T02:- How to setup the Qualcomm Neural Processing SDK

   Setup of Qualcomm Neural Processing SDK


We will now understand how we can setup the Qualcomm Neural Processing Engine SDK in our system
  -> To start  with first thing we have to understand what is required for this setup.
     1. Oracle Virtual Box https://www.virtualbox.org/wiki/Downloads
     2. Ubuntu 20.04  https://releases.ubuntu.com/focal/
     We can also work with WSL2 environment that will work on Windows 10/11.
     3. Any Machine Learning Framework
        3.1 Tensorflow
        3.2 Pytorch
        3.3 Tensorflow lite
        3.4 Onnx
     4. Android NDK
     5. Microsoft Visual C++(Resdistrubution)

So now we will go to the practical aspect of the setup of the Neural Processing SDK(SNPE).

1.We will first download the Virtual box as per the requirement.
   1.1  Here is the link for the download  https://www.virtualbox.org/wiki/Downloads
   1.2  After downloading of virtual box we will first download the Microsoft visual C++ redistribution
         Here is the link  https://aka.ms/vs/17/release/vc_redist.x86.exe 
          You can download Microsoft visual c++ according to your system architecture.
   1.3 After downloading the both we will now download the Ubuntu 20.04 in  our system https://releases.ubuntu.com/focal/
                         


 2. After download of Ubuntu we will now setup the Oracle Virtual Box with Ubuntu ISO image file.
 2.1 We will now create the a new virtual machine.
    -> It will open like this below image .
    

    -> You will click on New button for creating the new virtual machine .
    ->  After that step we will see a new interface like below one image.
  


     ->  So, in the Name section we will name our Virtual machine (You can name anything).
     ->  In the second section we will choose the folder where Virtual box is present.
     ->  In the third section we will choose that Ubuntu ISO file which is present in file Folder.

    Now we can click onto the Next step which will be in the interface.
 After this step we will jump into the Profile section of the Virtual Machine.
 The image will be like this below one :-
 

    -> You can setup the Username according to your will.
    -> Then choose the Strong password.
   Then click on to the Guest Additions(Improves performance and usability of Virtual Machine(VMs) 
   running in Virtual Box).

  After this step we will define the Virtual machine resources.
  The interface will be like this below one:-
   


    -> You can drag the slider only till the green marker on both Base Memory and Processors.
    -> For better performance of the Virtual Machine we can choose 4 processors and 4096MB(base memory).
     Now click onto the Next button.
   
 We will get this type of interface .
  
 

  ->You can Disk size according to your requirement(But the required disk size is 60 Gb )
   Now Click onto the Next button

  After this step we will now get this type of interface .
  

Now click onto the Finish Button .
It will prompt into the Ubuntu Interface like this one .

Now ,we will setup the Neural processing SDK through the Terminal.
->You can press (CTRL + ALT+ T) for terminal .
->After opening of Terminal .
  We will run these commands .
  
       

   ->We will run this command sudo apt-get update ( It downloads all the package information from all
     configured sources and updates the package index).
   ->Now after complete installation of Ubuntu ( You can now go to  the Qualcomm Neural Processing
     SDK website).

   -> There will be a download button from there you will login to the Qualcomm Neural processing       SDK Website.(You will follow this only on the Virtual machine Browser not on the Windows).

   ->Your Interface should look like this  below  image.

         
         -> Now we will see the steps required for the installation of Qualcomm package Manager.
         You will run these commands into your Virtual machine terminal.
          Install QPM3 from https://qpm.qualcomm.com/#/main/tools/details/QPM3

              Run this command for Qualcomm Manager file

            1.1   sudo dpkg -i QualcommPackageManager3.3.0.97.2.Linux-x86.deb

        After this we will run this step for the login to the SNPE SDK. 
             1.2  qpm-cli --login.
           It will prompt for username and password of your Qualcomm account.
       After that step you will be running this command for activating the license.
        1.3  qpm-cli --license-activate qualcomm-neural processing_sdk.

       After running above command you will get an error message that your account is not activated  something like that then you have to go to this website and activate all your license


       After activating your license you can run this below command for downloading and extracting the qualcomm neural processing SDK.
      1.4 qpm-cli --extract qualcomm_neural_processing_sdk.
       
      After all those steps your Neural processing Sdk will be  installed  to your specific folder.
      And you will get some path like this below one.
      SNPE_ROOT :- /opt/qcom/aistack/snpe/<version>.
      

From the next blog we will begin to understand how we can convert given machine learning model into  dlc.  Stay with us for the next part....

-


      

Comments

Post a Comment

Popular posts from this blog

T01:- Introduction to Ondevice AI

Image
                Understanding Of On-device Ai Smart stuff like phones and cars are getting smarter . They can crunch data and learn without needing the internet all the time. Qualcomm is a big part of making this happens.                                       Fig - 1.1(On-device AI) So, What is On-device AI? On-device means smart devices like phones or smartwatches can work without need of constant internet connection. Its like having a live brain inside your gadgets, making quick decisions and performing task without the need of live servers. This technology is good for things like voice assistants and image recognition , as it reduces the latency and ensures privacy by keeping data local.                                           Fig- 1.2 ( ON-...
Read more

T03:- How to convert given existing model into DLC format

Image
    Conversion of given model into DLC format We will try to convert the machine learning model which is given in the neural processing sdk into the Dlc format manually. -> We are doing this step because SDK tools and libraries are able to understand the code only in the      converted DLC format. -> We will first make directory like above structure in this path /opt/qcom/aistack/snpe/<Version_ number>/examples/Models/InceptionV3  -> We will make a folder data.        mkdir data && cd data  -> Then we will make another subfolder into data folder.         mkdir cropped  -> Then we will come out from that folder data.    -> After that we will make dlc and tensorflow folder in the InceptionV3 folder.         mkdir dlc && tensorflow After making all the required folders into InceptionV3 model , we will download InceptionV3 Model into the tmp ...
Read more