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:tensorflow-detection-squeezedet (v1.0.0)
Creation date: 2018-03-20
Source: GitHub
cID: b0ac08fe1d3c2615:59df77344848419b

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:tensorflow-detection-squeezedet --cmd_key=test (META)
  • Support for host OS: any
  • Support for target OS: any
  • Tags: tensorflow,squeezedet,object-detection
  • How to get the stable version via the client:
    pip install cbench
    cb download program:tensorflow-detection-squeezedet --version=1.0.0 --all
    ck run program:tensorflow-detection-squeezedet
  • How to get the development version:
    pip install ck
    ck pull repo:ck-tensorflow
    ck run program:tensorflow-detection-squeezedet

  • CLI and Python API: module:program
  • Dependencies    

    ReadMe  

    SqueezeDet validation and finetuning demo

    This demo is mainly based on another demo by BichenWuUCB et al. and uses it as dependency.

    Requirements

    • Tensorflow library:
    ck install package --tags=lib,tensorflow --no_tags=vshared
    
    • KITTI images dataset:
    ck install package --tags=dataset,kitti
    
    • One of SqueezeDet models:
    ck install package:squeezedetmodel-squeezedet
    ck install package:squeezedetmodel-squeezedet-plus
    ck install package:squeezedetmodel-resnet50
    ck install package:squeezedetmodel-vgg16
    
    • SqueezeDet demo:
    ck install package:demo-squeezedet-patched
    

    This is only required as it contains Python modules implementing models.

    TODO: Including Python modules into respective package listed above we could avoid this dependency.

    • KITTI evaluation tool:
    ck compile program:kitti-eval-tool
    

    Validation

    ck run program:tensorflow-detection-squeezedet --cmd_key=test
    

    Finetuning (TODO)

    ck run program:tensorflow-detection-squeezedet --cmd_key=finetune
    

    We could implement a command to fine-tune selected SqueezeDet model to detect objects of VOC and COCO datasets.

    There are some challenges here:

    • Annotations format is different so some kind of label conversion is required.

    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!