Yelin Jeong [Tue, 14 May 2024 04:56:14 +0000 (13:56 +0900)]
[decoder] Remove dependency from base class to derived class
This patch removes dependency from Bounding box class to properties.
setBoxDecodingMode does not need to be modified even if a new box property added.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Wed, 8 May 2024 08:48:22 +0000 (17:48 +0900)]
[decoder] Remove subclasses in the header
This patch removes subclasses in the tensordec-boundingbox header.
Each box properties are located inside box_properties subdir.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Thu, 25 Apr 2024 07:18:20 +0000 (16:18 +0900)]
[CodeClean] Change macro to subclass variable, use enum class
This patch changes macro to subclass static-const variable.
Also use enum class instead of unclear integer code.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Fri, 15 Mar 2024 03:12:32 +0000 (12:12 +0900)]
[Refactoring] Split bounding_box struct
This patch splites properties so that bounding_box struct
does not have properties for all cases.
Also some functions like bb_setOptions, bb_decode have too many if cases,
so I replaced it to use pure virtual functions.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
hyunil park [Thu, 16 May 2024 07:36:51 +0000 (16:36 +0900)]
[edgesrc] Add checking caps before getting tensor size
- Prevent Gstreamer-CRITICAL message when caps is null
Signed-off-by: hyunil park <hyunil46.park@samsung.com>
Yelin Jeong [Mon, 13 May 2024 03:43:25 +0000 (12:43 +0900)]
[action] Add check-rebuild reusable workflows
This patch adds check-rebuild reusable workflows and
replace each step in workflow.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
MyungJoo Ham [Sat, 4 May 2024 02:02:38 +0000 (11:02 +0900)]
decoder/bb/yolov8 Elaborate error message
If input tensor dim/type is invalid, describe the given dim/type.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yelin Jeong [Tue, 30 Apr 2024 09:34:30 +0000 (18:34 +0900)]
[action] skip python test in riscv
This patch skips python test in riscv build action.
Although .so file created and PYTHONPATH set, python could not
find nnstreamer module in riscv.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Tue, 26 Mar 2024 23:47:11 +0000 (08:47 +0900)]
[filter] use tensor filter framework v1 in tensor_filter_python3
This patch makes tensor_filter_python3 to use tensor_filter_subplugin.
PYCore remains the same, but the type of callback function has been changed.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Tue, 26 Mar 2024 23:45:51 +0000 (08:45 +0900)]
[TDD] add unittest for python3 tensor_filter subplugin
This patch adds unittest for python3 tensor_filter subplugin.
python3 tensor_filter will be upgraded to use v0 to v1.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
hyunil park [Fri, 3 May 2024 01:04:04 +0000 (10:04 +0900)]
[tensor_trainer] bugfix: Add exception handling for a non-existent model config file
Added exception handling for a non-existent model config file
Signed-off-by: hyunil park <hyunil46.park@samsung.com>
Yongjoo Ahn [Thu, 2 May 2024 06:37:15 +0000 (15:37 +0900)]
[actions] Make pubilder cache daily
This patch makes the daily pdebuild workflow save the cache key with date postfix and outdate previous cache. Then the pdebuild.yml workflow can use the fresh cache.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Thu, 2 May 2024 06:21:59 +0000 (15:21 +0900)]
[actions] Update gbs workflows to be run on 22.04
- Since Ubuntu 22.04 supports gbs from this year, let's switch to it.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun Jung [Thu, 2 May 2024 04:45:39 +0000 (13:45 +0900)]
[Build] onnx-runtime from tizen 9.0
Update spec to enable ONNX runtime from Tizen 9.0.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Dongkyun Son [Thu, 14 Mar 2024 00:21:13 +0000 (09:21 +0900)]
build: update header path
Fix fatal error: asm-arm/hwcap.h: No such file or directory
Signed-off-by: Dongkyun Son <dongkyun.s@samsung.com>
Yongjoo Ahn [Tue, 30 Apr 2024 06:27:57 +0000 (15:27 +0900)]
[spec] Fix lcov options for different Tizen/lcov versions
- Set proper lcov options w.r.t. Tizen/lcov versions.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Fri, 26 Apr 2024 08:46:33 +0000 (17:46 +0900)]
[action] Save pbuilder cache daily and use it in each PR
- Let the daily job `update_pbuilder_cache.yml` save cache.
