platform/upstream/nnstreamer.git
5 years ago[Example] remove common header
Jaeyun [Wed, 12 Dec 2018 03:57:27 +0000 (12:57 +0900)]
[Example] remove common header

In custom filter examples, remove tensor-common header.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Test] add plugin path
Jaeyun [Wed, 12 Dec 2018 07:34:29 +0000 (16:34 +0900)]
[Test] add plugin path

set plugin path for the unittest using nnstreamer elements.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter] add condition to check input/output name
HyoungjooAhn [Tue, 11 Dec 2018 04:05:53 +0000 (13:05 +0900)]
[Filter] add condition to check input/output name

check the existance of the value before free for input/output name properties

Signed-off-by: HyoungjooAhn <hello.ahnn@gmail.com>
5 years ago[Transform/Orc] remove unnecessary memcpy
Jaeyun Jung [Mon, 10 Dec 2018 14:50:12 +0000 (23:50 +0900)]
[Transform/Orc] remove unnecessary memcpy

Related issue: #975

In arith mode, copying input array to output is unnecessary.
To fix this, add source in orc functions and set the data ptr for each operator.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Meson/CustomFilter] link custom-filter obj
Jaeyun [Mon, 10 Dec 2018 10:27:33 +0000 (19:27 +0900)]
[Meson/CustomFilter] link custom-filter obj

In example custom-filter, link custom-filter.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter/TF] fix warning and check dependency
Jaeyun [Mon, 10 Dec 2018 04:53:48 +0000 (13:53 +0900)]
[Filter/TF] fix warning and check dependency

1. check dependency of protobuf, tensorflow
2. fix build warning and code indentation

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter] Build Error Fix (gcc > 6)
MyungJoo Ham [Sat, 8 Dec 2018 08:58:05 +0000 (17:58 +0900)]
[Filter] Build Error Fix (gcc > 6)

Recent code commit has introduced the following errors in
modern gcc:

```
[ 20%] Building C object gst/tensor_filter/CMakeFiles/tensor_filterOBJ.dir/tensor_filter.c.o
cd /<<PKGBUILDDIR>>/build/gst/tensor_filter && /usr/bin/cc -DENABLE_TENSORFLOW_LITE -DHAVE_ORC=1 -DVERSION=\"0.1.0\" -I/<<PKGBUILDDIR>>/gst/nnstreamer -isystem /usr/include/gstreamer-1.0 -isystem /usr/include/glib-2.0 -isystem /usr/lib/x86_64-linux-gnu/glib-2.0/include -isystem /usr/include/orc-0.4  -g -O2 -fdebug-prefix-map=/<<PKGBUILDDIR>>=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2  -Wall -Werror -fPIC -g -std=c89  -Wno-sign-compare   -o CMakeFiles/tensor_filterOBJ.dir/tensor_filter.c.o   -c /<<PKGBUILDDIR>>/gst/tensor_filter/tensor_filter.c
In file included from /usr/lib/x86_64-linux-gnu/glib-2.0/include/glibconfig.h:9:0,
                 from /usr/include/glib-2.0/glib/gtypes.h:32,
                 from /usr/include/glib-2.0/glib/galloca.h:32,
                 from /usr/include/glib-2.0/glib.h:30,
                 from /usr/include/gstreamer-1.0/gst/gstinfo.h:27,
                 from /<<PKGBUILDDIR>>/gst/tensor_filter/tensor_filter.c:57:
/<<PKGBUILDDIR>>/gst/tensor_filter/tensor_filter.c: In function ‘gst_tensor_filter_set_property’:
/<<PKGBUILDDIR>>/gst/tensor_filter/tensor_filter.c:560:51: error: comparison between pointer and zero character constant [-Werror=pointer-compare]
           g_assert (prop->input_meta.info[i].name != '\0');
                                                   ^
/<<PKGBUILDDIR>>/gst/tensor_filter/tensor_filter.c:560:21: note: did you mean to dereference the pointer?
           g_assert (prop->input_meta.info[i].name != '\0');
                     ^
/<<PKGBUILDDIR>>/gst/tensor_filter/tensor_filter.c:581:52: error: comparison between pointer and zero character constant [-Werror=pointer-compare]
           g_assert (prop->output_meta.info[i].name != '\0');
                                                    ^
/<<PKGBUILDDIR>>/gst/tensor_filter/tensor_filter.c:581:21: note: did you mean to dereference the pointer?
           g_assert (prop->output_meta.info[i].name != '\0');
                     ^
```

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Meson] add unittest
Jaeyun [Fri, 7 Dec 2018 10:40:57 +0000 (19:40 +0900)]
[Meson] add unittest

check dependency of gtest and add exe to run unittest
(command '$ ninja test' will build and start gtest)

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Meson] code clean
Jaeyun [Fri, 7 Dec 2018 10:34:42 +0000 (19:34 +0900)]
[Meson] code clean

1. rename nnstreamer include path and dependencies
2. link proper objs
3. fix indentation

