Jaeyun [Wed, 29 Jul 2020 04:07:43 +0000 (13:07 +0900)]
[Android] params to init nnstreamer
Add condition to check params when initializing nnstreamer.
Also, single-shot does not need gstreamer initialization. Add feature for this.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Parichay Kapoor [Tue, 28 Jul 2020 03:45:28 +0000 (12:45 +0900)]
[single] Optimize invoke critical path
Remove setup gstTensorMemory in each invoke call
rather, pre-set the tensor memory when input dimensions are set
and re-use that setup tensor memory wrapper each time
Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
Sangjung Woo [Fri, 24 Jul 2020 05:44:36 +0000 (14:44 +0900)]
[Test/CAPI] Update testcases of element-wise control functions
This patch updates testcases of element-wise control functions to comply
with Tizen API Design Guideline.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Fri, 24 Jul 2020 05:44:10 +0000 (14:44 +0900)]
[C-API] Modify element-wise control functions
To comply with Tizen API Design Guideline, this patch use single
key-value pair for ml_pipeline_element_set_property and
ml_pipeline_element_get_property function.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
MyungJoo Ham [Mon, 27 Jul 2020 10:53:10 +0000 (19:53 +0900)]
Fix Ubuntu CI Build Error
Having header inclusion with incorrect orders
may incur errors with older gcc of older Ubuntu distro.
You shouldn't omit headers only because they may be included
indirectly by other headers.
Change-Id: Iaf4a096e08ee27d431fad85052edbae21470114f
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Parichay Kapoor [Tue, 28 Jul 2020 03:56:24 +0000 (12:56 +0900)]
[single] Memory leak bug fix
Add memory leak bug fix
When output ml_tensors_data_h fails to allocate, the already computed output must be freed before return
Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
Jaeyun [Tue, 28 Jul 2020 07:18:07 +0000 (16:18 +0900)]
[Meson] dependency for filter subplugin
1. For nnfw deprecated function, find symbol in header. (cannot find function in library)
2. Remove unnecessary dependency to check pytorch version.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Fri, 10 Jul 2020 05:35:44 +0000 (14:35 +0900)]
[Test] testcase to convert multi tensors
add new testcases to convert byte stream to multi tensors.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Fri, 10 Jul 2020 05:30:48 +0000 (14:30 +0900)]
[Converter] bytes to multi tensors
parse the list of input info (dimension and type), and convert byte-stream to multi tensors.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 9 Jul 2020 10:25:48 +0000 (19:25 +0900)]
[Common] function to get data size
Add new function to get data size from tensors info.
If index is negative value, this will return total data size of tensors.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Wed, 29 Jul 2020 03:57:36 +0000 (12:57 +0900)]
[CodeClean] remove redundant space
Remove redundant space in source file.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Yongjoo Ahn [Mon, 27 Jul 2020 01:59:09 +0000 (10:59 +0900)]
[tizensensor] Add tolerance for sensor data check
Ease the future timestamp check:
- At the check time, the timestamp of event could be the "next" sample
- Add tolerance amount of sampling rate
- Change Error to Warning
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
gichan-jang [Mon, 27 Jul 2020 09:45:15 +0000 (18:45 +0900)]
[TCM] Add yaml config file for android
TCM(Test Case Manager) requires config.yaml file.
The config file is written for android API test.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Jaeyun [Mon, 27 Jul 2020 04:40:27 +0000 (13:40 +0900)]
[Android/Single] allow 0 timeout
Now C-API allows setting 0 timeout val, change condition to set timeout value.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Wed, 22 Jul 2020 07:35:32 +0000 (16:35 +0900)]
CAPI/Single: Optimize no-timeout mode run-time performance
Do not invoke in a secondary thread, but ivoke in
the primary thread directly without CV so that
there is minimized latencies for single-invoke calls.
This has refactored the invoke-output-process routine.
