• Automation framework: CK
  
• Development repository: ck-ml
  
• Source: GitHub
  
• Tags: model,openvino,dldt,converted,converted-from-tf
  
• Support for host OS: any
  
• Support for target OS: any
  
• Software detection plugin: model.openvino
  
• How to get the stable version from this portal via the CK client:
  
  pip install cbench
  cb download package:model-openvino-convert-from-tf --version=3.0.0 --all
  ck install package:model-openvino-convert-from-tf
  ck help package
  
• How to get the development version:
  
  pip install ck
  ck pull repo:ck-ml
  ck install package:model-openvino-convert-from-tf
  ck help package
  
• Useful CK automation actions (CLI with the Python CK API and JSON IO):
  
  ck show env
  ck find env:{ID from above}
  ck virtual env:{ID from above}
  
• CLI and Python API: module:package
  
• Variations:
  • ssd-mobilenet
  • mobilenet
  • resnet50

Convert TF models into OpenVINO format

Calibration prerequisites (for the image classification variations only)

$ python3.6 -m pip install --user \
  nibabel numpy pillow progress py-cpuinfo pyyaml shapely sklearn tqdm xmltodict yamlloader

NB: The requirements specifically mandated py-cpuinfo<=4.0 and scipy<1.2 but py-cpuinfo-5.0.0 and scipy-1.3.1 seem to be fine.

• 3.0.0 (2021-04-11)
• 2.5.0 (2020-09-04)
• 2.0.3 (2020-09-03)
• 1.0.1 (2020-09-02)
• 1.0.0 (2020-05-02)

• .cm/desc.json (3 bytes)
• .cm/info.json (324 bytes)
• .cm/meta.json (5648 bytes)
• README.md (399 bytes)
• custom.py (5821 bytes)
• install.sh (3056 bytes)