This portal has been archived. Explore the next generation of this technology.
CK MLPerf inference 0.7 (object detection • tflite ssd mobilenet non quantized)
solution:ck-mlperf-inference-0.7-object-detection-tflite-ssd-mobilenet-non-quantized (v1.0.0)CK solution description
- Automation framework: CK
- GitHub repository: A collection of all AI and ML workflows and packages in the CK format
- Project overview: Philosophical Transactions of the Royal Society
- Documentation: online
- Results: CK dashboards , MLPerf v0.7 table
- Reproducibility: ACM/cTuning
- Source: GitHub
Installation
Follow this guide to install CK. Then pull CK repositories with AI/ML workflows and components:
MLPerf Inference - Object Detection - TFLite (with Coral EdgeTPU support)
Prerequisites
Install Collective Knowledge (CK)
Please follow the installation instructions for your system e.g.:
$ python3 -m pip install ck --user
$ echo "export PATH=$HOME/.local/bin:$PATH" >> ~/.bashrc
$ source ~/.bashrc && ck version
V1.15.0
Pull CK-MLPerf
$ ck pull repo:ck-mlperf
Pull CK-Coral
To use the Coral EdgeTPU accelerator:
$ ck pull repo:ck-coral
NB: Refresh all CK repositories after any updates (e.g. bug fixes):
$ ck pull all