Jaeyun [Wed, 17 Feb 2021 04:55:36 +0000 (13:55 +0900)]
[Test] remove dependency to ml api
For tizen sensor element, remove dependency to ml api. Replace to gst functions.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Dongju Chae [Tue, 16 Feb 2021 08:34:16 +0000 (17:34 +0900)]
[gRPC] remove uncessary dependency declaration
This patch removes unnecessary dependency declaration.
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Dongju Chae [Tue, 16 Feb 2021 07:50:30 +0000 (16:50 +0900)]
Revert "[grpc] Temporral disable grpc package"
This reverts commit
f563d989d6b26ce097574c21c6c1e6185b189614.
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Gichan Jang [Mon, 15 Feb 2021 01:58:32 +0000 (10:58 +0900)]
[TEST/common] Fix memory leak
Fix memory leak of the tensor common unit test.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Mon, 15 Feb 2021 06:29:00 +0000 (15:29 +0900)]
[CAPI] Change comment to comply convention
Change comment for nntrainer enum to comply convention.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Wed, 10 Feb 2021 06:52:24 +0000 (15:52 +0900)]
[Bug] Fix memory leak
Fix memory leak detected by valgrind.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Wed, 10 Feb 2021 06:58:27 +0000 (15:58 +0900)]
[TEST/sink] Change free function
Some tests do not remove and free temporary files.
Change to remove and free temporary files from `_free_test_data`.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
MyungJoo Ham [Tue, 9 Feb 2021 15:35:14 +0000 (00:35 +0900)]
[OSX] Build error fix
OSX does not have sys/auxv.h
Add a macro assuming that SIMD is always available for
OSX-AARCH64 (e.g., M1) devices.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun [Thu, 4 Feb 2021 07:42:01 +0000 (16:42 +0900)]
[Build] remove unnecessary option
Remove unnecessary build option for sub-plugins, default val is auto.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Tue, 9 Feb 2021 10:58:21 +0000 (19:58 +0900)]
[TEST/single] Destory output data handle
After #3002, User should destory the output handle.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jaeyun [Tue, 9 Feb 2021 08:07:35 +0000 (17:07 +0900)]
[C-Api/Tizen] restricted elements for internal function
Do not check restricted list when constructing a pipeline with internal API.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Gichan Jang [Tue, 9 Feb 2021 08:04:30 +0000 (17:04 +0900)]
[grpc] Temporral disable grpc package
The grpc version is upgraded, but the grpc package of the nnstreamer ppa is not upgraded properly, so it is temporarily disabled.
Discussed with dongju-chae
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Dongju Chae [Mon, 8 Feb 2021 05:55:24 +0000 (14:55 +0900)]
[gRPC/Test] Skip SSAT tests on qemu/aarch64
This patch makes gbs skip ssat tests on qemu/aarch64 env.
In gRPC 1.35.0, some behaviors are not supported on qemu/aarch64.
See the below error log
```
[ 119s] qemu: Unsupported syscall: 168
[ 119s] E0208 04:45:45.
854670498 21089 cpu_linux.cc:41] Error determining current CPU: Function not implemented
[ 119s]
[ 119s] Unsupported setsockopt level=1 optname=15
[ 119s] E0208 04:45:45.
874942631 21089 socket_utils_common_posix.cc:222] check for SO_REUSEPORT: {"created":"@
1612759545.