- Let the PR job `pdebuild.yml use proper cache for each arch.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Fri, 26 Apr 2024 08:34:39 +0000 (17:34 +0900)]
[action] Save gbs cache daily and restore gbs cache per PR
- Let the daily job `update_gbs_cache.yml` save cache for every build arch.
- Let the PR job `gbs_build.yml` restore proper cache for each arch.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Fri, 26 Apr 2024 08:23:30 +0000 (17:23 +0900)]
[action] Diable cache actions except for the gbs build
- Saving cache in each PR consumes too much space.
- To utilize the cache, we need to update each cache in main branch periodically.
Before introducing such action, disable cache for a while.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Fri, 26 Apr 2024 08:19:44 +0000 (17:19 +0900)]
[action] Let pdebuild action do not build arm64
- Currently `pdebuild --architecture arm64` is equivalent as `pdebuild --architecture amd64`.
- Drop arm64 build.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
MyungJoo Ham [Mon, 29 Apr 2024 08:06:57 +0000 (17:06 +0900)]
github-action/macos build fix
Github-action macos build started spitting:
```
Run actions/setup-python@v1
with:
python-version: 3.x
architecture: x64
env:
changed_file_list: /var/folders/3m/p59k4qdj0f17st0gn2cmj3640000gn/T/tmp.b0uhtmFUzp
rebuild: 1
Error: Version 3.x with arch x64 not found
Available versions:
```
Similar with https://github.com/actions/setup-python/issues/162
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Wed, 17 Apr 2024 13:33:47 +0000 (22:33 +0900)]
Ubuntu: mantic & noble support
I decided to use pytorch being integrated by Ubuntu (debian/sid),
and this package provides libtorch-dev for C++ binding.
Trying to address #4431
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Fri, 19 Apr 2024 10:59:52 +0000 (19:59 +0900)]
Update Dockerfile
1. Update 18.04 --> 22.04
2. Add gpg-agent to resolve docker build error in 22.04
3. Add mirror ARG for faster usage
- e.g., w/ --build-arg="UBUNTU_APT_MIRROR=http://mirror.kakao.com/ubuntu/"
Addresses #4432
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun Jung [Mon, 22 Apr 2024 09:53:08 +0000 (18:53 +0900)]
[CodeClean] handle hashtable function
Code clean, check hash-table util function result.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Jaeyun Jung [Mon, 22 Apr 2024 06:33:33 +0000 (15:33 +0900)]
[CodeClean] fix typo
Code clean, fix indent and typo in source files.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Yongjoo Ahn [Wed, 17 Apr 2024 04:11:03 +0000 (13:11 +0900)]
[test] Set a `gstTestBackground` SSAT tc as not critical
Set the gstTestBackground TCs as not critical:
The another background pipeline (videotestsrc ! ... ! filesink) from
`gstTestBackground` sometimes does not make test file properly.
If following tests succeed, It means background pipeline works well.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Wed, 17 Apr 2024 05:37:16 +0000 (14:37 +0900)]
[ncnn] Use g_message for accl log
This patch makes ssat test (grep "accl = gpu" string) works.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun Jung [Tue, 16 Apr 2024 07:22:12 +0000 (16:22 +0900)]
[CodeClean] unnecessary mem allocation
Code clean, remove unnecessary memory allocation while creating edge handle.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Yongjoo Ahn [Mon, 15 Apr 2024 08:52:33 +0000 (17:52 +0900)]
[workflow] Fix pbuilder cache permission error
- Currently pbuilder workflow does not use stored cache for permission
error. This commit resolve the issue.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun Jung [Fri, 12 Apr 2024 12:46:21 +0000 (21:46 +0900)]
[Query] util function using integer id
To prevent double free case, remove query handle and use integer id.