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Meson] rename gst/glib dependency
Jaeyun [Fri, 7 Dec 2018 07:55:03 +0000 (16:55 +0900)]
[Meson] rename gst/glib dependency

rename dependencies of gstreamer, glib (follows gst-base)

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Converter] code clean
Jaeyun Jung [Sat, 8 Dec 2018 02:05:47 +0000 (11:05 +0900)]
[Converter] code clean

1. move function video-stride to converter.
2. move mainpage tag to nnstreamer.c.
3. in nnstreamer.c, include config header for orc feature.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter/Tensorflow] upload tensorflow draft
HyoungjooAhn [Tue, 4 Dec 2018 07:14:25 +0000 (16:14 +0900)]
[Filter/Tensorflow] upload tensorflow draft

this is a draft of tensorflow filter

Signed-off-by: HyoungjooAhn <hello.ahnn@gmail.com>
5 years ago[Test] add more testcases
Jaeyun [Thu, 6 Dec 2018 10:12:13 +0000 (19:12 +0900)]
[Test] add more testcases

Using gst-harness, add testcases for the property acceleration in tensor-transform.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Transform/Orc] code clean to prepare meson
Jaeyun [Fri, 7 Dec 2018 03:50:57 +0000 (12:50 +0900)]
[Transform/Orc] code clean to prepare meson

1. Orc feature is defined in config, include config header to prepare meson build.
2. Set default property value with orc feature.
3. Add log message to indicate orc acceleration.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Meson] include orc
Jaeyun [Fri, 7 Dec 2018 04:14:06 +0000 (13:14 +0900)]
[Meson] include orc

1. set base-args and include orc features
2. check orc lib and orcc, and generate orc files in tensor-transform

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Transform] apply orc functions
Jaeyun [Wed, 5 Dec 2018 08:14:33 +0000 (17:14 +0900)]
[Transform] apply orc functions

1. add flags to check orc support
2. add property to set orc acceleration
3. apply orc functions for arith/typecast

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Orc] update functions for divide, typecast
Jaeyun [Wed, 5 Dec 2018 08:10:32 +0000 (17:10 +0900)]
[Orc] update functions for divide, typecast

1. add function _div (float and double only)
2. add typecast to same type (copy input array to output)
3. update opcode for typecast

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter] fix cmake typo about tensorflow
HyoungjooAhn [Wed, 5 Dec 2018 11:27:16 +0000 (20:27 +0900)]
[Filter] fix cmake typo about tensorflow

fix typos at CMakeLists.txt of tensor_filter

Signed-off-by: HyoungjooAhn <hello.ahnn@gmail.com>
5 years ago[Orc] add functions for typecast
Jaeyun [Tue, 4 Dec 2018 10:16:47 +0000 (19:16 +0900)]
[Orc] add functions for typecast

1. add typecast functions
2. add testcases for typecast

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Bug Fix] fix unused variables bug
HyoungjooAhn [Tue, 4 Dec 2018 11:43:05 +0000 (20:43 +0900)]
[Bug Fix] fix unused variables bug

it resolves #957 about unused variables

Signed-off-by: HyoungjooAhn <hello.ahnn@gmail.com>
5 years ago[Tool] Added a front-end GUI toolkit
Geunsik Lim [Mon, 3 Dec 2018 11:50:07 +0000 (20:50 +0900)]
[Tool] Added a front-end GUI toolkit

Fixed issue #878.

This commit is to provide a front-end GUI application to connect
tools such as tracing, debugging, profiling packages.

After doing a packaging work of back-end applications, the each menu
is going to be interconnected each other.

**Changes proposed in this PR:**
1. Added front-end GUI application

Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
5 years ago[Orc] update function for operator add/mul
Jaeyun [Mon, 3 Dec 2018 08:31:35 +0000 (17:31 +0900)]
[Orc] update function for operator add/mul

1. add functions for operator add/mul
2. add functional testcases for orc

TODO :
1. support int64
2. add typecast functions

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years agoStart of 0.1.0 rc1 development
MyungJoo Ham [Mon, 3 Dec 2018 06:33:04 +0000 (15:33 +0900)]
Start of 0.1.0 rc1 development

This commit marks the start of 0.1.0 rc1 development.

The version is jumped to 0.1.0 as it has now enough
number of features for a few real products/applications
and we have full CI/CD support.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years agoRelease of v0.0.3 v0.0.3
MyungJoo Ham [Mon, 3 Dec 2018 05:45:54 +0000 (14:45 +0900)]
Release of v0.0.3

As Sprint 1811A and 1811B conclude along with Coverity/SVACE issues cleared, 0.0.3 is hereby released.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Common/Subplugin] Internal API to handle subplugins
MyungJoo Ham [Tue, 27 Nov 2018 12:28:11 +0000 (21:28 +0900)]
[Common/Subplugin] Internal API to handle subplugins

Any subplugin-using elements may call get_subplugin () to
get internal data (set of callbacks) of the subplugin.