This follows-up #2551
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Parichay Kapoor [Mon, 27 Jul 2020 02:00:15 +0000 (11:00 +0900)]
[unittest] Bug fix for c-api unittest
Bug fix for c-api unittest when tensorflow-lite is not present
Bug of destroy info without create in invoke_01
Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
MyungJoo Ham [Fri, 24 Jul 2020 09:58:09 +0000 (18:58 +0900)]
Test/Fix potential macro bug
What if you do:
```
if (WHATSOEVER)
_print_log (MESSAGE);
else
do_something ();
```
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Tony Jinwoo Ahn [Sun, 26 Jul 2020 14:23:09 +0000 (23:23 +0900)]
[Test] Remove trailing whitespace
Signed-off-by: Tony Jinwoo Ahn <tony.jinwoo.ahn@gmail.com>
gichan-jang [Fri, 24 Jul 2020 02:23:34 +0000 (11:23 +0900)]
[Protobuf] Fix protobuf util function header file
Fix protobuf util function header file.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Sangjung Woo [Mon, 20 Jul 2020 07:48:51 +0000 (16:48 +0900)]
[Build] Support VD product build system
This patch supports the VD product build system.
`enable_tizen_privilege_check` and `enable_tizen_feature_check` are
newly added and below features are disabled.
* Privacy / Privilege Manager
* Resource Manager
* ProtoBuffer / FlatBuffer
* Test since python-numpy is not supported
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Yongjoo Ahn [Mon, 13 Jul 2020 09:10:51 +0000 (18:10 +0900)]
[tizensensor] Let the element make use of GstBaseSrc
- Remove timestamp in `_create()` and `_fill()` and let BaseSrc do timestamp
- Remove `_get_times()`
- Init debug category
- Add query for latency
- set_interval for tizen sensor_listener
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Mon, 13 Jul 2020 09:07:19 +0000 (18:07 +0900)]
[tensor_sink] Add debug log for timestamp in tensor_sink
- Add macro for logging timestamp in render_buffer
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
gichan-jang [Thu, 23 Jul 2020 10:45:18 +0000 (19:45 +0900)]
[Debian] Fix protobuf lib install path
Fix protobuf util lib install path
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Parichay Kapoor [Fri, 24 Jul 2020 01:45:45 +0000 (10:45 +0900)]
[single] Enable setting timeout to 0
Enable setting timeout to 0
timeout 0 now has significance and re-setting timeout to 0 should be allowed
Related issue: #2568
Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
MyungJoo Ham [Tue, 21 Jul 2020 09:17:37 +0000 (18:17 +0900)]
README: update example style and add more examples
- Restyle example lists of README.md
- Add "edge-ai" and "products" category
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
gichan-jang [Mon, 20 Jul 2020 06:17:57 +0000 (15:17 +0900)]
[Test] Ignore src iio unusual cases test
Unusual cases test fails occasionally when getting state of the pipeline.
I removed the previous patch and modified it to ignore this test in Ubuntu.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Parichay Kapoor [Thu, 16 Jul 2020 09:59:05 +0000 (18:59 +0900)]
[caffe2] Warning fix based for updated caffe2 v1.6.0-rc1
Update caffe2 extension to remove warning based on api update
for version 1.6.0-rc1
Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
Parichay Kapoor [Thu, 16 Jul 2020 09:54:03 +0000 (18:54 +0900)]
[pytorch] Update pytorch extension for pytorch v1.6.0-rc1
Update pytorch extension for pytorch v1.6.0-rc1
Also pytorch and caffe2 headers do not follow redundant declarations
So, remove redundant declaration warning flag when compiling with them
V2:
Check version of pytorch from pkg-config
Update extension based on version number due to api update
Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
MyungJoo Ham [Wed, 22 Jul 2020 07:37:15 +0000 (16:37 +0900)]
Test/CAPI: Type mismatch warning
ret_sync_mode is unsigned.
If it is compiled with more strict compilers,
it emits errors. Fix it by adding U.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Wed, 22 Jul 2020 10:13:53 +0000 (19:13 +0900)]
Debian: add flatbuf/protobuf packaging
nnstreamer-flatbuf and
nnstreamer-protobuf will be available for Ubuntu/Debian.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Wook Song [Fri, 10 Jul 2020 07:11:44 +0000 (16:11 +0900)]
[Dist/Debian] Add a sub-package that provides the openvino filter
This patch adds a sub-package that provides the tensor filter for
OpenVino to Debian/Ubuntu.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Jaeyun [Fri, 17 Jul 2020 10:54:28 +0000 (19:54 +0900)]
[Api/Single] default no timeout when invoking model
If user does not set the timeout, single-invoke function will wait for the output till the invoke is done.