Also, add util function to hide edge handle in query elements and fix null ptr case.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
gichan2-jang [Fri, 12 Apr 2024 01:48:41 +0000 (10:48 +0900)]
[Query] Release edge handle when stopping the playing
Problem: When state changes from PAUSED to NULL,the tensor_query_serversrc cannot switch to NULL state because it keeps waiting for data pop.
Solution: Change the creation and destruction of server data and edge handle to be managed according to the state.
READY->PAUSED: Create query server common data
PAUSED->PLAYING: Create nns-edge handle
PLAYING->PAUSED: Rlease nns-edge handle
PAUSED->READY: Descruct qeury server common data
Releated issue: https://github.com/nnstreamer/api/issues/487
Signed-off-by: gichan2-jang <gichan2.jang@samsung.com>
Jaeyun Jung [Mon, 8 Apr 2024 08:10:52 +0000 (17:10 +0900)]
[Edge/CodeClean] remove unnecessary connection timeout
Fix svace issue, remove unnecessary code to check connection timeout.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
hyunil park [Tue, 26 Mar 2024 02:11:52 +0000 (11:11 +0900)]
[tensor_trainer] Add condition to stop model training
- When a request to stop model training is received,
if it has already been completed, it is ignored
Signed-off-by: hyunil park <hyunil46.park@samsung.com>
gichan2-jang [Tue, 19 Mar 2024 01:52:24 +0000 (10:52 +0900)]
[Tizen] Fix gcov build error
Due to the lcov 2.0 upgrade, the warning is changed to error so the gcov build fails.
Ignore this case. (Tizen PM guide)
Signed-off-by: gichan2-jang <gichan2.jang@samsung.com>
MyungJoo Ham [Wed, 13 Mar 2024 05:42:31 +0000 (14:42 +0900)]
meson: explicit 'enabled' should spit errors if not found
If -Dsupport-ncnn=enabled is given and ncnn is not found,
an error should be generated by meson.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Fri, 8 Mar 2024 04:42:35 +0000 (13:42 +0900)]
decoder/direct_video: detect element size mismatch
Return error with explicit error message (GST_ERROR) if
the element size mismatches.
For example, float32 tensor stream cannot be converted
to RGB video stream without tensor_transform.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
gichan2-jang [Tue, 12 Mar 2024 07:05:15 +0000 (16:05 +0900)]
[AITT] Skip AITT test
Skip AITT gtest and ssat until aitt-ses is available.
