MLPerf benchmark demoΒΆ

We collaborate with the MLPerf benchmarking consortium to automate the manual and tedious process of creating MLPerf inference benchmarks and submitting results.

We have prepared a demo of the open-source CodeReef solution for the object detection application from the MLPerf inference benchmark based on SSD-Mobilenets, TensorFlow and COCO data-set:

Please follow the instructions from above page to install the open-source CodeReef Client with the unified CodeReef API to automatically build, run and validate this solution on your machine.

You should be able to reproduce some of the latest MLPerf inference benchmark results from this research paper and compare your results against the official ones using this CodeReef dashboard.

You may be interested to check the CodeReef meta information for this solution including stable dependencies.