• Automation framework: CK
  
• Development repository: ck-ml
  
• Source: GitHub
  
• Tags: model,onnx,mlperf,converted,converted-from-tf
  
• Support for host OS: any
  
• Support for target OS: any
  
• Software detection plugin: model.onnx
  
• How to get the stable version from this portal via the CK client:
  
  pip install cbench
  cb download package:model-onnx-convert-from-tf --version=3.0.0 --all
  ck install package:model-onnx-convert-from-tf
  ck help package
  
• How to get the development version:
  
  pip install ck
  ck pull repo:ck-ml
  ck install package:model-onnx-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:
  • mobilenet
  • resnet
  • ssd-mobilenet
  • nchw
  • nhwc

Install ONNX models by converting from TF models

A package that installs ONNX models by converting from TF models.

Currently, only the following MLPerf Image Classification models are supported: - MobileNet (non-quantized). - ResNet.

MobileNet

NHWC

$ ck install package --tags=onnx,model,mobilenet,converted,nhwc

NCHW

$ ck install package --tags=onnx,model,mobilenet,converted,nchw

ResNet

NHWC

$ ck install package --tags=onnx,model,resnet,converted,nhwc

NCHW

$ ck install package --tags=onnx,model,resnet,converted,nchw

• 3.0.0 (2021-04-11)
• 2.5.0 (2020-09-04)
• 2.0.3 (2020-09-03)
• 1.1.1 (2020-09-02)
• 1.1.0 (2020-05-02)
• 1.0.0 (2019-10-08)

• .cm/desc.json (3 bytes)
• .cm/info.json (311 bytes)
• .cm/meta.json (4541 bytes)
• README.md (691 bytes)
• install.sh (486 bytes)