Signed-off-by: gichan2-jang <gichan2.jang@samsung.com>
Wook Song [Mon, 26 Feb 2024 12:02:52 +0000 (21:02 +0900)]
Filter/MLAgent: Update build dependency on MLOps Agent
This patch updates build dependency on MLOps Agent. Note that MLAgent
has been renamed to MLOps Agent and provided from a new repository
separated from the API repository.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Yongjoo Ahn [Thu, 7 Mar 2024 04:04:34 +0000 (13:04 +0900)]
[trivial] Fix bogus date in chagnelog
- Fix rpmbuild warning about wrong date
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun Jung [Mon, 4 Mar 2024 04:39:27 +0000 (13:39 +0900)]
[CodeClean] set null after free
Clearly set null after releasing the name in tensor-info struct.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Jaeyun Jung [Thu, 22 Feb 2024 09:58:04 +0000 (18:58 +0900)]
[CodeClean] missing lock
Fix svace issues, add missing lock.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Suyeon Kim [Thu, 15 Feb 2024 01:39:49 +0000 (10:39 +0900)]
[build/debian] add dependency to onnxruntime
- add new pkg for onnxruntime in debian build
Signed-off-by: Suyeon Kim <suyeon5.kim@samsung.com>
Yongjoo Ahn [Wed, 14 Feb 2024 08:56:05 +0000 (17:56 +0900)]
[protobuf] Fix memory leak in nnstreamer_protobuf
- Make GstMemory with properly set GDestroyNotify func
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Wed, 14 Feb 2024 08:53:19 +0000 (17:53 +0900)]
[filter] Fix memory leak in reload model
- Fix memory leak when reload tflite model
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Wed, 14 Feb 2024 08:52:28 +0000 (17:52 +0900)]
[fix] Resolve memory leak in tensor_if
- Free g_list and GValue properly.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Wed, 14 Feb 2024 08:51:23 +0000 (17:51 +0900)]
[test] Freeing memory during unittests
- Unref memory properly used in unittests.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Wed, 14 Feb 2024 08:49:48 +0000 (17:49 +0900)]
[fix] Free option context in gtest
- Call g_option_context_free in unittest_latency
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Mon, 19 Feb 2024 01:43:43 +0000 (10:43 +0900)]
[spec] Suppress ORC log level
- Suppress ORC logs as showing WARNING or higher logs to reduce too many
them during gbs unittests.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
MyungJoo Ham [Wed, 7 Feb 2024 07:53:37 +0000 (16:53 +0900)]
test/datareposinK: timing error in test case
Occasionally, in github-action CI, datareposink.writeFlexibleTensors_n
fails due to synchronization errors:
```
[ RUN ] datareposink.writeFlexibleTensors_n
../tests/nnstreamer_datarepo/unittest_datareposink.cc:570: Failure
Expected: (file_info) != (nullptr), actual: NULL vs (nullptr)
[ FAILED ] datareposink.writeFlexibleTensors_n (173 ms)
```
It happens when the pipeline is set NULL before the file 'flexible.data'
is writtn within the pipeline.
Allow some time (0.1s) before setting it NULL.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yongjoo Ahn [Thu, 8 Feb 2024 07:31:54 +0000 (16:31 +0900)]
[region] Fix memory leak in tensor_region
- mem argument of `gst_tensor_meta_info_append_header` should be freed.
- Properly free old memory after the call and replace the buffer with
new memory
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Thu, 8 Feb 2024 07:19:47 +0000 (16:19 +0900)]
[test] Fix mem leak in tflite unittest
- Fix memory leak by unref
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Thu, 8 Feb 2024 07:17:07 +0000 (16:17 +0900)]
[common] Fix mem leak in extra tensors
- Extra tensor names stored in GstMemory leaks.
- Let the extra tensor do not store names.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
MyungJoo Ham [Thu, 8 Feb 2024 08:17:00 +0000 (17:17 +0900)]
github-action: indent style error --> warning
Indent style error is set down to warning.
Until we have ZERO indent style error in overall,
let's keep them warning.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
linuxias [Thu, 8 Feb 2024 07:39:38 +0000 (16:39 +0900)]
[mlagent] Fix misspelling variable naming and log
- change misspelling 'stringied' to 'stringfied'
Signed-off-by: linuxias <linuxias@gmail.com>
MyungJoo Ham [Wed, 24 Jan 2024 02:54:48 +0000 (11:54 +0900)]
github-action: import all TAOS-CI post-build
- gbs build for x64, x86, arm32, arm64
- pdebuild for { x64, arm64 } x { 22.04, 20.04 }
- yocto build w/ eSDK (Yocto 4.0.15)
- android build w/ nttld/setup-ndk
to enable such github actions,
- android / jni build script fix
and, drop TAOS-CI. (all imported!)
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yongjoo Ahn [Tue, 6 Feb 2024 04:33:40 +0000 (13:33 +0900)]
[common] Fix mem leak in gst_tensor_buffer_append_memory
- last_memory should be released before calling
`gst_buffer_replace_memory`
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
MyungJoo Ham [Tue, 23 Jan 2024 07:52:55 +0000 (16:52 +0900)]
actions: add sloccount, prohibited-words, signed-off-by, ...