874068306","description":"Protocol not available","errno":92,"file":"/home/abuild/rpmbuild/BUILD/grpc-1.35.0/src/core/lib/iomgr/socket_utils_common_posix.cc","file_line":198,"os_error":"Protocol not available","syscall":"setsockopt(SO_REUSEPORT)"}
[ 119s] qemu: uncaught target signal 4 (Illegal instruction) - core dumped
```
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Jaeyun [Thu, 4 Feb 2021 07:42:01 +0000 (16:42 +0900)]
[Build] remove unnecessary option
Remove unnecessary build option for sub-plugins, default val is auto.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Fri, 5 Feb 2021 08:35:46 +0000 (17:35 +0900)]
[CodeClean] fix indent
fix indent in c-api source.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Yongjoo Ahn [Mon, 18 Jan 2021 07:35:18 +0000 (16:35 +0900)]
[test/SSAT] Check flatbuf and protobuf decoder sub-plugins
- Check existence of flatbuf and protobuf sub-plugins for decoder SSAT test
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun [Fri, 5 Feb 2021 09:07:35 +0000 (18:07 +0900)]
[Build] fix package name
fix package name required for devel packages.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Geunsik Lim [Thu, 4 Feb 2021 01:51:11 +0000 (10:51 +0900)]
TAOS-CI: Use .TAOS-CI/.gbs.conf by default
This commit is to use a (1) ./.TAOS-CI/.gbs.conf or (2) ./packaging/.gbs.conf file
by default to support customized GBS repositories for each GitHub repository
because the (3) ~/.gbs.conf file of user account (e.g., www-data) can be used among
lots of repositories.
**Changelog**
* Added ./.TAOS-CI/.gbs.conf
* Added ./packaging/.gbs.conf
* Replaced https with http to avoid ssl issue due to firewall
Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
Gichan Jang [Wed, 3 Feb 2021 05:01:15 +0000 (14:01 +0900)]
[TEST] Code clean unittest plugins
- It causes confusion by performing free resource in the macros.
Changed to release the resource in same code block.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Tue, 2 Feb 2021 07:14:58 +0000 (16:14 +0900)]
[TEST] Add tensor filter fw autodetection unit test
Add tensor filter framework autodetection unit tests
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Tue, 2 Feb 2021 06:54:43 +0000 (15:54 +0900)]
[Filter] Framework auto detection without specifying the option
Modify the tensor filter to automatically detect the framework without specifying the framework option.
Default value of the framework is changed to "auto".
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jaeyun [Fri, 29 Jan 2021 06:25:13 +0000 (15:25 +0900)]
[Test] separate nnfw testcase
separate testcases for nnfw plugin (functions for filter-plugin and ml-api)
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Gichan Jang [Wed, 27 Jan 2021 04:48:16 +0000 (13:48 +0900)]
[SSAT] Remove some log files generated by SSAT tests
- Remove some log files during SSAT test for humble yocto qemu environment
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Hyoung Joo Ahn [Thu, 4 Feb 2021 03:02:27 +0000 (12:02 +0900)]
[ML-API] add log messages
The additional log messages are required because returning the error code `ML_ERROR_STREAMS_PIPE` gives very little information for the abnormal situation.
Signed-off-by: Hyoung Joo Ahn <hello.ahn@samsung.com>
Gichan Jang [Wed, 27 Jan 2021 04:48:16 +0000 (13:48 +0900)]
[Doc] Move stable wiki doc to /Documentation
Copy stable wiki documents to /Documentation.
After this PR, copied wiki page will be deleted.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Mon, 1 Feb 2021 10:37:19 +0000 (19:37 +0900)]
[DOC] Add a description of the combination option
Add a description of the comparison between tee and input-combination.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Tue, 2 Feb 2021 07:47:00 +0000 (16:47 +0900)]
[Doc] Add nnstreamer tools to github.io
Add nnstreamer tools doc to github.io
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Gichan Jang [Tue, 2 Feb 2021 00:23:31 +0000 (09:23 +0900)]
[Doc] Add nnstreamer logo to github.io
Add NNStreamer logo to github.io.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jaeyun [Fri, 29 Jan 2021 07:57:38 +0000 (16:57 +0900)]
[Build] internal header for APIs
Add internal header for sub-plugins and native APIs.
After separating API repo, native API build will include this header.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Gichan Jang [Mon, 1 Feb 2021 08:40:05 +0000 (17:40 +0900)]
[TEST] Change string property test
Current setting and getting string property test try to select tensor(s) that does not exist.
Changed to set and get framework of the tensor filter.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Xavier Roumegue [Tue, 26 Jan 2021 17:15:07 +0000 (18:15 +0100)]
[Decoder/BoundingBox] Add option for detection threshold on tf-ssd reported scores
This limits boxes drawing to objects detected with reasonable confidence,
specifying the threshold in percentage thanks to the option-3 as below:
option-3=bbox idx:classes idx:scores idx:num detection idx,threshold
So this adds ",threshold" to the current option-3 configuration scheme.
