Enviroment Setup for Qualcomm's Neural processing SDK

Pre-requisite :-

  • A workstation running x86_64 Linux for DLC preparation, generation, and quantization.
  • Ubuntu 20.04 (either in a native OS environment or through WSL2 on Windows 10/11).
  • Model should be in One of the following frameworks:

  1. TensorFlow
  2. ONNX
  3. PyTorch
  4. TensorFlow Lite 

  • Model training must be complete. 
  •  The Android developer’s toolkit (NDK) is required.
  •  Python v2.7 or later is required. 
  •  Android SDK platform tools are required. 
  •  The Android debug bridge (adb) must be installed.

Here we will discuss the steps to setup the Environment for Qualcomm Neural processing SDK :- 

step I :- Installing Ubuntu(20.04) using Virtual Box.

1. Install the Oracle VirtualBox -> https://www.virtualbox.org/wiki/Downloads 

 2. Download the Ubuntu 20.04 ISO image. -> https://releases.ubuntu.com/focal/ 

complete the Ubuntu(20.04) installation on windows using this -> setup Ubuntu 20.04 on Windows 10/11

open a terminal and run sudo apt update && sudo apt upgrade -y and then sudo snap refresh to get everything updated to the latest versions.


step II :-

Download Qualcomm Package Managaer (for linux) :- https://qpm.qualcomm.com/#/main/tools/details/QPM3

After downloading the Qualcomm package manager.

you have to licence agreement otherwise you may login error   

linl for product licence : https://www.qualcomm.com/agreements/https://www.qualcomm.com/agreements/


 You have to run this command in your terminal. -> sudo dpkg –i Qualcomm package manager.

 It will install the Qualcomm package manager in your environment.

 From terminal, run below commands:

  1.  qpm-cli --login
  2.  qpm-cli --license-activate qualcomm_neural_processing_sdk 
  3.  qpm-cli --extract qualcomm_neural_processing_sdk (or) qpm-cli --extract<full path to .qik file>

                                                                   Or

 From QPM3 Desktop App:

  1.   Open QPM3 App on desktop 
  2.  Goto Tools page, then select Qualcomm® Neural Processing SDK
  3.  Select version and click "Extract".

After install Qualcomm neural processing sdk . You will get this path. /opt/qcom/aistack/qairt/2.21.0.240210

step III : setting  SNPE SDK environment setup :-

Python

The SDK requires python3.8. If python3.8 is not already installed on your system, you may install it with the following commands:

  • $ sudo apt-get update
  • $ sudo apt-get install python3.8 python3-distutils libpython3.8

To work with TensorFlow 1.15.0, Python 3.6 is required. Install Python 3.6 with the following commands:
  • $ sudo apt-get install software-properties-common
  • $ sudo add-apt-repository ppa:deadsnakes/ppa
  • $ sudo apt-get update
  • $ sudo apt-get install python3.6 python3-distutils libpython3.6
Virtual Environment (VENV)

to tackle conflict between different version of python you can use virtual enviroment

  • $ sudo apt-get install python3.8-venv
  • $ python3.8 -m venv "<PYTHON3.8_VENV_ROOT>"
  • $ source <PYTHON3.8_VENV_ROOT>/bin/activate
To work with TensorFlow 1.15.0, Python 3.6 is required:
  • $ sudo apt-get install python3.6-dev python3.6-venv
  • $ python3.6 -m venv "<PYTHON3.6_VENV_ROOT>"
  • $ source <PYTHON3.6_VENV_ROOT>/bin/activate
run the following command to check any missing dependencies :-
  • $ python3 -m pip install --upgrade pip
  • $ ${SNPE_ROOT}/bin/check-python-dependency
Clang 9

install clang 9 and linux dependencies with following command :-
  •  $ sudo bash ${SNPE_ROOT}/bin/check-linux-dependency.sh
Supported ML Frameworks Versions :-
  • TensorFlow: tf-1.15.0,or tf-2.10.1 
  • TFLite: tflite-2.3.0
  •  PyTorch: torch-1.13.1
  •  ONNX: onnx-1.11.0
  •  ONNX Runtime: onnxruntime-1.11.1

Make 

install make with following command :

  • $ sudo apt-get install make

Android NDK

install Android NDK version r25c with this link ->https://dl.google.com/android/repository/android-ndk-r25c-linux.zip

After download, extract the zip file and add the extracted location to your PATH environment variable.