The following TAOS-CI pr-prebuild checks are imported
- sloccount
- prohibited words
- signed off by
- shellcheck
- flawfinder
- coverity
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yongjoo Ahn [Mon, 15 Jan 2024 07:51:39 +0000 (16:51 +0900)]
[test] Fix snpe filter test to support two API versions
- Add dlc model files for SNPE2.
- Rename SNPE1 model files.
- Fix unittest to set proper model files.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Mon, 15 Jan 2024 07:49:21 +0000 (16:49 +0900)]
[filter] Add SNPE filter supports API ver 2
- Add a SNPE filter source `tensor_filter_snpe.cc` to support SNPE API version 2
- It utilizes new C APIs.
- Let meson decide cpp source file to compile by checking snpe_api_version
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
MyungJoo Ham [Mon, 22 Jan 2024 08:17:42 +0000 (17:17 +0900)]
actions: add cppcheck, doxygen-build, executable, ...
The following TAOS-CI pr-prebuild checks are imported
- cppcheck
- doxygen-build
- executable
- hardcoded-path
- misspelling
- nobody
- timestamp
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Fri, 19 Jan 2024 07:12:25 +0000 (16:12 +0900)]
actions: static/rpm-spec check added
RPM-SPEC runs rpmlint if .spec file is updated.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Fri, 19 Jan 2024 06:39:10 +0000 (15:39 +0900)]
actions: static/doxygen-tag style clean
Make the code style consistant with other recent checks.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Fri, 19 Jan 2024 06:32:37 +0000 (15:32 +0900)]
actions: more static checks from TAOC-CI
- indent
- newline
- pylint
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun Jung [Thu, 25 Jan 2024 12:12:27 +0000 (21:12 +0900)]
[CodeClean] fix svace issue
1. change data type to handle gst-memory.
2. use util function to get nth tensor info.
3. add null-init in filter-edgetpu.
4. fix use-after-free case when parsing accel in tensor-filter.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
MyungJoo Ham [Wed, 17 Jan 2024 06:40:06 +0000 (15:40 +0900)]
github-action: rebuild only if it's required
This adds a workflow routine that checks if rebuild is needed.
Then, if there is no changes in source code, skip rebuilding
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Wook Song [Tue, 23 Jan 2024 05:10:24 +0000 (14:10 +0900)]
GitHub/Workflows: Add an action to check C++ source file format
This patch adds a GitHub Action workflow to check C++ source file
format.
Signed-off-by: Wook Song <wook16.song@samsung.com>
[Imported from deviceMLOps.MLAgent]
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Wed, 24 Jan 2024 03:55:15 +0000 (12:55 +0900)]
github-action: do not run static-checks on deleted files.
The git-changed files may include deleted files.
Do not run static-cchecks on deletec files.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Tue, 23 Jan 2024 02:14:31 +0000 (11:14 +0900)]
test: nondeterministic unit test error.
Due to multithread nondeterminism, we get
occasional unit test error from the "new_data_cb"
callback.
Create a lock and make data local to the function.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun Jung [Mon, 22 Jan 2024 05:07:44 +0000 (14:07 +0900)]
[Filter] remove space of model file
To prevent not-found error, remove space of model path.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
MyungJoo Ham [Fri, 12 Jan 2024 08:45:27 +0000 (17:45 +0900)]
actions: add static checks
Add static checkers & verifiers to github-actions.
Initially, clang-format for C++ files and file size checker
are migrated from TAOS-CI.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Tue, 7 Feb 2023 07:22:09 +0000 (16:22 +0900)]
github-action/risc-v test update
Use dockerfile of nnstreamer's fork designed for nnstreamer packages.