Next Step: modify tensor_decoder to use nnstreamer_subplugin.h
and test with it.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Filter] update macros to avoid assertion
Jaeyun [Fri, 30 Nov 2018 11:10:06 +0000 (20:10 +0900)]
[Filter] update macros to avoid assertion

1. check fw and fw-function before calling in macro
2. return true in _start() and _stop() vmethods

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Decoder] Coverity issue 1036581 fix
MyungJoo Ham [Mon, 3 Dec 2018 00:56:47 +0000 (09:56 +0900)]
[Decoder] Coverity issue 1036581 fix

Coverity wants to check the return value of
_tensordec_process_plugin_options.

Let't check and log if there is an unwanted return value.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Transform] limit typecast in arith mode
Jaeyun Jung [Fri, 30 Nov 2018 16:15:51 +0000 (01:15 +0900)]
[Transform] limit typecast in arith mode

set typecast option only in the first

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Orc] initial commit to add orc file
Jaeyun [Thu, 29 Nov 2018 08:30:25 +0000 (17:30 +0900)]
[Orc] initial commit to add orc file

add command to generate -orc c and h files in tensor-transform

TODO update orc functions and link to tensor-transform

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[meson] add meson.build for example apps and custom filter
sewon.oh [Thu, 29 Nov 2018 08:08:31 +0000 (17:08 +0900)]
[meson] add meson.build for example apps and custom filter

For ssat and example, add meson.build

Signed-off-by: sewon.oh <sewon.oh@samsung.com>
5 years ago[Filter] Support pipeline stop and go.
MyungJoo Ham [Fri, 30 Nov 2018 02:28:42 +0000 (11:28 +0900)]
[Filter] Support pipeline stop and go.

Pipeline Stop does not always mean pipeline close.
A pipeline may be paused and resumed (stop and start).
Thus, do not clean up internal data structure for stop.

Instead just notify the plugins of the events with
callbacks.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Decoder] Do not die for option errors.
MyungJoo Ham [Thu, 29 Nov 2018 02:26:11 +0000 (11:26 +0900)]
[Decoder] Do not die for option errors.

With dynamic pipeline configurations, the mode/option
properties may become incomplete. Do not die for such status
if the pipeline is not active.

This is critical for GUI toolkits.

Fixes a subitem of #827

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Repo] Add runTest.sh for the dummy LSTM Test
jijoong.moon [Wed, 28 Nov 2018 06:05:38 +0000 (15:05 +0900)]
[Repo] Add runTest.sh for the dummy LSTM Test

- Add python script to generate input stream & golden data.
- Add runTest.sh to run.

                        repository
                      +-----------+
+---------------------|  slot 1   |<-------------------- ---+
|                     +-----------+                         |
|  +------------------|  slot 0   |<----------------------+ |
|  |                  +-----------+                       | |
|  |                                                      | |
|  |                  +---+   +---+  +---+                | |
|  +-->repo_src:0 --->|   |-->|   |->|   |-->repo_sink:0 -+ |
+----->repo_src:1 --->| M |   | F |  | D |-->repo_sink:1 ---+
       filesrc(new)-->|   |   |   |  |   |  |
                      +---+   +---+  +---+  -->out_%1d.log

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo] Split Cond variable to use push and pull the data
jijoong.moon [Tue, 27 Nov 2018 07:57:26 +0000 (16:57 +0900)]
[Repo] Split Cond variable to use push and pull the data

In order to keep the synchronization better, two cond variable is
used.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Common/Conf] Fix coverity issue, uninitialized pointer read
MyungJoo Ham [Fri, 30 Nov 2018 02:43:20 +0000 (11:43 +0900)]
[Common/Conf] Fix coverity issue, uninitialized pointer read

With auto-ptr, it tries to access read the pointer.
Thus, it should be initialized somehow.

Fixes Coverity Issue 1036166

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Repo] Fix the test bug
jijoong.moon [Thu, 29 Nov 2018 11:00:50 +0000 (20:00 +0900)]
[Repo] Fix the test bug

Caps for the tensor_reposrc has bug. unit8 should be uint8.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo] Add MIME to limit for the tensor/tensors only for now.
jijoong.moon [Tue, 27 Nov 2018 00:34:10 +0000 (09:34 +0900)]
[Repo] Add MIME to limit for the tensor/tensors only for now.

Add MIME check becase currently onlye tensor/tensors are supported
for now.

**Changes proposed in this PR:**
- Added TOC generator for README.md

Resolves:

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo] Fix bug return without releasing lock
jijoong.moon [Thu, 29 Nov 2018 02:05:47 +0000 (11:05 +0900)]
[Repo] Fix bug return without releasing lock

tensor_repo.c::gst_tensor_repo_add_repodata, unlock should be used
before return.

Resolves: #933

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[DummyLSTM] Add Dummy LSTM custom example
jijoong.moon [Wed, 28 Nov 2018 02:33:42 +0000 (11:33 +0900)]
[DummyLSTM] Add Dummy LSTM custom example

Add Dymmy LSTM custom example. Two input stream and two outputstream.
First input is recursion and Second input is new input stream. First
output is recursion stream which is matched with first inputstream and
the second output stream is matched with second input stream.