This requires another ACR.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
박형민 (Park Hyeoung Min) [Thu, 9 Jul 2020 07:37:29 +0000 (16:37 +0900)]
Fix comments in SingleShot.java
Fix comments grammatically correct by adding subject, "this".
Signed-off-by: Park Hyeoung-Min <phm0127@gmail.com>
Sangjung Woo [Fri, 17 Jul 2020 09:51:05 +0000 (18:51 +0900)]
[Tests/C-API] Add test case for abnormal accessing of callback function
This patch newly adds a test case for abnormal accessing of callback
function when calling both `ml_pipeline_element_get_handle()` and
`ml_pipeline_sink_register()` functions.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Fri, 17 Jul 2020 09:47:04 +0000 (18:47 +0900)]
[C-API] Bugfix for abnormal accessing of the callback function
If the handle of sink element is fetched by calling both
`ml_pipeline_element_get_handle()` and `ml_pipeline_sink_register()`
functions, segmantation fault occurs because of abnormal accessing for
callback function. This patch fixes that bug.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Mon, 20 Jul 2020 04:15:00 +0000 (13:15 +0900)]
[SPEC] Cleanup spec file
* Fix the wrong definition of flat buffer
* Add `nnfw_support` flag to control NNFW even though ARM architecture
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Jaeyun [Fri, 17 Jul 2020 09:17:45 +0000 (18:17 +0900)]
[Filter/NNFW] change nnfw api
1. Change nnfw api to set input info.
The function apply_tensorinfo will be deprecated soon.
2. Remove unnecessary definition about max rank of nnfw.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Fri, 17 Jul 2020 09:50:40 +0000 (18:50 +0900)]
[Api/Single] init status code before invoking
In invoke thread, init status (error-none) before calling the invoke callback.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Wed, 15 Jul 2020 07:31:15 +0000 (16:31 +0900)]
[SAM/CodeClean] remove global val
sam report, remove global val in openvino plugin.
update script to install common header file.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Sangjung Woo [Wed, 15 Jul 2020 09:36:05 +0000 (18:36 +0900)]
[Demux] Bugfix for set_property function
If `tensorpick` property of demux element is set twice by calling
g_object_set() function, the previous value should be removed and
new one should be written. However, the value is appended and it can
make a problem. This patch fixes this bug.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
gichan-jang [Wed, 15 Jul 2020 02:23:19 +0000 (11:23 +0900)]
[SPEC] Add supproting element for tizen
Adding an element : gdppay, gdpdepay
These elements payload and depayload GStreamer buffers and events using the GStreamer Data Protocol.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
MyungJoo Ham [Mon, 13 Jul 2020 07:17:15 +0000 (16:17 +0900)]
[Fix/SVACE] memory leak and un-init local variables
SVACE reported issues in Tizen CAPI unit test cases:
- 443268 (uninitialized local variable)
- 443269 (uninitialized local variable)
- 443278 (memory leak): although this is always not allocated successully, I've added "free" that fails with its error code assertion.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun [Tue, 7 Jul 2020 11:35:13 +0000 (20:35 +0900)]
[Tizen/Sensor] remove deprecated api
API to read sensor data was deprecated since 5.5.
Replace this API (sensor data list).
Also set block size of output buffer when starting the src element.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 9 Jul 2020 08:47:44 +0000 (17:47 +0900)]
[Converter] code clean (parse media info)
code clean, function to set/parse media info for each mime type.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Sangjung Woo [Mon, 13 Jul 2020 02:20:16 +0000 (11:20 +0900)]
[C-API] Add remarks section for ml_tensors_info_get_tensor_name()
This patch adds the remarks section for
ml_tensors_info_get_tensor_name() since the behavior of this function is
changed since 6.0.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Wook Song [Fri, 10 Jul 2020 05:42:48 +0000 (14:42 +0900)]
[Filter/OpenVino] Fix compile error due to OoO designated initialization
This patch fixes compile errors related to restriction of designated
initialization in C++.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Wook Song [Fri, 10 Jul 2020 06:29:08 +0000 (15:29 +0900)]
[Tests/Sink] Fix compiler warnings with -Werror=sign-compare
This patch fixes compiler warnings with -Werror=sign-compare related to
the TestData and TestOption structures in unittest_sink.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Jaeyun [Wed, 8 Jul 2020 03:53:42 +0000 (12:53 +0900)]
[Tizen/Restriction] add sensor-src in restriction
change condition to check restricted element.
