yolov3 accuracy

[sfatimar]

This one line change is to ensure myriad configuration is set to achieve maximum yolov3 accuracy.

Motivation and Context

• We have found that the reason is that in this case preprocessing is not a part of the model and is performed separately (while the converted IRs usually have the preprocessing inside the model) which in turn affects MYX heuristic algorithms. To avoid the degradation we added an additional option, which should be used in this case.
• If it fixes an open issue, please link to the issue here.

[jywu-msft]

/azp run Windows GPU CI Pipeline, Windows GPU TensorRT CI Pipeline, centos7_cpu, centos7_cpu (linux_centos_ci Debug), centos7_cpu (linux_centos_ci Release), orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, orttraining-amd-gpu-ci-pipeline, Linux Nuphar CI Pipeline, orttraining-distributed

[jywu-msft]

/azp run Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux CPU x64 NoContribops CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, MacOS NoContribops CI Pipeline, Windows CPU CI Pipeline, orttraining-ortmodule, orttraining-ortmodule-distributed

[azure-pipelines]

Azure Pipelines successfully started running 6 pipeline(s).

[azure-pipelines]

Azure Pipelines successfully started running 10 pipeline(s).

[jywu-msft]

/azp run Linux GPU CI Pipeline

[azure-pipelines]

Azure Pipelines successfully started running 1 pipeline(s).

[jywu-msft]

looks like there is a merge conflict. can you please resolve?

[sfatimar]

looks like there is a merge conflict. can you please resolve?

Resolved

[jywu-msft]

/azp run Windows GPU CI Pipeline, Windows GPU TensorRT CI Pipeline, centos7_cpu, centos7_cpu (linux_centos_ci Debug), centos7_cpu (linux_centos_ci Release), orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, orttraining-amd-gpu-ci-pipeline, Linux Nuphar CI Pipeline, orttraining-distributed

[azure-pipelines]

Azure Pipelines successfully started running 6 pipeline(s).

[jywu-msft]

/azp run Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux CPU x64 NoContribops CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, MacOS NoContribops CI Pipeline, Windows CPU CI Pipeline, orttraining-ortmodule, orttraining-ortmodule-distributed, Linux GPU CI Pipeline

[azure-pipelines]

You have several pipelines (over 10) configured to build pull requests in this repository. Specify which pipelines you would like to run by using /azp run [pipelines] command. You can specify multiple pipelines using a comma separated list.

[jywu-msft]

/azp run Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux CPU x64 NoContribops CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, MacOS NoContribops CI Pipeline, Windows CPU CI Pipeline, orttraining-ortmodule, orttraining-ortmodule-distributed

[jywu-msft]

/azp run Linux GPU CI Pipeline

[azure-pipelines]

Azure Pipelines successfully started running 1 pipeline(s).

[azure-pipelines]

Azure Pipelines successfully started running 10 pipeline(s).