The threshold has to be within [0 100] range, otherwise skipped.
Signed-off-by: Xavier Roumegue <xavier.roumegue@nxp.com>
Xavier Roumegue [Thu, 28 Jan 2021 14:12:54 +0000 (15:12 +0100)]
[Decoder/BoundingBox] Fix off-by-one error on valid TF-SSD labels handling
The class label indexes starts at 0 while parsing the labels file,
and hence 0 should be considered as a valid label in the general case.
Signed-off-by: Xavier Roumegue <xavier.roumegue@nxp.com>
Xavier Roumegue [Thu, 28 Jan 2021 14:17:40 +0000 (15:17 +0100)]
[Decoder/BoundingBox] Clamp bounding boxes locations
Some neural networks could return negative values, which can lead to
segfault errors while drawing the boxes.
For example, the model below outputs some locations boxes with values
out of [0.0 1.0] in some circumstances.
http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v2_quantized_300x300_coco_2019_01_03.tar.gz
Signed-off-by: Xavier Roumegue <xavier.roumegue@nxp.com>
Xavier Roumegue [Fri, 22 Jan 2021 19:46:02 +0000 (19:46 +0000)]
[Decoder/BoundingBox] Add option to specify TF-SSD output tensors mapping
Recent tensor flow object detections neural network models use output
tensor mapping defined by google:
https://www.tensorflow.org/lite/models/object_detection/overview#output_signature
which is different than the one currently used on bounding boxes tensor
decoder element.
This patch adds the possibility to specify any output tensors mapping
through the option-3 parameter for tf-ssd mode using the following
convention:
locations index:classes index: scores index: number of detections index.
For example, option3=0:1:2:3 would map the output tensors as defined by
previous link, .i.e. :
- Bounding boxes locations tensor on index 0
- Classes tensor on index 1
- Scores tensor on index 2
- Number of detection tensor on index 3
option3 for tf-ssd mode is optional, and if not specified, the default
tensors mapping preserve the backward compatibility (.i.e. 3:1:2:0)
Signed-off-by: Xavier Roumegue <xavier.roumegue@nxp.com>
Xavier Roumegue [Thu, 28 Jan 2021 16:26:15 +0000 (17:26 +0100)]
[Decoder/BoundingBox] Apply gst-indent
Signed-off-by: Xavier Roumegue <xavier.roumegue@nxp.com>
Gichan Jang [Tue, 26 Jan 2021 02:15:07 +0000 (11:15 +0900)]
[C-API] Fix C-API header comments
Clarify the description of nnstreamer C-API comments
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jihoon Lee [Wed, 20 Jan 2021 07:47:05 +0000 (16:47 +0900)]
[pkg-config] Update require to capi-nnstreamer
As users of capi-nnstreamer.pc need `capi-ml-common.pc`, it should be
added to the require although currently, capi-ml-common.pc has the
exactly same include path so nothing really changes.
This is more of a future proof that one day capi-ml-common.pc might
point to a different include header.
**Self evaluation:**
1. Build test: [X]Passed [ ]Failed [ ]Skipped
2. Run test: [X]Passed [ ]Failed [ ]Skipped
Signed-off-by: Jihoon Lee <jhoon.it.lee@samsung.com>
Jaeyun [Fri, 29 Jan 2021 09:43:12 +0000 (18:43 +0900)]
[Build] package for nnstreamer API
add package for nnstreamer API (separate from nnstreamer pkg)
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Fri, 11 Dec 2020 06:36:14 +0000 (15:36 +0900)]
[Tools/Parser] Rule Implementation Done
Redefine "GstBin" and "GstElement" for nns-parser.
As we do not create actual pipelines from strings,
we only need symbolic data.
