https://github.com/openmachine-ai/mlperf-tools

https://github.com/openmachine-ai/mlperf-tools

Last synced: 11 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/openmachine-ai/mlperf-tools
• Owner: OpenMachine-ai
• Created: 2023-08-23T16:53:46.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-08-24T21:12:34.000Z (over 1 year ago)
• Last Synced: 2024-11-10T09:15:14.963Z (2 months ago)
• Language: Jupyter Notebook
• Size: 30.3 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


 

This repo contains the following tools for running MLPerf benchmarks:

- [eval.py](eval.py): For the tiny MLPerf visual wake word (vww), this script downloads

  the dataset from Silabs and runs both TFLite reference models (int8-model and float-model)

  with the 1000 images listed in y_labels.csv to measure their accuracy.

- [eval.ipynb](eval.ipynb): Jupyter notebook generated from [eval.py](eval.py),

  click [here](https://colab.research.google.com/github/OpenMachine-ai/mlperf-tools/blob/main/eval.ipynb)

  to run it from your browser.