Use the following commands to set the environment to use Android NDK and check configuration :

  • $ export ANDROID_NDK_ROOT=<PATH-TO-NDK>
  • $ export PATH=${ANDROID_NDK_ROOT}:${PATH}
  • $ ${SNPE_ROOT}/bin/envcheck -n
to check if enviroment is properly setup to use clang 9 run the following command :-
  •  ${SNPE_ROOT}/bin/envcheck -c

Java :-

Java environment is required to integrate Qualcomm® Neural Processing SDK with Android applications. Java 8 is required check if Java 8 is installed or not using following command :-
  • $ sudo apt-get install openjdk-8-jdk

Now to check if the linux enviroment is setup proper run the following command :

  • $ source ${SNPE_ROOT}/bin/envsetup.sh

This will set/update the following environment variables:
  •  SNPE_ROOT
  •  PYTHONPATH
  •  PATH 
  • LD_LIBRARY_PATH


Machine Learning frameworks 

ensure you have installed the required version of ML framework to use 

you check if your ml frameworks are in your pythonpath by following commands for respective ML frameworks :

  • python -c "import tensorflow"
  • python -c "import onnx"
  • python -c "import tflite"
  • python -c "import torch"

read out the next blog , where we will learn to execute Inception_V3  using SNPE SDK.












Comments

Post a Comment

Popular posts from this blog

Examples of running Machine Learning Model on Device using Qualcomm AI HUB

Getting started  Installation  We recommend using Miniconda to manage your python versions and environments. Step 1: Python environment Install  miniconda  on your machine. Windows : When the installation finishes, open Anaconda Prompt from the Start menu. macOS/Linux : When the installation finished, open a new shell window. Set up an environment for Qualcomm® AI Hub: conda create python = 3 .8 -n qai_hub conda activate qai_hub Warning If any of these steps fail with  SSL:   CERTIFICATE_VERIFY_FAILED  errors, you have an SSL interception and traffic inspection tool installed. Ask your IT department for instructions on how to set up certificates for Python  pip  and the Python  Requests  library. They should provide you with a new certificate file. You will also need to add this certificate to Miniconda prior to creating your environment. This can be done with  conda   config   --set   ssl_verify   <path ...
Read more

Medical Report Analyzer - Progess

Image
Content : You get to know the approach what we have followed for this Medical report Analyzer project. there are different steps involved in this process and get to know  which libraries are used with code snippets. Extracting the Text From the Input PDF step 1 : We have extracted text from the pdf using the Python library  Pytesseract  installing the usefull libraries using pip command :- ! sudo apt-get install tesseract-ocr ! pip install pytesseract pip install PyMuPDF step 2 : now code to extract text from pdf you will get the output text as : Now there are two ways to Extract the specific field details from the extracted field :  Using the HardCode Method where you will Write code with many if-else condition to handle' different cases for different format of Medical Report you have to parse the text using regular expressions to extract the relevant field details like Name , Age , Gender, DOB , etc.       2. You Can use LLMs to extract the req...
Read more

Running Inception_V3 using On-device AI

Image
  Introduction  The Inception v3 Imagenet classification model is trained to classify images with 1000 labels. Inception-V3 is a convolutional neural network architecture designed for image classification and recognition tasks. Tensorflow Setup : To set up TensorFlow, perform the following procedure: 1.  Download android-ndk- , and set the ANDROID_NDK_ROOT environment variable.   $export ANDROID_NDK_ROOT=<path to Android Ndk root> 2. Go to the SNPE SDK root directory, and run the following script to set up the SNPE SDK environment (the TensorFlow home directory must be provided):  $export TENSORFLOW_DIR=/usr2/ /.local/bin/ $source bin/envsetup.sh -t $TENSORFLOW_DIR   where $TENSORFLOW_DIR is the path to the TensorFlow installation. The script sets up the following environment variables:  SNPE_ROOT: root directory of the SNPE SDK installation  TENSORFLOW_HOME: root directory of the TensorFlow installation provided   Th...
Read more