From eb833057d24d7f7c87a239352e2c2e3bdbac9283 Mon Sep 17 00:00:00 2001 From: Changming Sun Date: Thu, 20 Jun 2019 19:51:54 -0700 Subject: [PATCH] Update Model_Test.md (#1264) --- docs/Model_Test.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/docs/Model_Test.md b/docs/Model_Test.md index 0a298b4ad3..33821a02a1 100644 --- a/docs/Model_Test.md +++ b/docs/Model_Test.md @@ -9,8 +9,8 @@ You should have: You can get onnx python package from [pypi](https://pypi.org/). However, if you are a onnxruntime developer, you may need to work on a cutting edge ONNX version. In this case, you need to build and install ONNX from source code. ### Install ONNX from source code -1. (windows) set ONNX_ML=1 - (linux) export ONNX_ML=1 +1. (windows) set ONNX_ML=1 + (linux) export ONNX_ML=1 2. Install protobuf and put protoc into your PATH environment. When you compile protobuf, it's better to only enable the static libraries. 3. run "python setup.py bdist_wheel" and "pip install dist/*.whl" @@ -20,9 +20,9 @@ e.g. python3 -m onnx.backend.test.cmd_tools generate-data -o C:\testdata -## Get the onnx model zoo models -Download the files from: https://github.com/onnx/models. Unzip them. -(TODO: put a full copy on Azure blob, instead of downloading these files from different sources individually) +## Get more models +Download https://onnxruntimetestdata.blob.core.windows.net/models/20190419.zip and unzip it. + # Compile onnx_test_runner and run the tests onnx_test_runner is a C++ program. Its source code is in onnxruntime/test/onnx directory. @@ -39,9 +39,9 @@ Options: -x: Use parallel executor, default (without -x): sequential executor. -h: help -e.g. -//run the tests under C:\testdata dir and enable CUDA provider +e.g. +//run the tests under C:\testdata dir and enable CUDA provider $ onnx_test_runner -e cuda C:\testdata -//run the tests sequentially. It would be easier to debug +//run the tests sequentially. It would be easier to debug $ onnx_test_runner -c 1 -j 1 C:\testdata