION_PATH : 

/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/lib/ubuntu_16.04/intel64/libcpu_extension_avx2.so

留言

Google Search

推薦內容橫式

本月熱門文章

2025 中華民國政府該怎麼用現有預算做事情?

什麼是 OTA ?

八炯統戰影片心得 千萬要謹慎 勿掉入金錢陷阱

孫生的謊言 - 性騷擾被判刑 法院認證

泰國北碧 大象世界 Elephants World Kanchanaburi - 大象保護園區 大象照料體驗行程

蔣萬安訪中後,換侯友宜訪美,中國國民黨有機會組成侯蔣配嗎?

中華民國國軍辛苦了 因應中共軍演努力監視

2020年 中華人民共和國 軍機繞台380次 中華民國國防部回應

[FAANG面試] Amazon/AWS 領導力準則 14 Amazon Leadership Principles

這個網誌中的熱門文章

Android應用開發豆知識:利用 adb 安裝 apk 到裝置上

Android 中文輸入法 官方版 ! Gboard - Google 鍵盤 開始支援注音輸入啦

Google Play 推薦Android app 誠徵App排行榜

北京故宮首訪,一窺清宮秘史 大玉兒 & 甄嬛

[家教][社會觀察] 建中教我的事 沒上建中被父母親折磨? 在建中到底是如何 ...

[FAANG面試] Amazon/AWS 領導力準則 14 Amazon Leadership Principles

Acer ICONIA Smart S300 更新後越來越好 Acer也有出手機?!

[品質控制] 什麼是Sanity test ? 軟體測試常見名詞整理 包含不同部門的測試人員負責範圍

新鮮人找工作:職場名詞解釋 AE FAE Pre-sales Post-sales