 - in2_tmp0 = (in2+in1)/2 (in2_tmp0 : mimic sigmoid)
 - in2_tmp1 = tanh(in2)
 - in0 = in0 x in2_tmp0
 - in0 = in0 + (in2_tmp0 x in2_tmp1)
 - out0 = in0
 - out1 = in1 = (tanh(in0) x in2_tmp0)

                     +------------+
         in0 ------->|            |----> out0
         in1 ------->| dummy LSTM |----> out1
         in2 (new)-->|            |  |
                     +------------+  +--> out (equal out1)

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo/RNN] Add dummy RNN test case
jijoong.moon [Mon, 26 Nov 2018 06:42:53 +0000 (15:42 +0900)]
[Repo/RNN] Add dummy RNN test case

In order to test recurtion & Tensor repo, dumm RNN test case is added.

It generate 10 4x4x4x1 tensors and use first input of RNN. Second
input for RNN is generated by tensor_reposrc which take from
Tensor_Repo. Of course, the first tensor of tensor_reposrc is filled
with zero. After simple calcution,
RNN (build/nnstreamer_exampel/custom_exampe_RNN/libdummyRNN.so ) push
the result and tensor_reposink upload this output into Tensor_Repo.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Common/Conf] Close g_dir_open instance.
MyungJoo Ham [Thu, 29 Nov 2018 00:39:32 +0000 (09:39 +0900)]
[Common/Conf] Close g_dir_open instance.

The returned object must be closed.

Reported-by: Wook Song <wook16.song@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Repo] Add testcases for tensor_reposink/tesnor_reposrc
jijoong.moon [Fri, 23 Nov 2018 02:12:06 +0000 (11:12 +0900)]
[Repo] Add testcases for tensor_reposink/tesnor_reposrc

3 testcases are added.

- ID 0 : 10 stream --> tensor_reposink --> (Repo) --> tensor_reposrc

- ID 0 : 10 stream --> tensor_reposink --> (Repo) --> tensor_reposrc
  ID 1 : 10 stream --> tensor_reposink --> (Repo) --> tensor_reposrc

- ID 0 : 10 stream --> tensor_reposink --> (Repo) --> tensor_reposrc
  ID 1 : 10 stream --> tensor_reposink --> (Repo) --> tensor_reposrc
  ID 2 : 10 stream --> tensor_reposink --> (Repo) --> tensor_reposrc

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Orc] add init function
Jaeyun [Wed, 28 Nov 2018 07:19:48 +0000 (16:19 +0900)]
[Orc] add init function

add orc_init to initialize orc library.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Transform/Orc] replace memcpy
Jaeyun [Tue, 27 Nov 2018 09:39:22 +0000 (18:39 +0900)]
[Transform/Orc] replace memcpy

1. define macro nns_memcpy/nns_memset
2. include liborc and use orc_memcpy instead in plugin tensor-transform and tensor-aggregator.

TODO check cmake to use orc lib

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Repo] Add & Modify for meson.build for tensor_repo
jijoong.moon [Tue, 27 Nov 2018 04:57:27 +0000 (13:57 +0900)]
[Repo] Add & Modify for meson.build for tensor_repo

- Add meson.build for tensor_reposrc & tensor_reposink
- Modify meson.build in nnstreamer root dir.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Common/Conf] API to get conf values.
MyungJoo Ham [Mon, 26 Nov 2018 10:24:32 +0000 (19:24 +0900)]
[Common/Conf] API to get conf values.

We are going to allow users to configure paths of
filters, decoders, and custom filters.

This is the API skeletons for the first step of #804

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[CMake] Do not download anything during build.
MyungJoo Ham [Mon, 26 Nov 2018 07:41:53 +0000 (16:41 +0900)]
[CMake] Do not download anything during build.

Let the user download the model at run-time with the given scripts.
They will be able to do so after #909

With #909, this concludes #866

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Filter/CMAKE] Remove unnecessary message printing out
Wook Song [Mon, 26 Nov 2018 10:08:31 +0000 (19:08 +0900)]
[Filter/CMAKE] Remove unnecessary message printing out

This patch removes unnecessary message printed out by the cmake script
in the filter directory.

Signed-off-by: Wook Song <wook16.song@samsung.com>
5 years ago[Repo] Use GST_DEBUG instead of silent_debug
jijoong.moon [Fri, 23 Nov 2018 02:53:29 +0000 (11:53 +0900)]
[Repo] Use GST_DEBUG instead of silent_debug

Replace custom debug/error/warning macro to GST_*

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo] Change GstTensorData to GstTensorRepoData
jijoong.moon [Fri, 23 Nov 2018 07:49:28 +0000 (16:49 +0900)]
[Repo] Change GstTensorData to GstTensorRepoData

In order not to confuse, change the name GstTensorData to
GstTensorRepoData.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo] Change Element Name & Fix Sync Bug when EOS
jijoong.moon [Fri, 23 Nov 2018 00:33:44 +0000 (09:33 +0900)]
[Repo] Change Element Name & Fix Sync Bug when EOS

- Element Name is changed.
  . tensor_repopush -> tensor_reposink
  . tensor_repopop  -> tensor_reposrc

- There is hanging bug when reposrc is tryig to get buffer and
  reposink set eos signal meanwhile. It is fixed by double check eos
  signal during cond wait.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo/Push-Pop] Implement NYI part of tensor_reppop.
jijoong.moon [Thu, 22 Nov 2018 06:02:28 +0000 (15:02 +0900)]
[Repo/Push-Pop] Implement NYI part of tensor_reppop.

