David Kanter

Can we get tables showing what is in the benchmark suite in the landing page? See https://github.com/mlcommons/inference for a great example with all the different rounds.

https://mlcommons.org/en/credits/ needs to be updated. Can we fill in https://docs.google.com/spreadsheets/d/17q_OtvVI_C5ET0shUTObHwiplUVRj5gFkU1dTkU7AcQ/edit#gid=0 for the three HPC benchmarks?

Add paper reference to readme

1

Can we add the HPC training paper reference to the readme? Cody Coleman created a great example for training here: https://github.com/mlcommons/policies/issues/86

https://mlcommons.org/en/credits/ needs to be updated. Can we fill in https://docs.google.com/spreadsheets/d/17q_OtvVI_C5ET0shUTObHwiplUVRj5gFkU1dTkU7AcQ/edit#gid=0 for MobileNetEdgeTPU DeepLabV3 OLD SSD MobileDETs MobileBERT

Fix typo in training_rules.adoc

1

Fixed a typo

Rules state: "To extract submission convergence points, logs should report epochs as follows. For this round no RCP checks will be made for Minigo." What is "this round"??? This is...

See the title, to do for v0.8.

Performance measurement for short run times and DVFS

2

- Need run-time >5min in order to get good estimate of steady state perf otherwise power draw can exceed TDP for short periods. So not really a fair measurement. -...

Table summarizing benchmark suite

1

Can we get a table that summarizes the benchmark suite on the readme page, e.g., similar to inference

Can we get tables showing what is in the benchmark suite in the landing page? See https://github.com/mlcommons/inference for a great example with all the different rounds.