All the parsing rule implementations are fixed for nns-parser.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Mon, 30 Nov 2020 07:04:04 +0000 (16:04 +0900)]
[Tools/Parser] Remove GSTPARSE functions
GSTPARSE has defined its own functions,
which are replaced with general functions
by this commit.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Tue, 1 Dec 2020 08:04:29 +0000 (17:04 +0900)]
[Tools/Parser] Do ref counting with pseudo elements
With linked list, psuedo elements are required to be ref-counted.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun [Fri, 29 Jan 2021 05:15:35 +0000 (14:15 +0900)]
[Test] fix coverity issue
create buffer with pre-allocated mem.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Xavier Roumegue [Wed, 27 Jan 2021 08:50:36 +0000 (09:50 +0100)]
[BUILD/TF-Lite] Add nnapi delegate option
Some NPU vendors such as Verisilicon integrate their neural network
stack within TF-LITE through NNAPI for Linux OS.
https://github.com/VeriSilicon/tensorflow/commit/
07a2d86919d2c27dc350a065ab01c815a3f4aa15
Thus, this option enables NNAPI support on tf-lite tensor filter plugin
for non android build such as NPU delegates could use NNAPI on non
Android OS.
Signed-off-by: Xavier Roumegue <xavier.roumegue@nxp.com>
Jihoon Lee [Tue, 26 Jan 2021 07:19:38 +0000 (16:19 +0900)]
[ACR] Add NNTrainer enum to singleshot api
This patch adds Add NNtrainer enum to singleshot api, `ml_nnfw_type_e`
**Self evaluation:**
1. Build test: [ ]Passed [ ]Failed [X]Skipped
2. Run test: [ ]Passed [ ]Failed [X]Skipped
Signed-off-by: Jihoon Lee <jhoon.it.lee@samsung.com>
Sangjung Woo [Mon, 25 Jan 2021 08:12:26 +0000 (17:12 +0900)]
[C-API] Add note comments for custom easy filter.
If ml_custom_easy_invoke_cb() returns negative error values, the
constructed pipeline does not work properly anymore. This patch adds the
Note comments for this.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Gichan Jang [Fri, 22 Jan 2021 06:43:09 +0000 (15:43 +0900)]
[Coverity] Resolve coverity issue
Resolve coverity issue
1. Unchecked return value
2. Logically dead code
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jaeyun [Mon, 25 Jan 2021 04:48:00 +0000 (13:48 +0900)]
[If/Api] api description for if callback
update description for tensor-if custom callback and set init value for condition.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Tue, 19 Jan 2021 10:06:04 +0000 (19:06 +0900)]
[Filter/Single] move tensor-filter single class
move tensor-filter single class to nnstreamer core directory
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Fri, 22 Jan 2021 06:34:52 +0000 (15:34 +0900)]
[Coverity] fix coverity issues
1. handle error case when failed to map the gst buffer.
2. init variable in cls constructor.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Fri, 22 Jan 2021 11:58:28 +0000 (20:58 +0900)]
[Test] add filter-cpp test
add missed testcases - filter-cpp in tizen build.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Mon, 18 Jan 2021 04:32:12 +0000 (13:32 +0900)]
[Common] code clean
fix typo and remove duplicated code to compare file extension.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Gichan Jang [Fri, 22 Jan 2021 04:50:31 +0000 (13:50 +0900)]
[Badge] Change coverity link of the badge
Change coverity link of the badge because coverity project has been
changed.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jaeyun [Thu, 21 Jan 2021 03:12:31 +0000 (12:12 +0900)]
[Common] function to check peer caps
Update description to check peer pad caps, and fix invalid condition.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Fri, 22 Jan 2021 05:21:05 +0000 (14:21 +0900)]
[Join] remove unnecessary code
remove unnecessary code (duplicated free line)
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jihoon Lee [Wed, 20 Jan 2021 05:07:06 +0000 (14:07 +0900)]
[debian] Add nnstreamer-api-common-dev package
Currently, `capi-ml-common-devel` was added to rpm package but
corresponding package was not available in debian.
This patch adds `nnstreamer-api-common-dev` to the debian which
corresponds with `capi-ml-common-devel` in rpm.
**Self evaluation:**
1. Build test: [X]Passed [ ]Failed [ ]Skipped
2. Run test: [X]Passed [ ]Failed [ ]Skipped
Signed-off-by: Jihoon Lee <jhoon.it.lee@samsung.com>
Gichan Jang [Thu, 7 Jan 2021 09:18:32 +0000 (18:18 +0900)]
[Doc] Initial commit to generate doccument using hotdoc
Initial commit to generate doccument using hotdoc.
