Merge back from rel-0.2.1 (#422)

* Addl TPN updates (#403)

* Updated TPN

* Update batch_norm_op_test.cc

* Update ThirdPartyNotices.txt

* Update ThirdPartyNotices.txt

* Update readme with package links

* Update README.md

* Update README.md

* Update README.md

* Merged Ryan and TPN changes into single PR

* minor fix

* added mkldnn to GPU pipeline. Required by C# library as it is the default execution provider

* Bump up version number for 0.2.1 release (#420)

VERSION_NUMBER

@@ -1 +1 @@
-0.2.0
+0.2.1

docs/Versioning.md

@@ -30,6 +30,7 @@ opset version implemented in that release.
 
 | ONNX Runtime release version | ONNX opset version <br> implemented in this release | ONNX ML opset version <br> implemented in this release | Supported ONNX IR version |
 |------------------------------|--------------------|----------------------|------------------|
+| 0.2.1 | 8 | 1 | 3 |
 | 0.2.0 | 8 | 1 | 3 |
 | 0.1.5 | 8 | 1 | 3 |
 | 0.1.4 | 8 | 1 | 3 |

docs/python/README.rst

@@ -52,6 +52,11 @@ replaces *scikit-learn* to compute the predictions.
 Changes
 -------
 
+0.2.1
+^^^^^
+
+C-API, Linux support for Dotnet Nuget package, Cuda 10.0 support (patch to 0.2.0).
+
 0.2.0
 ^^^^^
 

onnxruntime/__init__.py

@@ -12,7 +12,7 @@ community, it supports traditional ML models as well
 as Deep Learning algorithms in the
 `ONNX-ML format <https://github.com/onnx/onnx/blob/master/docs/IR.md>`_.
 """
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 __author__ = "Microsoft"
 
 from onnxruntime.capi import onnxruntime_validation

package/rpm/onnxruntime.spec

@@ -1,5 +1,5 @@
 Name:           onnxruntime
-Version:        0.2.0
+Version:        0.2.1
 Release:        1%{?dist}
 Summary:        onnxruntime
 

setup.py

@@ -53,7 +53,7 @@ with open(README) as f:
 # Setup
 setup(
     name=package_name,
-    version='0.2.0',
+    version='0.2.1',
     description='ONNX Runtime Python bindings',
     long_description=long_description,
     author='Microsoft Corporation',