program:request-armcl-inference (v1.0.0)
Share
License: BSD 3-clause (code) and CC BY-SA 4.0 (data)
Creation date: 2018-02-16
Source: GitHub
cID: b0ac08fe1d3c2615:8f8dd5e56f4ed39e

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-request-asplos18-mobilenets-tvm-arm
  • Source: GitHub
  • Available command lines:
    • ck run program:request-armcl-inference --cmd_key=all (META)
    • ck run program:request-armcl-inference --cmd_key=help (META)
    • ck run program:request-armcl-inference --cmd_key=run-net (META)
  • Support for host OS: any
  • Support for target OS: android, linux
  • Tags: armcl,benchmark,armcl-benchmark,float32,float16,tvm,vopencl
  • How to get the stable version via the client:
    pip install cbench
    cb download program:request-armcl-inference --version=1.0.0 --all
    ck run program:request-armcl-inference
  • How to get the development version:
    pip install ck
    ck pull repo:ck-request-asplos18-mobilenets-tvm-arm
    ck run program:request-armcl-inference
  • CLI and Python API: module:program

    • Dependencies    

    ReadMe  

    System-level network classification and benchmarking

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

    $ ck pull all
$ ck install package:lib-armcl-opencl-17.12 --env.USE_GRAPH=ON --env.USE_NEON=ON --extra_version=-graph --env.USE_EMBEDDED_KERNELS=ON

    When this is done, compile and run the program as usual:

    $ ck compile
$ ck run --cmd_key=help

    You can rubn on all networks

    • ck run --cmd_key=all

    You can run on different networks:

    • ck run --env.CK_ACL_MODEL=mobilenet (this is the default)

    You can run on different convolution methods:

    • ck run --env.CK_ACL_CONV_METHOD=gemm (this is the default)

    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!