tizen sensor-src will be included in restrict list.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 9 Jul 2020 03:19:48 +0000 (12:19 +0900)]
[Android/Doc] update doc about nn framework
Update javadoc
- link to ONE and NNStreamer repo
- add add options for SNPE
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Sangjung Woo [Wed, 8 Jul 2020 05:55:15 +0000 (14:55 +0900)]
[SPEC] Newly add devel-static packages
To avoid the license conflict issue by an automatic tool, this patch
newly adds the `capi-nnstreamer-devel-static` and `nnstreamer-devel-static`
packages which only contain static libraries. `devel` packages only have
headers and package config as below.
$ rpm -qlp capi-nnstreamer-devel-static-1.5.3-0.armv7l.rpm
/usr/lib/libcapi-nnstreamer.a
$ rpm -qlp capi-nnstreamer-devel-1.5.3-0.armv7l.rpm
/usr/include/nnstreamer/nnstreamer-single.h
/usr/include/nnstreamer/nnstreamer.h
/usr/lib/pkgconfig/capi-nnstreamer.pc
$ rpm -qlp nnstreamer-devel-static-1.5.3-0.armv7l.rpm
/usr/lib/libnnstreamer-tizen-sensor.a
/usr/lib/libnnstreamer.a
/usr/lib/libnnstreamer_decoder_bounding_boxes.a
/usr/lib/libnnstreamer_decoder_direct_video.a
/usr/lib/libnnstreamer_decoder_image_labeling.a
/usr/lib/libnnstreamer_decoder_image_segment.a
/usr/lib/libnnstreamer_decoder_pose_estimation.a
/usr/lib/libnnstreamer_filter_movidius-ncsdk2.a
/usr/lib/libnnstreamer_filter_nnfw.a
/usr/lib/libnnstreamer_filter_python2.a
/usr/lib/libnnstreamer_filter_tensorflow-lite.a
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Mon, 6 Jul 2020 05:11:56 +0000 (14:11 +0900)]
[C-API] Add remarks section in ml_tensors_data_create()
Since 6.0, ML_ERROR_STREAMS_PIPE error code is removed in
ml_tensors_data_create() function and ML_ERROR_OUT_OF_MEMORY is returned
for internal error. This patch adds a remarks section in
ml_tensors_data_create() for Tizen application developers.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sung-Jae Lee [Wed, 8 Jul 2020 05:11:32 +0000 (14:11 +0900)]
Update README.md
- Update the name `NN Runtime` to `ONE Runtime` with a link to github repo of the project.
Signed-off-by: Sung-Jae Lee <sj925.lee@samsung.com>
gichan-jang [Wed, 8 Jul 2020 03:11:13 +0000 (12:11 +0900)]
[TEST] Fix iio unit test that fails occasionally
Add sleep time unitl state changed within the timeout
Related issue : #2434
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
gichan-jang [Tue, 7 Jul 2020 09:55:29 +0000 (18:55 +0900)]
[SPEC] Fix install files list
Fix install files list.
Seperate flatbuf as independent package.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Jaeyun [Wed, 17 Jun 2020 03:28:15 +0000 (12:28 +0900)]
[Android] custom-easy filter
Update custom-filter API using custom-easy.
- register custom-filter with in/out info and implement invoke interface only.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
gichan-jang [Mon, 6 Jul 2020 07:47:34 +0000 (16:47 +0900)]
[Decoder] Dynamic update of tensor config
Changed to update tensor config dynamically.