- Implement NYI part of tensor_reppop. It's parent element is
  GstPushSrcClass and it's relevant vm functions are implemented such
  as (create*).

- Several utility functions of tensor_repo is newly implemented.

- Some changes are made to handle thread synchronization.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo/Pop] Tensor_RepoPop Draft
jijoong.moon [Tue, 20 Nov 2018 10:03:29 +0000 (19:03 +0900)]
[Repo/Pop] Tensor_RepoPop Draft

This is the the anthor part to complete the tensor
repo. tensor_repopop get the tensor repo data.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo/Push] Use Has Table to handle repo & add slot_id property
jijoong.moon [Wed, 21 Nov 2018 01:46:32 +0000 (10:46 +0900)]
[Repo/Push] Use Has Table to handle repo & add slot_id property

- Instead of single linked list, Hash table is used to manage repo's
  data. Hash Table is "key [slot_id], GstTensorData*" where slot_id is
  given by user when the tensor_repopush is used.

- Slot Id is added to use as key for hash table. This should be same
  with tensor_repopop element. "tensor_repopop" will withdraw the data
  according to this slot_id.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[CMake] Install example apps to "EXAMPLE_EXEC_PREFIX".
MyungJoo Ham [Mon, 26 Nov 2018 07:16:31 +0000 (16:16 +0900)]
[CMake] Install example apps to "EXAMPLE_EXEC_PREFIX".

Do not install example apps into /usr/bin, but to /usr/lib/nnstreamer/bin/

Partially addresses the third subitem of #866

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Filter] Fix coverity issue, pointer out of scope.
MyungJoo Ham [Mon, 26 Nov 2018 05:18:52 +0000 (14:18 +0900)]
[Filter] Fix coverity issue, pointer out of scope.

This fixes the coverity issue, pointer out of scope.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Meson] Support Ubuntu/Xenial and Tizen.
MyungJoo Ham [Mon, 26 Nov 2018 05:09:24 +0000 (14:09 +0900)]
[Meson] Support Ubuntu/Xenial and Tizen.

1. Both Tizen and Ubuntu/Xenial does not support meson 0.47.
Lower down the Meson version requirement.
2. Add meson support for repo-push

Fixes #897

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Example] remove unnecessary caps-filter
Jaeyun [Mon, 26 Nov 2018 04:34:07 +0000 (13:34 +0900)]
[Example] remove unnecessary caps-filter

1. remove caps-filter between tensor-converter and tensor-filter. (tensor-converter will get peer caps and set possible caps.)
2. update download link to get tf-lite model

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Converter] get possible caps from downstream
Jaeyun [Wed, 21 Nov 2018 10:41:34 +0000 (19:41 +0900)]
[Converter] get possible caps from downstream

When received caps query, get the possible caps of peer pad and convert it to media caps.
Related issue #818

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter/TFLite] code clean
HyoungjooAhn [Mon, 26 Nov 2018 10:45:00 +0000 (19:45 +0900)]
[Filter/TFLite] code clean

move unused method to private and remove extern methods

Signed-off-by: HyoungjooAhn <hello.ahn@samsung.com>
5 years ago[PkgConfig] Update 'Libs' field
Wook Song [Mon, 26 Nov 2018 01:29:40 +0000 (10:29 +0900)]
[PkgConfig] Update 'Libs' field

This patch fills the 'Libs' field in the pkg-config file.

Signed-off-by: Wook Song <wook16.song@samsung.com>
5 years ago[Dist/Debian] Change installation directories based on multiarch scheme
Wook Song [Mon, 26 Nov 2018 01:25:22 +0000 (10:25 +0900)]
[Dist/Debian] Change installation directories based on multiarch scheme

This patch, based on the multiarch directory scheme of Debian/Ubuntu,
chages the installation directories of nnstreamer and nnstreamer
development packages.

Signed-off-by: Wook Song <wook16.song@samsung.com>
5 years ago[Filter/TFLite] Move shared object of tflitecore to libdir
Wook Song [Mon, 26 Nov 2018 01:17:58 +0000 (10:17 +0900)]
[Filter/TFLite] Move shared object of tflitecore to libdir

This patch moves the shared object of tflitecore,
libtensor_filter_tflitecore.so, from GST_PLUGIN_PATH to INSTALL_LIBDIR.

Signed-off-by: Wook Song <wook16.song@samsung.com>
5 years ago[Common] build error fix for ubuntu/example.
MyungJoo Ham [Mon, 26 Nov 2018 07:27:46 +0000 (16:27 +0900)]
[Common] build error fix for ubuntu/example.