- Modify markdown files to follow hotdoc's rule
- Add element descriptions
- The API reference is connected with doxygen book link
- NNStreamer-example doc is linked.
- Tizen nativa and .ENT doc is linked.
- Android doc is linked.
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jaeyun [Mon, 18 Jan 2021 07:27:29 +0000 (16:27 +0900)]
[Filter/Single] hide private properties
set private data for tensor-filter single properties.
TODO: move filter-single class to gst directory or declare extern for filter common function.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Yongjoo Ahn [Thu, 14 Jan 2021 08:32:10 +0000 (17:32 +0900)]
[test/SSAT] Optimize python lazy `pack`
- Call python `pack` only once with list.
- This reduces test time on yocto qemu environment.
REF: https://stackoverflow.com/questions/9940859/fastest-way-to-pack-a-list-of-floats-into-bytes-in-python/9941455
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jihoon Lee [Wed, 20 Jan 2021 03:39:02 +0000 (12:39 +0900)]
Add pc file for capi-ml-common-devel
pc file was missing for capi-ml-common-devel package.
This patch adds pc file so that capi-ml-common can be included from
`pkg-config`
**Self evaluation:**
1. Build test: [X]Passed [ ]Failed [ ]Skipped
2. Run test: [X]Passed [ ]Failed [ ]Skipped
Signed-off-by: Jihoon Lee <jhoon.it.lee@samsung.com>
Dongju Chae [Mon, 21 Dec 2020 10:30:01 +0000 (19:30 +0900)]
[gRPC/Src/Sink] Revise grpc_src/sink for the updated interface
This patch revises gRPC source/sink codes for the updated gRPC
common interface.
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Dongju Chae [Mon, 21 Dec 2020 10:34:58 +0000 (19:34 +0900)]
[gRPC/Common] Add grpc_config struct and revise gRPC common codes
This patch revises gRPC common codes by adding grpc_config structure.
Also, gRPC blocking mode will be supported soon.
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Gichan Jang [Tue, 19 Jan 2021 04:19:56 +0000 (13:19 +0900)]
[README] Fix daily build path
Fix daily build directory path.
.... /nnstreamer/ci/taos/daily-build/ -> .... /nnstreamer/ci/daily-build/
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jaeyun [Thu, 14 Jan 2021 07:43:19 +0000 (16:43 +0900)]
[C-API] fix double free case
If filter sub-plugin allocates output tensor, single-shot notifies releasing output buffer when closing the single handle.
In this case, we dont need to free the output handle itself. Calling single-close and destroy-outdata functions will make an error.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Yongjoo Ahn [Tue, 12 Jan 2021 01:04:55 +0000 (10:04 +0900)]
[build/Android] Update android lib build script for PyTorch
- Add PyTorch to build script for android library
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Wook Song [Fri, 15 Jan 2021 03:25:45 +0000 (12:25 +0900)]
[Tests/Meson] Fix wrong option values for 'sed' in meson.build
This is a trivial patch to fix wrong option values following the '-i'
option of 'sed' in the meson build script. Without this patch, some
useless files such as "unittest_tizen_custom.cc'.cc'" are generated in
the build directory.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Yongjoo Ahn [Tue, 12 Jan 2021 02:21:45 +0000 (11:21 +0900)]
[Java-API] Fix `StateChangeCallback`
- StateCallback occasionally fails to get initial state changes (null -> ready or ready -> pause)
- Assign `mStateCallback` before `ml_pipeline_construct`
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Sangjung Woo [Mon, 21 Dec 2020 03:27:19 +0000 (12:27 +0900)]
[C-API] Add note comment for ml_tensors_data_destroy and ml_single_close
This patch adds the note comment for ml_tensors_data_destroy and
ml_single_close APIs.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Fri, 18 Dec 2020 08:09:11 +0000 (17:09 +0900)]
[C-API] Fix the occasional Segmentation fault in test case.