Clear private data of subplugin, and init the subplugin.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Jaeyun [Fri, 3 Jul 2020 07:18:40 +0000 (16:18 +0900)]
[Android] enable nnfw
Change default option to enable NNFW in android-api build, and clean up build script.
When building android library, download nnfw libs from ONE repo and start to build library.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 2 Jul 2020 02:40:22 +0000 (11:40 +0900)]
[Filter/TF] code clean
change to static function to release buffer.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Yongjoo Ahn [Sun, 5 Jul 2020 07:24:59 +0000 (16:24 +0900)]
[doc/android] Update README for android build and test
- Add links to data for tflite and snpe test
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Sun, 5 Jul 2020 07:24:21 +0000 (16:24 +0900)]
[Test/android/snpe] Add android tests with snpe
- Add classification result test with inception_v3 model
- Add runtime checks
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
gichan-jang [Fri, 12 Jun 2020 07:21:53 +0000 (16:21 +0900)]
[Protobuf] Add protobuf util function
The problem happens when multiple objects using .pb.cc file are loaded simultaneously.
I changed to tensor converter and decoder of protobuf subplugin shared libnnstreamer_protobuf.so
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
gichan-jang [Tue, 9 Jun 2020 05:18:52 +0000 (14:18 +0900)]
[Converter] Add tensor converter sub-plugin protobuf
Add tensor converter subplugin protobuf
Add protobuf unittest
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Jaeyun [Wed, 10 Jun 2020 11:48:56 +0000 (20:48 +0900)]
[C-Api] define new API for custom filter
This PR defines new APIs and callbacks for custom filter.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 2 Jul 2020 02:37:33 +0000 (11:37 +0900)]
[Android/AMCSrc] prevent build warning
1. fix macro to get private data in element (will be deprecated)
2. fix indent
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Tue, 28 Apr 2020 07:36:38 +0000 (16:36 +0900)]
[Common] Allow to fetch nnstreamer version
Let external nnstreamer plugins to probe nnstreamer version
at both run-time and build-time.
Fixes #2294
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun [Thu, 2 Jul 2020 08:21:29 +0000 (17:21 +0900)]
[Test] testcase with typecast option
Add new testcases for caps-nego in tensor-transform, and remove duplicated test code.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 2 Jul 2020 08:18:38 +0000 (17:18 +0900)]
[Transform] nego failure with appsrc
When pushing the data directly from appsrc to tensor-transform (with typecast option), caps-negotiation failed and cannot run the pipeline.
To fix this, set type to unknown when direction is src pad.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Sangjung Woo [Tue, 16 Jun 2020 09:50:13 +0000 (18:50 +0900)]
[Test/CAPI] Add testcases for element-wise control functions
This patch newly adds testcases for element-wise control function APIs.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Tue, 16 Jun 2020 08:10:12 +0000 (17:10 +0900)]
[C-API] Add element-wise control functions
This patch newly adds element-wise control functions to get and set
property values of the target element in NNStreamer pipeline.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Wed, 17 Jun 2020 10:22:23 +0000 (19:22 +0900)]
[C-API] Rename ml_pipeline_get_element() to ml_pipeline_get_gst_element()
This patch renames ml_pipeline_get_element() to
ml_pipeline_get_gst_element(). It is only used for demo application
internally and the name 'ml_pipeline_get_element' is going to use for
other purposes.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Wed, 1 Jul 2020 10:29:00 +0000 (19:29 +0900)]
[CAPI] Add ml_error_e into CAPI_ML_FRAMEWORK group
This patch newly adds the ml_error_e Enumeration into the
CAPI_ML_FRAMEWORK doxygen group.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
gichan-jang [Wed, 26 Feb 2020 11:30:28 +0000 (20:30 +0900)]
[Decoder] Add tensor decoder subplugin flatbuffers
Add tensor decoder subplugin for flatbuffer
flatbuffers package can be found here :
https://launchpad.net/~nnstreamer/+archive/ubuntu/ppa-build-test/+packages
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
gichan-jang [Tue, 26 May 2020 12:16:54 +0000 (21:16 +0900)]
[Test] Add flatbuffer converter and decode test
Add flatbuffer converter and decoder run test
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
gichan-jang [Thu, 25 Jun 2020 11:54:13 +0000 (20:54 +0900)]
[TEST] Fix Tensor converter test
fix tensor converter unit test
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Jaeyun [Fri, 26 Jun 2020 02:04:20 +0000 (11:04 +0900)]
[C-Api] fix mem leak
1. add g_free to release the memory when appending mem block in buffer.