There is a missing header in typedef header.
Without stdint.h, you won't be able to find "uint8_t".

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Example] Change LSTM to RNN
jijoong.moon [Mon, 26 Nov 2018 01:40:42 +0000 (10:40 +0900)]
[Example] Change LSTM to RNN

It is more like RNN rather than LSTM. RNN is better name for this testcase.

**Changes proposed in this PR:**
- Change directory name and files LSTM to RNN

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Filter] Update reaction to tensor dimension errors.
MyungJoo Ham [Fri, 23 Nov 2018 02:54:14 +0000 (11:54 +0900)]
[Filter] Update reaction to tensor dimension errors.

When input/output tensor dimension is not compatible,
don't exit with assert, let gstreamer handle the rest.

This will help looking at the issue of #886

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Repo/Push] Use Has Table to handle repo & add slot_id property
jijoong.moon [Wed, 21 Nov 2018 01:46:32 +0000 (10:46 +0900)]
[Repo/Push] Use Has Table to handle repo & add slot_id property

- Instead of single linked list, Hash table is used to manage repo's
  data. Hash Table is "key [slot_id], GstTensorData*" where slot_id is
  given by user when the tensor_repopush is used.

- Slot Id is added to use as key for hash table. This should be same
  with tensor_repopop element. "tensor_repopop" will withdraw the data
  according to this slot_id.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[Repo/Push] Rename Repo_sink to repopush and implement NYI
jijoong.moon [Tue, 20 Nov 2018 09:39:44 +0000 (18:39 +0900)]
[Repo/Push] Rename Repo_sink to repopush and implement NYI

**Changes proposed in this PR:**

- Rename tensor_reposink to tensor_repopush. It seems more reseanable.

- Split tensor_repo.h and tensor_repo.c for the repo utility function
  and place them in gst/nnstreamer.

- Implement render fucntion to push GstBuffer into repo.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[TensorRepo/Sink] TensorRepo_Sink Draft
jijoong.moon [Mon, 19 Nov 2018 11:15:08 +0000 (20:15 +0900)]
[TensorRepo/Sink] TensorRepo_Sink Draft

In order to enable the recursion, we may need this tensor
repository. In order to feed or get the tensor(s) to/from tensor
repository, we need tensor_reposink and tensor_reposrc element.

This PR includes initial draft for tensor_repo data structure and
tensor_reposink.

**Self evaluation:**
1. Build test:  [X]Passed [ ]Failed [ ]Skipped
2. Run test:  [ ]Passed [ ]Failed [X]Skipped

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
5 years ago[CI] update config files.
sewon.oh [Fri, 23 Nov 2018 05:38:45 +0000 (14:38 +0900)]
[CI] update config files.

For ci server, update config files.

Signed-off-by: sewon.oh <sewon.oh@samsung.com>
5 years ago[Decoder] fix coverity issue
Jaeyun [Fri, 23 Nov 2018 03:05:39 +0000 (12:05 +0900)]
[Decoder] fix coverity issue

1. init struct detected-object
2. remove macro with no effect (unsigned compare)

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years agoTrivial Typo Fix
MyungJoo Ham [Fri, 23 Nov 2018 05:27:03 +0000 (14:27 +0900)]
Trivial Typo Fix

We will be using typefind soon along with tensor_save/load.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Test] update git ignore
Jaeyun [Thu, 22 Nov 2018 05:11:27 +0000 (14:11 +0900)]
[Test] update git ignore

add .xraw file and change temp file format in unit-test

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Common] remove macro to print log
Jaeyun Jung [Wed, 21 Nov 2018 15:51:04 +0000 (00:51 +0900)]
[Common] remove macro to print log

nnstreamer elements use gst/glib macro to print logs.
remove unnecessary macros in common header.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter/TFLite] change log format
Jaeyun Jung [Wed, 21 Nov 2018 15:46:24 +0000 (00:46 +0900)]
[Filter/TFLite] change log format

1. change log format (use glib)
2. update indentation

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years agoChange log format
Jaeyun [Wed, 21 Nov 2018 12:53:11 +0000 (21:53 +0900)]
Change log format

Use common gst macros to print debug logs.

TODO: remove log macro in common header

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Example] update arithmetic for normalization
Jaeyun [Fri, 23 Nov 2018 04:54:22 +0000 (13:54 +0900)]
[Example] update arithmetic for normalization

update arith mode in tensor-transform to normalize

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Transform/Typecast] Fix float -> unsigned bug
MyungJoo Ham [Thu, 22 Nov 2018 07:20:08 +0000 (16:20 +0900)]
[Transform/Typecast] Fix float -> unsigned bug

It is supposed to do float -> signed -> unsigned.
This is regression due to the omitted per-pr arm testing :(

Fixes #882

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Example] ObjectDetection(SSD) with Gst-Launch
MyungJoo Ham [Wed, 21 Nov 2018 06:11:22 +0000 (15:11 +0900)]
[Example] ObjectDetection(SSD) with Gst-Launch

