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:kitti-eval-tool (v1.0.0)
Share
Creation date: 2018-03-21
Source: GitHub
cID: b0ac08fe1d3c2615:62e8996f6ce93af9

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-tensorflow
  • Source: GitHub
  • Available command lines:
    • ck run program:kitti-eval-tool --cmd_key=default (META)
  • Support for host OS: any
  • Support for target OS: linux
  • Tags: kitti-eval-tool
  • How to get the stable version via the client:
    pip install cbench
    cb download program:kitti-eval-tool --version=1.0.0 --all
    ck run program:kitti-eval-tool
  • How to get the development version:
    pip install ck
    ck pull repo:ck-tensorflow
    ck run program:kitti-eval-tool
  • CLI and Python API: module:program

    • Dependencies    

    ReadMe  

    KITTI evaluation tool

    Official KITTI evaluation tool is located here. But it requires boost as additional dependency, so included source is taken from this SqueezeDet demo and it has no dependencies.

    The code is slightly modified to be able also taking parameters from environment variables in addition to command line arguments.

    Build

    ck compile program:kitti-eval-tool

    Run

    ck run program:kitti-eval-tool

    This program is mainly used internally by various detection programs, e.g. tensorflow-detection-squeezedet.

    Environment variables

    CK_KITTI_LABELS_DIR

    Path to KITTI annotations that will be used for validation. E.g. ${CK-TOOLS}/KITTI-full/training/label_2

    CK_IMAGE_LIST_FILE

    Path to a text file containing list of paths to images that were processed by a detection program.

    CK_RESULTS_DIR

    Path to a directory containig detection results.

    CK_IMAGE_COUNT

    Number of processed images.

    Detection result file format

    TODO

    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!