2. free interator in switch api.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Hyoung Joo Ahn [Thu, 25 Jun 2020 11:37:02 +0000 (20:37 +0900)]
[Repo] fix a mem leak
fix a mem leak at tensor_repo
Signed-off-by: Hyoung Joo Ahn <hello.ahn@samsung.com>
Hyoung Joo Ahn [Thu, 25 Jun 2020 03:13:58 +0000 (12:13 +0900)]
[Mux] add the new sync_mode:REFRESH
This new sync mode allows PUSHING with only one new buffer of sinkpads of `tensor_mux`. Previously, if `tensor_mux` want to push its buffers to srcpad, all of sink pads had to be filled with new buffers. However, this new mode, REFRESH, push buffers when `tensor_mux` receive a new buffer. For the other sink pads, except the one received the new buffer, will use again the previous one. It decides EOS when any of the sink pads receive it.
Signed-off-by: Hyoung Joo Ahn <hello.ahn@samsung.com>
Jaeyun [Thu, 25 Jun 2020 11:42:18 +0000 (20:42 +0900)]
[Test] fix mem leak
fix possible mem leak in c-api testcases.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Hyoung Joo Ahn [Thu, 25 Jun 2020 10:39:34 +0000 (19:39 +0900)]
[Filter] fix a memory leak
the allocated memory(when `allocate_in_invoke` is FALSE) should be free when `invoke()` returns not 0(OK)
Signed-off-by: Hyoung Joo Ahn <hello.ahn@samsung.com>
Wook Song [Wed, 24 Jun 2020 07:09:21 +0000 (16:09 +0900)]
[Tests/Filter/EdgeTPU] Enable test() in the meson build script
This patch enables test(), which has been commented out, in the meson
build script for the EdgeTPU filter.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Wook Song [Wed, 24 Jun 2020 06:49:51 +0000 (15:49 +0900)]
[Meson] Add missing environment variable, NNSTREAMER_SOURCE_ROOT_PATH
This patch adds the missing environment variable,
NNSTREAMER_SOURCE_ROOT_PATH, to the test environment object in the
meson build script. This variable is necessary to run the test cases
via 'ninja test'.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Jaeyun [Fri, 19 Jun 2020 06:19:55 +0000 (15:19 +0900)]
[Mux/Merge] code clean
code clean, prepare new sync-mode.
- remove unnecessary param
- reduce code complexity
- change return val (true to push buffer to src pad)
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Tue, 23 Jun 2020 11:17:32 +0000 (20:17 +0900)]
[CodeClean] remove unnecessary defines
code clean, remove unnecessary predefinition to set pad template.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
gichan-jang [Wed, 24 Jun 2020 11:04:43 +0000 (20:04 +0900)]
[TEST] Fix nnfw unit test
When testing the operation of the multi-framework, if tflite is disabled, the test fails.
If tflite is disabled, skip the test.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Wook Song [Wed, 24 Jun 2020 05:57:51 +0000 (14:57 +0900)]
[Tests] Rename NNSTREAMER_BUILD_ROOT_PATH with NNSTREAMER_SOURCE_ROOT_PATH
In most cases, the environment variable, NNSTREAMER_BUILD_ROOT_PATH,
is used for indicating the root directory of the path to which the
'test_models' directory belongs, which means the source root path. To
avoid confusion, this patch renames it with NNSTREAMER_SOURCE_ROOT_PATH.