With the new decoder/bounding-box, we can do
object-detection + labeling in gst-launch with
visualization.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Decoder] Fix cap negotiation bug
MyungJoo Ham [Wed, 21 Nov 2018 05:46:01 +0000 (14:46 +0900)]
[Decoder] Fix cap negotiation bug

Decoder::Main had been saying that it cannot accept other/tensors.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Decoder] Add bounding box plugin
MyungJoo Ham [Thu, 15 Nov 2018 08:27:40 +0000 (17:27 +0900)]
[Decoder] Add bounding box plugin

1. The basic mechanism is imported from nnstreamer_example/example_object_detection.
2. The mechanism is updated to support
    - Different tensor types (it supports integers and double as well if the two tensors have the same type)
    - Input tensors may have smaller number of detections (less than DETECTION_MAX)
    - A few performance updates to execute less loops
3. No more dependencies on graphics library for drawing boxes or rendering text
4. Imported "font.c" of Silicon Graphics Inc 1992 to render text. The license is open for any purpose as long as the license statement is in tact.
5. Tested with a basic case
```
gst-launch-1.0 --gst-debug=2  \
        v4l2src name=cam_src ! videoscale ! videoconvert ! video/x-raw,width=640,height=480,format=RGB,framerate=30/1 ! tee name=t \
        t. ! queue leaky=2 max-size-buffers=2 ! videoscale ! video/x-raw,width=300,height=300,format=RGB ! tensor_converter ! \
                tensor_transform mode=arithmetic option=typecast:float32,add:-127,mul:0.007843 ! \
                tensor_filter framework=tensorflow-lite model=ssd_mobilenet_v2_coco.tflite ! \
                tensor_decoder mode=bounding_boxes option1=ssd option2=coco_labels_list.txt option3=box_priors.txt option4=640:480 option5=300:300 ! \
                compositor name=mix sink_0::zorder=2 sink_1::zorder=1 ! videoconvert ! ximagesink \
        t. ! queue leaky=2 max-size-buffers=10 ! mix.
```

In later PRs, we need
- Test cases (and probably some fixes)
- Hardcode the pre-processing results of font.h, then remove the "rasters" from font.h

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years agoDIST: Fix broken OBS build log of unit tests
MyungJoo Ham [Wed, 21 Nov 2018 09:31:28 +0000 (18:31 +0900)]
DIST: Fix broken OBS build log of unit tests

SSAT writes colored text by default.
Apply -n (nocolor) in .spec so that SSAT writes non-colored results,
which will no more break OBS build logs.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years agoCMake Build Script Clean Up
MyungJoo Ham [Wed, 21 Nov 2018 07:40:12 +0000 (16:40 +0900)]
CMake Build Script Clean Up

- Remove libcommon.a from the project
- Remove multi-binary support

Fixes two subissues of the three in #866

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years ago[Test] Suppress log messages for unit testing
MyungJoo Ham [Wed, 21 Nov 2018 10:20:28 +0000 (19:20 +0900)]
[Test] Suppress log messages for unit testing

- s/silent=false/silent=true/
- s/--gst-debug=[a-zA-Z_\:0-9]* / /

Fixes #872

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years agoTools/gst-instruments: Added how to profile a bottleneck among elements
Geunsik Lim [Wed, 21 Nov 2018 04:51:40 +0000 (13:51 +0900)]
Tools/gst-instruments: Added how to profile a bottleneck among elements

Fixed issue #132 (Epic: Performance- Profiling)

This commit is to append how to use a gst-instruments tool in order to
do a profiling for performance optimization of NNStreamer.
This guide is experimented on Ubuntu 16.04 x86_64 distribution.

**Changes proposed in this PR:**
1. Added gst-top to display a performance report in real time such as top, perf-top
2. Added gst-report-1.0 to generate the trace file the below two goals as following:
   a. It display CPU usage, time usage, and execution time amon the elements.
   b. It generate a performance graph from a GStreamer pipeline.
3. Added screenshot of gst-top, gst-report, and generating pipeline graph

Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
5 years agoTests: Fixed incorrect link
Geunsik Lim [Wed, 21 Nov 2018 07:47:53 +0000 (16:47 +0900)]
Tests: Fixed incorrect link

It is trivial. This commit is to fix incorrect link.

Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
5 years agoTools: Add how to use GST_DEBUG to get debug messages
Geunsik Lim [Tue, 20 Nov 2018 04:32:39 +0000 (13:32 +0900)]
Tools: Add how to use GST_DEBUG to get debug messages

Fixed issue #132 (Epic: Performance - Debugging)

This commit is to append how to use environment variable GST_DEBUG to
get more debug messages for debugging of NNStreamer.

