Release of 1.4.0

Major changes since 1.2.0 release:

1.3.1 -> 1.4.0
        - Stable release with API changes
        - *Tensor-filter subplugin API has been updated.*
        - Stability fixes & added unit test cases
        - C-API updates

1.3.0 -> 1.3.1
        - 1.3.1 is a devel version for 1.4.0 release.
        - Support C++ class custom filters. (C++ class as a NN model)
        - A tensor-filter instance may have multiple model files easily.
        - Updated env-var handling logic for non-Tizen devices.
        - Unit test: higher visibility & behavior correctness fixes.
        - Auto-generated test cases for tensor-filter sub-plugins (extensions).
        - Android/Java support with more convinient methods.
        - Support gcc9
        - Support openVino as a tensor-filter, allowing to accelerate with Intel NCS/Myriad.
        - Support NCSDK as a tensor-filter.
        - Support ARMNN as a tensor-filter. (support TF-Lite and Caffe models)
        - Reduce asserts and add error handling routines.
        - Support Androdi/SNAP as a tensor-filter.
        - Support hardware accelerators & 8-bit quantization for NNFW-Runtime & stabilize NNFW-Runtime support with test cases.
        - Support Edge-TPU and its runtime as a tensor-filter.
        - Filter subplugins refactored to have a single source file (.cc)
        - Support model reload
        - A lot of fixes for bugs found by Coverity, SVACE, and other static analysis tools

1.2.0 -> 1.3.0:
        - 1.3.0 is a devel version for 1.4.0 release.
        - From 1.2.0, 1.even.x is a release and 1.odd.x is a devel version.
        - When 1.3.x is "done", it will release 1.4.0 and move on to 1.5.0

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>

diff --git a/CHANGES b/CHANGES
index ec6c11b..b2b463d 100644 (file)
--- a/CHANGES
+++ b/CHANGES
@@ -1,3 +1,29 @@
+1.3.1 -> 1.4.0
+       - Stable release with API changes
+       - *Tensor-filter subplugin API has been updated.*
+       - Stability fixes & added unit test cases
+       - C-API updates
+
+1.3.0 -> 1.3.1
+       - 1.3.1 is a devel version for 1.4.0 release.
+       - Support C++ class custom filters. (C++ class as a NN model)
+       - A tensor-filter instance may have multiple model files easily.
+       - Updated env-var handling logic for non-Tizen devices.
+       - Unit test: higher visibility & behavior correctness fixes.
+       - Auto-generated test cases for tensor-filter sub-plugins (extensions).
+       - Android/Java support with more convinient methods.
+       - Support gcc9
+       - Support openVino as a tensor-filter, allowing to accelerate with Intel NCS/Myriad.
+       - Support NCSDK as a tensor-filter.
+       - Support ARMNN as a tensor-filter. (support TF-Lite and Caffe models)
+       - Reduce asserts and add error handling routines.
+       - Support Androdi/SNAP as a tensor-filter.
+       - Support hardware accelerators & 8-bit quantization for NNFW-Runtime & stabilize NNFW-Runtime support with test cases.
+       - Support Edge-TPU and its runtime as a tensor-filter.
+       - Filter subplugins refactored to have a single source file (.cc)
+       - Support model reload
+       - A lot of fixes for bugs found by Coverity, SVACE, and other static analysis tools
+
 1.2.0 -> 1.3.0:
        - 1.3.0 is a devel version for 1.4.0 release.
        - From 1.2.0, 1.even.x is a release and 1.odd.x is a devel version.

diff --git a/debian/changelog b/debian/changelog
index 15891aa..2884fea 100644 (file)
--- a/debian/changelog
+++ b/debian/changelog
@@ -1,3 +1,9 @@
+nnstreamer (1.4.0.0) unstable xenial bionic; urgency=medium
+
+  * 1.4.0 Release (Tensor-filter API updated)
+
+ -- MyungJoo Ham <myungjoo.ham@samsung.com>  Tue, 11 Feb 2020 19:07:14 +0900
+
 nnstreamer (1.3.1.0) unstable xenial bionic; urgency=medium
 
   * 1.3.1 development starts

diff --git a/jni/nnstreamer.mk b/jni/nnstreamer.mk
index 42658fd..e5372f3 100644 (file)
--- a/jni/nnstreamer.mk
+++ b/jni/nnstreamer.mk
@@ -8,7 +8,7 @@ ifndef GSTREAMER_ROOT_ANDROID
 $(error GSTREAMER_ROOT_ANDROID is not defined!)
 endif
 
-NNSTREAMER_VERSION  := 1.3.1
+NNSTREAMER_VERSION  := 1.4.0
 
 NNSTREAMER_GST_HOME := $(NNSTREAMER_ROOT)/gst/nnstreamer
 NNSTREAMER_EXT_HOME := $(NNSTREAMER_ROOT)/ext/nnstreamer

diff --git a/meson.build b/meson.build
index a667532..35d1057 100644 (file)
--- a/meson.build
+++ b/meson.build
@@ -2,7 +2,7 @@
 # If you are using Tizen 5.0+ or Ubuntu/Bionix+, you don't need to mind meson version.
 
 project('nnstreamer', 'c', 'cpp',
-  version: '1.3.1',
+  version: '1.4.0',
   license: ['LGPL'],
   meson_version: '>=0.50.0',
   default_options: [

diff --git a/packaging/nnstreamer.spec b/packaging/nnstreamer.spec
index 766c43d..1f57dd2 100644 (file)
--- a/packaging/nnstreamer.spec
+++ b/packaging/nnstreamer.spec
@@ -23,7 +23,7 @@ Summary:      gstreamer plugins for neural networks
 # 2. Tizen  : ./packaging/nnstreamer.spec
 # 3. Android: ./jni/nnstreamer.mk
 # 4. Meson  : ./meson.build
-Version:       1.3.1
+Version:       1.4.0
 Release:       0
 Group:         Applications/Multimedia
 Packager:      MyungJoo Ham <myungjoo.ham@samsung.com>
@@ -578,6 +578,9 @@ cp -r result %{buildroot}%{_datadir}/nnstreamer/unittest/
 %endif
 
 %changelog
+* Tue Feb 11 2020 MyungJoo Ham <myungjoo.ham@samsung.com>
+- Release of 1.4.0 (Tensor-filter API has been updated!)
+
 * Mon Feb 03 2020 MyungJoo Ham <myungjoo.ham@samsung.com>
 - Release of 1.3.1