When calling `ml_single_invoke()` after set the timeout option,
`ml_single_close()` should be called before destorying the inference
data. If not, the inference engine might try to access the data, which
is already freed by `ml_tensors_data_destroy()`.
This patch updates the related test cases.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Dongju Chae [Fri, 18 Dec 2020 07:07:37 +0000 (16:07 +0900)]
[Dist/gRPC] Create per-IDL grpc packages
This patch creates per-IDL grpc packages to resolve dependency issues.
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Jaeyun [Wed, 13 Jan 2021 10:08:13 +0000 (19:08 +0900)]
[Test] fix deprecated method
tostring() method was deprecated from python v3.2.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Wed, 13 Jan 2021 09:29:09 +0000 (18:29 +0900)]
[Filter/Python] pycore lib name
fix pycore lib name format (failure on v3.9)
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Yongjoo Ahn [Thu, 31 Dec 2020 08:52:25 +0000 (17:52 +0900)]
[Android/test] Add test for pytorch in Android
- Add a image classification test for SingleShot and Pipeline API using
PyTorch sub-plugin
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Thu, 31 Dec 2020 08:51:04 +0000 (17:51 +0900)]
[Android/PyTorch] Support pytorch subplugin on Android
- Support pytorch subplugin on Android
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun [Tue, 22 Dec 2020 07:20:08 +0000 (16:20 +0900)]
[Filter] code clean
code clean, add internal function and reduce duplicated code.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Mon, 21 Dec 2020 09:46:25 +0000 (18:46 +0900)]
[Filter] release mem block in combi case
Possible res leak in output combination case, release mem block if output tensor is not in the combination list.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Fri, 8 Jan 2021 04:36:51 +0000 (13:36 +0900)]
[Build/Tizen] dependency to check privilege
set dependency to check privilege in tizen build.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 7 Jan 2021 10:15:43 +0000 (19:15 +0900)]
[If] install header
add missed header for tensor-if custom callback.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Wook Song [Wed, 30 Dec 2020 08:28:29 +0000 (17:28 +0900)]
[Meson/TensorRT] Fix bugs in resolving dependencies on nvlibs
The existing logic to resolve dependencies on nvinfer and nvparsers
have bugs as follows:
1) Even though it is failed to find_library(), the declare_dependency()
creates a valid dependency object that returns True for .found(). For
this reason, the feature is enabled with some missing libraries.
2) Checking for required header files, NvUffParser.h and NvInfer.h, has
been omitted.
This patch fixes the above bugs.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Wook Song [Mon, 28 Dec 2020 10:56:09 +0000 (19:56 +0900)]
[Tests/Rate] Fix -Werror=sign-compare errors
This is a trivial patch to fix -Werror=sign-compare errors in
unittest_rate.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Sangjung Woo [Thu, 31 Dec 2020 06:01:27 +0000 (15:01 +0900)]
[Filter/PyTorch] Use try-catch block when loading pytorch model
If null or invalid paramete is passed when loading the pytorch model,
segmentation fault might occur and it makes runtime error. This patch
fixs this bug.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Thu, 31 Dec 2020 02:01:29 +0000 (11:01 +0900)]
[Spec] Add pytorch & caffe2 filter package and require options
Even though `pytorch_support` is enabled, the pytorch filter is not
built since the necessary option is omitted. This patch newly adds the
pytorch & caffe2 filter packages and the requires option.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
wip
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
gichan-jang [Tue, 5 Jan 2021 05:03:15 +0000 (14:03 +0900)]
[JOIN] Remove unnecessary code and fix minor bugs
Remove unnecessary code and fix minor bugs.(pass NULL param).
