NVIDIA AI Inference Performance Evaluation

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Hi All,
I would like to replicate the benchmarking on this article
https://news.developer.nvidia.com/nvidia-ai-inference-performance-milestones-delivering-leading-throughput-latency-and-efficiency/

I only know a bit of system under test information from the article

  • All data here gathered on ResNet-50 using TensorRT 5.
  • Throughput and Efficiency tests run at batch-size 128;
  • System config: Dual-socket Xeon Gold 6140 with 384GB of system memory and
    • a single Tesla V100 OR
    • Tesla T4

Could you please tell or give some hints on how to replicate this test such as:

  • How to setup the test
  • What is the test cases? Where to get the example code to run
  • Where to get the test data.
    …

Thank you very much!