**Changes proposed in this PR:**
* Version 2:
1. Case study: Tracing Gstreamer plugins with GST_DEBUG

* Version 1:
1. Added how to use GST_DEBUG
2. Added execution screenshot of xdot
3. Updated the existing statement for readability
4. Updated GST_DEBUG_DUMP_DOT_DIR usage

Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
5 years agoTools: Added how to use tracers of GstShark
Geunsik Lim [Mon, 19 Nov 2018 04:27:30 +0000 (13:27 +0900)]
Tools: Added how to use tracers of GstShark

This commit is to append how to use the nine below tracers in GstShark.
All tracers were selected as a initial set of tracers based on RidgeRun's fine-tuning experience.
* InterLatency
* Processing time
* Frame rate
* Schedule time
* CPU usage
* Graphic
* Bitrate
* Queue Level
* Buffer

**Changes proposed in this PR:**
* Version 3:
1. Added how to run gstshark-plot (Experimental)
2. Added how to create CTF (Common Trace Format) folder
3. Wrote how to build code with v.0.5.3 release tag

* Version 2:
1. Added additional instruction manual for easy debugging
2. Fixed incorrect statements
3. Appended some commands to helpe GstShark newbie
4. Added screenshot of GstShark: graphic tracer

* Version 1:
1. Added how to use GstShark tracers
2. Updated how to convert output data to a GNUplot data for analysis

Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
5 years ago[Aggregator] update log format
Jaeyun [Tue, 20 Nov 2018 04:07:30 +0000 (13:07 +0900)]
[Aggregator] update log format

Use gst macros to print debug logs

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Sink] update log format
Jaeyun [Mon, 19 Nov 2018 12:15:05 +0000 (21:15 +0900)]
[Sink] update log format

Use gst macros to print debug logs

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Transform] free operators list
Jaeyun [Mon, 19 Nov 2018 11:41:21 +0000 (20:41 +0900)]
[Transform] free operators list

1. If there exists pre-configured list for arith operators, free it before parsing new option.
2. Remove duplicated code in the loop of arith mode.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter/TFLite] code clean
Jaeyun [Mon, 19 Nov 2018 11:35:33 +0000 (20:35 +0900)]
[Filter/TFLite] code clean

use common macro and glib functions to print debug message

TODO : change function to print log later

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Filter/TFLite] init tensor info
Jaeyun [Mon, 19 Nov 2018 11:29:51 +0000 (20:29 +0900)]
[Filter/TFLite] init tensor info

Add code to init tensor info structure.
(This update is to fix coverity issue)

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Meson] Initial commit of meson build
sewon.oh [Thu, 15 Nov 2018 01:43:12 +0000 (10:43 +0900)]
[Meson] Initial commit of meson build

Initial commit of meson. This commit's goal is to make single binary.

Signed-off-by: sewon.oh <sewon.oh@samsung.com>
5 years agoTools: Adde how to use Gstreamer Debugger (gst-debugger)
Geunsik Lim [Mon, 19 Nov 2018 07:07:59 +0000 (16:07 +0900)]
Tools: Adde how to use Gstreamer Debugger (gst-debugger)

Fixed issue 132#issuecomment-439788784.

This commit is to explain how to use a Gstreamer Debugger tool to
introspect a gst-pipeline remotely with a graphical client.

**Changes proposed in this PR:**
* Version 2:
1. Added GStreamer-based totem player as an example

* Version 1:
1. Added How to use Gstreamer debugger
2. Added How to patch ver 0.90.0 to build on Ubuntu 16.04

Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
5 years ago[Filter/TFLite] support dynamic model
HyoungjooAhn [Mon, 19 Nov 2018 06:50:11 +0000 (15:50 +0900)]
[Filter/TFLite] support dynamic model

User open tflite model when a model is already loaded, compare it with previous one and if it is different, make the  object the new one with new model.

Signed-off-by: HyoungjooAhn <hello.ahnn@gmail.com>
5 years ago[Test/Transform] add tc to test changed arith mode option
Jaeyun [Mon, 19 Nov 2018 07:06:49 +0000 (16:06 +0900)]
[Test/Transform] add tc to test changed arith mode option

1. add new testcases for changed arith mode using gst-harness
2. update the pipeline in object detection example

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Transform] refactor arith/typecast
Jaeyun [Wed, 14 Nov 2018 09:31:18 +0000 (18:31 +0900)]
[Transform] refactor arith/typecast

refactor arith/typecast to handle arithmetic in sequence

1. add operands and handle tensor element with parsed option
2. add common functions for the operators
3. remove multi-op (add-mul and mul-add) and handle operator in sequence

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
5 years ago[Decoder] option-3 is not enough. Increase to 9
MyungJoo Ham [Mon, 19 Nov 2018 02:38:53 +0000 (11:38 +0900)]
[Decoder] option-3 is not enough. Increase to 9

- Refactor option handling codes to handle much more without
damaging code readability.
- Fix decoder parameters in test cases / examples.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
5 years agoTools: Added how to use Hawktracer for profiling
Geunsik Lim [Mon, 19 Nov 2018 05:24:29 +0000 (14:24 +0900)]
Tools: Added how to use Hawktracer for profiling

This commit is append to how to use Hawktracer for profiling.

* HawkTracer:
It is a highly portable, low-overhead, configurable profiling tool
built in Amazon Video for getting performance metrics from low-end devices.

Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>