Enable gtest, too.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Suyeon Kim [Thu, 18 Jan 2024 02:01:58 +0000 (11:01 +0900)]
[fix/svace] fix svace issue
Fix covertiy and SVACE issue
- model_path isn't initialized. fixed it.
Signed-off-by: Suyeon Kim <suyeon5.kim@samsung.com>
Suyeon Kim [Wed, 17 Jan 2024 05:33:59 +0000 (14:33 +0900)]
[add/onnxruntime] Update onnxruntime_support on
add true default onnxruntime option for Tizen releases
Signed-off-by: Suyeon Kim <suyeon5.kim@samsung.com>
hyunil park [Tue, 16 Jan 2024 09:56:49 +0000 (18:56 +0900)]
[tensor_trainer] Move the function of checking invalid parameters
- Move gst_tensor_trainer_check_invalid_param to enable setting properties in PAUSED states
Signed-off-by: hyunil park <hyunil46.park@samsung.com>
Jaeyun Jung [Fri, 12 Jan 2024 11:53:24 +0000 (20:53 +0900)]
[CodeClean] util to get list size
Code clean, fix indent and util function to get list size.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Jaeyun Jung [Fri, 12 Jan 2024 11:51:48 +0000 (20:51 +0900)]
[Filter/ArmNN] fix mem leak
Fix mem leak, free model path in destructor.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Yongjoo Ahn [Fri, 12 Jan 2024 07:35:59 +0000 (16:35 +0900)]
[build] Let meson check API version of SNPE
- Let meson.build check SNPE API version.
- Added compile flag `SNPE_VERSION_MAJOR` would be used in future commits.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Fri, 12 Jan 2024 07:52:47 +0000 (16:52 +0900)]
[filter] Rename `tensor_filter_snpe.cc` to `tensor_filter_snpe_v1.cc`
- Current source code targets SNPE version 1.
- Future commits will add source code targets SNPE version 2.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yelin Jeong [Fri, 12 Jan 2024 06:07:35 +0000 (15:07 +0900)]
[tests] Add SSAT test for padding mode in tensor_transform
This patch adds SSAT test for padding mode in tensor_transform.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Fri, 12 Jan 2024 05:00:09 +0000 (14:00 +0900)]
[transform] Add tensor padding mode in tensor_transform
This patch adds tensor padding mode in tensor_transform.
tensor padding has options like this.
left, right, top, bottom, front, back, type (NCHW or NHWC).
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Fri, 12 Jan 2024 04:47:36 +0000 (13:47 +0900)]
[common] Move enum tensor_layout
This patch moves tensor_layout enum to tensor_typedef.
tensor_layout can be used in other elements.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yongjoo Ahn [Fri, 5 Jan 2024 09:20:45 +0000 (18:20 +0900)]
[trivial] Fix multiline comments to meet doxygen requiremnent
- Fix multiline comments in unittest_mlagent.cc to satisfy CI
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Fri, 5 Jan 2024 09:17:27 +0000 (18:17 +0900)]
[mlagent] Let `mlagent_get_model_path_from` returns uri in fallback
- Let the function returns properly allocated gchar* in fallback case.
- Fix memleak (g_strfreev).
- Fix memleak in a testcase.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Fri, 5 Jan 2024 08:41:38 +0000 (17:41 +0900)]
[test] Add a missing header in mock_mlagent.h
- Add a missing header <utility> in mock_mlagent.h
- It declares `std::exchange`
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Suyeon Kim [Tue, 9 Jan 2024 01:26:24 +0000 (10:26 +0900)]
[fix/onnxruntime-filter] fixed tensor with negative value in shape
Some onnx models had free dimensions for batch. ex) [None,3,720,720]
It fixed that creating tensor with negative value in shape '''Ort::Value''' is treated as 1.