Signed-off-by: Wook Song <wook16.song@samsung.com>
gichan-jang [Wed, 26 Feb 2020 11:30:28 +0000 (20:30 +0900)]
[Decoder] Add tensor decoder subplugin flatbuffers
Add tensor decoder subplugin for flatbuffer
flatbuffers package can be found here :
https://launchpad.net/~nnstreamer/+archive/ubuntu/ppa-build-test/+packages
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Yongjoo Ahn [Tue, 23 Jun 2020 05:20:38 +0000 (14:20 +0900)]
[Test] Add test for imageseg-decoder and tensor_filter profiling
- Add test cases for newly added option `snpe-deeplab` and `snpe-depth`
- It also check profiling option of tensor_filter
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Dongju Chae [Thu, 18 Jun 2020 05:43:18 +0000 (14:43 +0900)]
[Conf/MemLeak] Add missing g_free() to nnstreamer_conf.c
This patch adds missing `g_free()` to `nnstreamer_conf.c`
`nnsconf_get_custom_value_string()` allocates `hashkey` in the first
line. However, if a value is found in the first hash lookup or a value
does not exist in anywhere, `hashkey` is not inserted to the hash table,
which results in memory leak.
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Jaeyun [Fri, 19 Jun 2020 06:45:48 +0000 (15:45 +0900)]
[RepoSink] ignore sync and preroll
repo-sink may not receive a buffer when pipeline constructed.
set sync and async option to ignore this case.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
gichan-jang [Fri, 19 Jun 2020 08:01:00 +0000 (17:01 +0900)]
[Coverage] Exclude generated files by flatbuf
Exclude generated files by flatbuf from coverage report
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Wook Song [Thu, 18 Jun 2020 02:57:06 +0000 (11:57 +0900)]
[Tests/EdgeTPU] Use dummy device mode instead of dummy library
This patch revises the unit test cases for EdgeTPU to use dummy device
mode instead of the dummy EdgeTPU library.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Jaeyun [Wed, 17 Jun 2020 03:45:50 +0000 (12:45 +0900)]
[C-Api] handle invalid info when creating data handle
When creating the data handle, return error if given tensors-info is invalid.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Fri, 5 Jun 2020 05:51:55 +0000 (14:51 +0900)]
TAOS-CI / Enable clang-format for C++ codes
1. Enable clang TAOS-CI module
2. Add "C++ ONLY" mode for it.
Note that I need to update TAOS-CI to make it accept such options.
This depends on https://github.com/nnstreamer/TAOS-CI/pull/628
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun [Tue, 16 Jun 2020 07:35:35 +0000 (16:35 +0900)]
[Test/C-Api] add testcase of internal functions
add simple testcases to handle the case of invalid param.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Tue, 16 Jun 2020 07:26:21 +0000 (16:26 +0900)]
[C-Api] error code when failed to allocate tensor data
Remove unnecessary error code (stream-pipe).
If failed to allocate mem for tensors-data handle, API returns out-of-mem error.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Mon, 15 Jun 2020 12:47:53 +0000 (21:47 +0900)]
[Meson] converter sub-plugin path in test-env
Update sub-plugin path in test-env, set converter plugin path.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Dongju Chae [Tue, 16 Jun 2020 11:04:20 +0000 (20:04 +0900)]
[Fix] Remove unncessary arg checking before calling g_strdup()
This patch removes uncessary argument checking before calling g_strdup()
If an argument of g_strdup() is NULL, its return value is also NULL.
So, checking its argument before calling is duplicated and useless.
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Hyoung Joo Ahn [Tue, 16 Jun 2020 03:13:41 +0000 (12:13 +0900)]
[Repo/Test] make it easier to understand
applying line change at the complicated pipeline to understand easier.
Signed-off-by: Hyoung Joo Ahn <hello.ahn@samsung.com>
Wook Song [Thu, 11 Jun 2020 07:47:17 +0000 (16:47 +0900)]
[Filter/EdgeTPU] Add a 'dummy' device mode for the test purpose
This patch adds a 'dummy' device mode for the test purpose instead of
using the dummy shared library that pretends to be libedgetpu.so.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Jaeyun [Wed, 10 Jun 2020 04:11:21 +0000 (13:11 +0900)]
[Android] do not convert meta in invoke method
To improve performance, it is necessary to remove metadata conversion in invoke method.
Do not handle dynamic mode in invoke method and update description to change the tensor info.
Also, if output info is changed using set-info method, update cached instance in private data.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>