Add FAQ page

[Faith Xu (faxu)]

Adding a FAQ page with common questions and issues to help troubleshooting.

[snnn (snnn)]

Q: How to force to single threaded execution
By default, session.run() uses all my computer's cores, how to limit use to a single thread only?

A:
It requires onnxruntime version >=1.3.0.

Please do both of the following:

• Build with openmp disabled or set environment variable OMP_NUM_THREADS to 1.
• Set the session options intra_op_num_threads and inter_op_num_threads to 1 each.

Python example:

#!/usr/bin/python3
os.environ["OMP_NUM_THREADS"] = "1"
import onnxruntime

opts = onnxruntime.SessionOptions()
opts.intra_op_num_threads = 1
opts.inter_op_num_threads = 1
opts.execution_mode = onnxruntime.ExecutionMode.ORT_SEQUENTIAL
ort_session = onnxruntime.InferenceSession('/path/to/model.onnx', sess_options=opts)

C++ example:

// initialize  enviroment...one enviroment per process
Ort::Env env(ORT_LOGGING_LEVEL_WARNING, "test");

// initialize session options if needed
Ort::SessionOptions session_options;
session_options.SetIntraOpNumThreads(1);
session_options.SetInterOpNumThreads(1);
#ifdef _WIN32
  const wchar_t* model_path = L"squeezenet.onnx";
#else
  const char* model_path = "squeezenet.onnx";
#endif

Ort::Session session(env, model_path, session_options);

[Nat Kershaw (MSFT) (natke)]

I've left a few wording suggestions. Overall, looks great, much improved!

[Faith Xu (faxu)]

/azp run Linux CPU CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,MacOS CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,MacOS NoContribops CI Pipeline,Linux CPU x64 NoContribops CI Pipeline,Windows CPU CI Pipeline

[azure-pipelines]

Azure Pipelines could not run because the pipeline triggers exclude this branch/path.