inference issues

Query: How to run BERT INT8 TF model

1

Hi, I am trying to run BERT INT8 with TF backend. However, I don't see TF INT8 model info in below link. https://github.com/mlcommons/inference/tree/master/language/bert Any help on how to run will...

avinashcpandey

Fixes #1249

1

This PR enables one to run bert reference implementation using onnxruntime backend with custom model, dataset and log paths and also supports the usage of Nvidia GPUs with onnxruntime version...

arjunsuresh

Update file names in Readme

1

Reflect changes made in #1254

pgmpablo157321

Query: Is running two instances of MLPerf valid for Offline and Server Submission

3

Hi, To get the best performance from system(X86arch), I am running two instances of MLPerf simultaneously through shell script (Each with their own Loadgen and SUT), each instance is bind...

avinashcpandey

Pytorch DLRM reference scripts failing in accuracy mode

5

Dear All, We are trying to run inference reference scripts for pytorch DLRM (recommendation) in accuracy mode using mlperf official model (tb00_40M.pt). In order to check accuracy, we are using...

sudarshan-shinde

pycocotools for retinanet

14

We've been using the standard [`pycocotools`](https://pypi.org/project/pycocotools/) Python package for calculating the Object Detection accuracy since MLPerf Inference v0.5. It used to be OK for SSD-ResNet34 and SSD-MobileNet-v1, but it is...

psyhtest