Signed-off-by: Gichan Jang <gichan2.jang@samsung.com>
Jaeyun [Mon, 28 Dec 2020 06:58:51 +0000 (15:58 +0900)]
[Converter/Sub] sub-plugin name prefix
define name prefix of tensor-converter sub-plugins.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Mon, 28 Dec 2020 06:24:08 +0000 (15:24 +0900)]
[Converter] property to print sub-plugin list
add new property to get the sub-plugins list of tensor-converter.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Tue, 29 Dec 2020 06:40:06 +0000 (15:40 +0900)]
[CodeClean] element type classification
element name in nnstreamer and general classification of element.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Tue, 29 Dec 2020 07:47:11 +0000 (16:47 +0900)]
[Src/IIO] prevent assertion
prevent assertion, compare no of channles and handle error case.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Wed, 23 Dec 2020 07:05:13 +0000 (16:05 +0900)]
[Filter] change prop name (in/out combi)
Change property name for in/out combination and update document.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Mon, 28 Dec 2020 09:34:04 +0000 (18:34 +0900)]
[If] init property values
remove unnecessary value and init null to avoid exception case using gst-inspect.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Tue, 5 Jan 2021 09:13:27 +0000 (18:13 +0900)]
[Filter/SNPE] detect dlc file
add condition to check .dlc file for auto detection.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Wook Song [Wed, 23 Dec 2020 09:46:23 +0000 (18:46 +0900)]
[Dist/Debian] Revise 'Build-Depends' to support protobuf (>=3.12)
This patch revises the 'Build-Depends' field to use the protobuf
v3.12.3, which is provided by nnstreamer/ppa. This also fixes build
failure for Focal (and the laters) on the launchpad because of unmet
dependencies related to protobuf-compiler17.
Signed-off-by: Wook Song <wook16.song@samsung.com>
gichan-jang [Tue, 22 Dec 2020 05:12:04 +0000 (14:12 +0900)]
[TEST/SSAT] Print progress log
Because the SSAT result is printed after the tests are finished, the test results are not printed in deadlock status.
Change to print the progress logs.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
MyungJoo Ham [Mon, 23 Nov 2020 10:33:52 +0000 (19:33 +0900)]
[Tools/Parser] Parser Rule #4: chain/openchain with URL
Replacing GST methods with parser-only logic:
Rule 4 includes:
chain: openchain link PARSE_URL
openchain: PARSE_URL
With Rule 4, uri-element make is created.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Dongju Chae [Wed, 16 Dec 2020 10:05:11 +0000 (19:05 +0900)]
[CAPI] Wait until the pipeline state is changed
This patch fixes a potential danger after ml_pipeline_construct()
is called. As ml_pipeline_construct() does not wait the pipeline
state change, the following APIs such as set_property may affect
the initial pipeline processing with dummy data (even if the pipe
line is not started).
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
gichan-jang [Fri, 18 Dec 2020 00:33:55 +0000 (09:33 +0900)]
[C-API] Add tensor_if custom usage example
Add tensor_if custom condition usage example.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
gichan-jang [Thu, 17 Dec 2020 06:03:35 +0000 (15:03 +0900)]
[TEST] Add tizen capi test for tensor_if custom
Add tizen CAPI test for tensor_if custom
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
gichan-jang [Thu, 17 Dec 2020 04:29:23 +0000 (13:29 +0900)]
[C-API] If custom condition implementation
If the if-condition is complex and cannot be expressed with tensor_if expressions, user can define custom condition.
Signed-off-by: gichan-jang <gichan2.jang@samsung.com>
Yongjoo Ahn [Mon, 21 Dec 2020 04:04:11 +0000 (13:04 +0900)]
[Android/doc] Add guide for using model file in scoped storage
- Add guide for providing model file to NNS Java API with scoped storage
- Fix guide for tflite nnapi delegate
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Dongju Chae [Tue, 15 Dec 2020 04:25:52 +0000 (13:25 +0900)]
[gRPC/Fix] Decoupling gRPC IDL dependencies
This patch seperates gRPC IDL dependencies (protobuf/flatbuf) using
dlopen(). From now on, gRPC plugin does not have mandatory dependencies
for its IDLs.
Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
Jaeyun [Thu, 17 Dec 2020 08:20:26 +0000 (17:20 +0900)]
[Android/Build] remove unnecessary lib for nnapi
NNFW internally uses nnapi library, this can break tf-lite nnapi option on android-11.
Remove this when building with NNFW.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 17 Dec 2020 10:24:51 +0000 (19:24 +0900)]
[C-API] fix C-API header
Fix API headers with the script in API design guide.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>