Signed-off-by: Suyeon Kim <suyeon5.kim@samsung.com>
Jaeyun Jung [Mon, 8 Jan 2024 10:34:30 +0000 (19:34 +0900)]
[Py/CodeClean] pylock after checking ptr
Code clean, apply gil after checking null ptr.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Yongjoo Ahn [Fri, 5 Jan 2024 08:20:36 +0000 (17:20 +0900)]
[build] Remove unnecessary BuildRequires
- The latest tflite2 tizen package has its own flatbuffers header
internally. Let's remove the `BuildRequires: flatbuffers-debvel`
- Let meson check the header when build_platform is not tizen
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun Jung [Mon, 8 Jan 2024 10:36:01 +0000 (19:36 +0900)]
[Pkg] fix library name for nns internal
nnstreamer-internal pkg requires nns-single library.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
MyungJoo Ham [Wed, 13 Dec 2023 05:41:54 +0000 (14:41 +0900)]
Centralize python interpreter init/fini for subplugins
Python subplugins of decoder, converter, filter should
share the init/fini status.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Wed, 13 Dec 2023 04:44:46 +0000 (13:44 +0900)]
filter/python3: revise GIL access.
Control GIL at C callbacks.
Control mutex at C++ class.
As in decoder/converter changes.
This is the last step before the final step for #3834
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Tue, 12 Dec 2023 10:10:06 +0000 (19:10 +0900)]
converter::python make them thread safe with GIL
Apply GIL control to converter::python3 as in we do with filter::python3.
Fixes converter part of #3834
Overrides #3872
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun Jung [Tue, 2 Jan 2024 05:29:09 +0000 (14:29 +0900)]
[CodeClean/grpc] clearly define release function
The type of data pushed into queue is gst-buffer.
Clearly set the release function when calling free.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Jaeyun Jung [Wed, 3 Jan 2024 05:01:50 +0000 (14:01 +0900)]
[CodeClean] fix indent and codestyle
Trivial, fix indent and codestyle for line comment.
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Yongjoo Ahn [Mon, 11 Dec 2023 09:03:38 +0000 (18:03 +0900)]
[build] Halt meson setup when NOT-GCC is provided for pytorch subplugin
- Halt meson setup procedure when NOT-GCC is given and pytorch-support
is enabled. Rather than warning and go.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun Jung [Tue, 2 Jan 2024 09:40:23 +0000 (18:40 +0900)]
[Pkg] header file for devel package
1. move util for trainer (single-devel > devel)
2. update library (link to nns-single, internal devel package)
Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
Wook Song [Thu, 14 Dec 2023 04:08:03 +0000 (13:08 +0900)]
Dist/Tizen: Add an option to control MLAgent support
This patch adds an option for MLAgent support control to the Tizen RPM
spec file.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Wook Song [Thu, 14 Dec 2023 03:57:55 +0000 (12:57 +0900)]
Filter/MLAgent: Add unit test cases for parsing MLAgent URIs
This patch adds test cases for unit testing of parsing the MLAgent URIs.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Wook Song [Tue, 28 Nov 2023 04:38:19 +0000 (13:38 +0900)]
Filter/MLAgent: Implement the JSON parsing logic to get model's path
This patch adds the logic to parse the C-style stringified JSON data
gathered from the ML Agent in order to convert the given URI to the
model's path.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Wook Song [Mon, 27 Nov 2023 10:33:37 +0000 (19:33 +0900)]
Filter/MLAgent: Do not use g_autoptr for a const pointer
This is a trivial bug fix that removes the uneccessary attribute,
g_autofree, for the c string gathered from GObject, which is a const
pointer.
Signed-off-by: Wook Song <wook16.song@samsung.com>
Wook Song [Tue, 21 Nov 2023 04:47:04 +0000 (13:47 +0900)]
Filter/MLAgent: Use a proper data type argument for ml_agent_model_get
This patch is a trivial bug fix that changes the data type of an
argument for ml_agent_model_get.
Signed-off-by: Wook Song <wook16.song@samsung.com>