Check the preview of 2nd version of this platform being developed by the open MLCommons taskforce on automation and reproducibility as a free, open-source and technology-agnostic on-prem platform.
program:armcl-classification-mobilenet (v1.0.0)
Share
License: BSD 3-clause (code) and CC BY-SA 4.0 (data)
Creation date: 2018-06-26
Source: GitHub
cID: b0ac08fe1d3c2615:848509ef849f2f39

Don't hesitate to get in touch if you encounter any issues or would like to discuss this community project!
Please report if this CK component works: 1 ▲ or fails: 0 ▲
Sign up to be notified when artifacts are shared or updated!

Description  

This portable workflow is our attempt to provide a common CLI with Python JSON API and a JSON meta description to automatically detect or install required components (models, data sets, libraries, frameworks, tools), and then build, run, validate, benchmark and auto-tune the associated method (program) across diverse models, datasets, compilers, platforms and environments. Our on-going project is to make the onboarding process as simple as possible via this platform. Please check this CK white paper and don't hesitate to contact us if you have suggestions or feedback!
  • Automation framework: CK
  • Development repository: ck-math
  • Source: GitHub
  • Available command lines:
    • ck run program:armcl-classification-mobilenet --cmd_key=default (META)
  • Support for host OS: any
  • Support for target OS: android, linux
  • Tags: armcl-classification,demo
  • How to get the stable version via the client:
    pip install cbench
    cb download program:armcl-classification-mobilenet --version=1.0.0 --all
    ck run program:armcl-classification-mobilenet
  • How to get the development version:
    pip install ck
    ck pull repo:ck-math
    ck run program:armcl-classification-mobilenet
  • CLI and Python API: module:program

    • Dependencies    

    ReadMe  

    Classification program for ArmCL

    Requirements

    ArmCL library

    To build this program, you need ArmCL compiled with Graph API:

    $ ck install package:lib-armcl-opencl-18.05 --env.USE_GRAPH=ON --env.USE_NEON=ON --extra_version=-graph

    To build this program for Android you need to embedd kernels and select target API as follows:

    $ ck install package:lib-armcl-opencl-18.05 --env.USE_GRAPH=ON --env.USE_NEON=ON --extra_version=-graph --env.USE_EMBEDDED_KERNELS=ON --env.DEBUG=ON --target_os=android23-arm64

    NB: Use --target_os=android23-arm64 to build for Android API 23 (v6.0 "Marshmallow") or similar.

    We have to embed kernels when building for Android as OpenCL kernel files are not copied to a remote device.

    TODO: For some reason only debug version of the library can be used with this program on Android. When we use release version, the program gets stuck at stage "Preparing ArmCL graph".

    Weights package

    Install a package providing weights as NumPy array files:

    $ ck install package:weights-mobilenet-v1-1.0-224-npy
$ ck install package --tags=mobilenet,weights,npy

    Compile

    $ ck compile program:armcl-classification-mobilenet [--target_os=android23-arm64]

    Run

    $ ck run program:armcl-classification-mobilenet [--target_os=android23-arm64]

    Versions  

    Files  

    Comments  

    Please log in to add your comments!
    If you notice any inapropriate content that should not be here, please report us as soon as possible and we will try to remove it within 48 hours!