Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

* Upgrade presets for ONNX Runtime 1.3.0 #887

Merged
merged 2 commits into from
May 21, 2020
Merged

* Upgrade presets for ONNX Runtime 1.3.0 #887

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b22584c
* Upgrade presets for ONNX Runtime 1.3.0
EmergentOrder May 19, 2020
85b8646
Fix build on Mac and Windows
saudet May 21, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@

* Fix JPMS modules for CUDA, ARPACK-NG, GSL, SciPy, Gym, MXNet ([pull #880](https://github.com/bytedeco/javacpp-presets/pull/880) and [pull #881](https://github.com/bytedeco/javacpp-presets/pull/881))
* Build OpenBLAS with a `TARGET` even for `DYNAMIC_ARCH` to avoid SIGILL ([issue eclipse/deeplearning4j#8747](https://github.com/eclipse/deeplearning4j/issues/8747))
* Upgrade presets for Arrow 0.17.0, MKL-DNN 0.21.5, DNNL 1.4, NumPy 1.18.3, ONNX 1.7.0 ([pull #882](https://github.com/bytedeco/javacpp-presets/pull/882)), and their dependencies
* Upgrade presets for Arrow 0.17.0, MKL-DNN 0.21.5, DNNL 1.4, NumPy 1.18.3, ONNX 1.7.0 ([pull #882](https://github.com/bytedeco/javacpp-presets/pull/882)), ONNX Runtime 1.3.0 ([pull #887](https://github.com/bytedeco/javacpp-presets/pull/887)), and their dependencies
* Add `FullOptimization.h` allowing users to fully optimize LLVM modules ([pull #869](https://github.com/bytedeco/javacpp-presets/pull/869))

### April 14, 2020 version 1.5.3
Expand Down
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,7 @@ Each child module in turn relies by default on the included [`cppbuild.sh` scrip
* The Arcade Learning Environment 0.6.x https://github.com/mgbellemare/Arcade-Learning-Environment
* ONNX 1.7.0 https://github.com/onnx/onnx
* nGraph 0.26.0 https://github.com/NervanaSystems/ngraph
* ONNX Runtime 1.2.x https://github.com/microsoft/onnxruntime
* ONNX Runtime 1.3.0 https://github.com/microsoft/onnxruntime
* LiquidFun http://google.github.io/liquidfun/
* Qt 5.14.x https://download.qt.io/archive/qt/
* Mono/Skia 1.68.x https://github.com/mono/skia
Expand Down
10 changes: 5 additions & 5 deletions onnxruntime/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ Introduction
------------
This directory contains the JavaCPP Presets module for:

* ONNX Runtime 1.2.0 https://microsoft.github.io/onnxruntime/
* ONNX Runtime 1.3.0 https://microsoft.github.io/onnxruntime/

Please refer to the parent README.md file for more detailed information about the JavaCPP Presets.

Expand Down Expand Up @@ -34,29 +34,29 @@ We can use [Maven 3](http://maven.apache.org/) to download and install automatic
<modelVersion>4.0.0</modelVersion>
<groupId>org.bytedeco.onnxruntime</groupId>
<artifactId>cxxapisample</artifactId>
<version>1.5.3</version>
<version>1.5.4-SNAPSHOT</version>
<properties>
<exec.mainClass>CXXApiSample</exec.mainClass>
</properties>
<dependencies>
<dependency>
<groupId>org.bytedeco</groupId>
<artifactId>onnxruntime-platform</artifactId>
<version>1.2.0-1.5.3</version>
<version>1.3.0-1.5.4-SNAPSHOT</version>
</dependency>

<!-- Additional dependencies required to use CUDA and cuDNN -->
<dependency>
<groupId>org.bytedeco</groupId>
<artifactId>onnxruntime-platform-gpu</artifactId>
<version>1.2.0-1.5.3</version>
<version>1.3.0-1.5.4-SNAPSHOT</version>
</dependency>

<!-- Additional dependencies to use bundled CUDA and cuDNN -->
<dependency>
<groupId>org.bytedeco</groupId>
<artifactId>cuda-platform-redist</artifactId>
<version>10.2-7.6-1.5.3</version>
<version>10.2-7.6-1.5.4-SNAPSHOT</version>
</dependency>

</dependencies>
Expand Down
6 changes: 5 additions & 1 deletion onnxruntime/cppbuild.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ if [[ "$EXTENSION" == *gpu ]]; then
GPU_FLAGS="--use_cuda"
fi

ONNXRUNTIME=1.2.0
ONNXRUNTIME=1.3.0

mkdir -p "$PLATFORM$EXTENSION"
cd "$PLATFORM$EXTENSION"
Expand Down Expand Up @@ -58,6 +58,8 @@ sedinplace 's/Value(std::nullptr_t)/Value(std::nullptr_t = nullptr)/g' include/o
for f in java/src/main/native/*.c; do cp $f ${f}pp; done
for f in java/src/main/native/ai_onnxruntime_*.cpp; do sedinplace 's/#include "ai_onnxruntime_.*.h"/extern "C" {/g' $f; echo "}" >> $f; done
sedinplace 's/(\*jniEnv)->\(.*\)(jniEnv,/jniEnv->\1(/g' java/src/main/native/*.cpp
sedinplace 's/ WIN32/ _WIN32/g' java/src/main/native/*.cpp
sedinplace 's/FreeLibrary(/FreeLibrary((HMODULE)/g' java/src/main/native/*.cpp
sedinplace 's/(javaStrings/((jstring)javaStrings/g' java/src/main/native/*.cpp
sedinplace 's/(javaInputStrings/((jstring)javaInputStrings/g' java/src/main/native/*.cpp
sedinplace 's/(javaOutputStrings/((jstring)javaOutputStrings/g' java/src/main/native/*.cpp
Expand All @@ -78,6 +80,8 @@ which ctest3 &> /dev/null && CTEST="ctest3" || CTEST="ctest"

# install headers and libraries in standard directories
cp -r include/* ../include
cp -r orttraining/orttraining/models/runner/training_runner.h ../include
cp -r orttraining/orttraining/models/runner/training_util.h ../include
cp -r java/src/main/java/* ../java
cp ../build/Release/lib* ../lib || true
cp ../build/Release/Release/onnxruntime.dll ../bin || true
Expand Down
Loading