Yelin Jeong [Fri, 4 Nov 2022 05:11:28 +0000 (14:11 +0900)]
[test] add tests for dimension declaration
This patch adds tests for dimension declaration.
Related issue #3937
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Thu, 3 Nov 2022 06:53:18 +0000 (15:53 +0900)]
[Caps] update caps for negotiation
This patch adds update caps dimension properties.
`update_caps_dimension` uses peer_caps for negotiation.
`gst_tensor_caps_can_intersect` tries intersecting two tensor caps.
Both functions treat `a:b:c` and `a:b:c:1` equal.
Related issue #3937
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Mon, 14 Nov 2022 08:03:32 +0000 (17:03 +0900)]
[TensorIf] Allow to declare option without full dimension
This patch allows to declare compared-value-option in tensor_if without full dimension.
Undeclared dimension will be filled with zero.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Simon Guillot [Wed, 16 Nov 2022 08:49:17 +0000 (09:49 +0100)]
Update macOS tutorial
- Update the configure command for meson
- Removed table of content is already in the doc template
- Removed tools explanations that are duplicates of their own docs (brew, git)
- Removed commands outputs as they don't provide much info and are not up to date
Signed-off-by: Simon Guillot <cratere_01_tannin@icloud.com>
Simon Guillot [Wed, 16 Nov 2022 08:49:09 +0000 (09:49 +0100)]
Update gitignore
Signed-off-by: Simon Guillot <cratere_01_tannin@icloud.com>
Simon Guillot [Wed, 16 Nov 2022 08:49:03 +0000 (09:49 +0100)]
Add alternative target for PyTorch on macOS
Signed-off-by: Simon Guillot <cratere_01_tannin@icloud.com>
Yongjoo Ahn [Fri, 18 Nov 2022 04:38:00 +0000 (13:38 +0900)]
[svace] Fix mem leak in tensor_filter
- Fix mem leak of the `latency`
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Fri, 18 Nov 2022 04:37:13 +0000 (13:37 +0900)]
[svace] Remove unused code in gstjoin.c
- Remove unused member `discont` from gstjoin
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
gichan [Mon, 24 Oct 2022 02:41:15 +0000 (11:41 +0900)]
[Edge] Change input parameter type of the nns_edge_data_get.
Change input parameter type of the nns_edge_data_get.
Need to SR with https://github.com/nnstreamer/nnstreamer-edge/pull/107
Signed-off-by: gichan <gichan2.jang@samsung.com>
Yongjoo Ahn [Fri, 11 Nov 2022 04:54:14 +0000 (13:54 +0900)]
[build] Add compile arg for pytorch subplugin
- Add `-Wno-unused-parameter` args because recent pytorch contains
unused variables in its source.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Torsten Schulz [Wed, 9 Nov 2022 17:49:43 +0000 (09:49 -0800)]
[decoder/pose] Fix SEGV, ignore pixel when coordinates are out of bounds.
Under some circumstances, setpixel() is called with y==data.height which causes a SEGV. While this might be a rounding error in the caller draw(), the added code gracefully ignores such out-of-bound pixels gracefully.
Signed-off-by: Torsten Schulz <torsten.schulz@gmail.com>
Julien Vuillaumier [Wed, 12 Oct 2022 13:57:14 +0000 (15:57 +0200)]
[filter/core] Add tensor filter latency reporting to the pipeline
Tensor filter executes inferences that may take long time depending on
the model complexity and the compute capabilities of the platform.
When inference duration is long, it happens that some downstream
buffers are dropped because associated timestamp is too far in the past.
It results in a shaky pipeline buffer rate and for instance occurences
of error messages from the sink when operated in live mode (sync=TRUE):
'There may be a timestamping problem, or this computer is too slow.'
Tensor filter implementation already has the option to computes latency
estimates when its element property latency=1 is set.
This change introduces a new property value latency_report=1 that will
when enabled use those latency duration estimates to:
- implement LATENCY query handling to include GstTensorFilter latency
estimate in the overall pipeline latency computation
- track filter latency estimates updates to notify the bus through a
LATENCY message that its latency has changed. It triggers a new round
of LATENCY query in the pipeline to take into account the updated filter
latency.
Signed-off-by: Julien Vuillaumier <julien.vuillaumier@nxp.com>
Jaeyun [Mon, 24 Oct 2022 06:58:16 +0000 (15:58 +0900)]
[Common] tensor format in struct
Move enum flag - tensor_format into tensors-info struct.
To pass flexible tensors to filter sub-plugins, we should indicate tensor format in tensors-info struct, not tensors-config.
Internally tensors-config struct is used for caps negotiation.
TODO: need discussion, should we separate format in each tensor info, so that each mem chunk can express its format. (then, nnstreamer will combine memories: static+flexible in gst-buffer.)
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Wed, 26 Oct 2022 11:15:05 +0000 (20:15 +0900)]
Update documentations with recent data.
- Updated releases.
- Updated products and services.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Thu, 27 Oct 2022 05:57:06 +0000 (14:57 +0900)]
README: add demonstrations from different companies.
Fainders.AI, Klleon.IO, openncc.com, PrintNanny.ai
use NNStreamer to create their products and services.
Their demonstration video clips are presented as
NNStreamer example in README.md with their
permission to use for such purposes.
Product.md is updated accordingly.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
gichan [Tue, 25 Oct 2022 05:05:53 +0000 (14:05 +0900)]
[Edge] Change localhost address for mqtt
Change localhost address for mqtt from tcp://localhost to 127.0.0.1.
* mosquitto lib cannot parse the previous form.
Signed-off-by: gichan <gichan2.jang@samsung.com>
Yelin Jeong [Mon, 24 Oct 2022 08:31:40 +0000 (17:31 +0900)]
[edge] fix test code's multifilesink usage
This patch fixes nnstreamer_edge test code.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
gichan [Tue, 18 Oct 2022 06:43:44 +0000 (15:43 +0900)]
[Join] Remove unnecessary variables.
Remove unnecessary variables from the gstjoin.
Related issue #3938
Signed-off-by: gichan <gichan2.jang@samsung.com>
Yelin Jeong [Tue, 18 Oct 2022 06:44:12 +0000 (15:44 +0900)]
[Doc] fix broken link
This patch fixes broken link in tensor_sink documentation.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
gichan [Fri, 14 Oct 2022 04:36:28 +0000 (13:36 +0900)]
[AITT] Remove AITT build dependency
Remove build dependency of AITT.
Check whether the AITT lib is installed or not at run-time for AITT test.
Signed-off-by: gichan <gichan2.jang@samsung.com>
Yongjoo Ahn [Fri, 14 Oct 2022 07:55:38 +0000 (16:55 +0900)]
[filter] Fix guide document of snpe subplugin
- Fix the outdated custom property description.
- Fix log messages.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Yongjoo Ahn [Thu, 13 Oct 2022 07:06:27 +0000 (16:06 +0900)]
[trivial/build] Fix meson error when the disabled option is given
- Fix meson config error when the 'disabled' options for mxnet is given explicitly
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
gichan [Thu, 6 Oct 2022 05:09:08 +0000 (14:09 +0900)]
[Package] Add nnstreamer-edge dependency to nnstreamer-core
Add nnstreamer-edge dependency to nnstreamer-core.
Signed-off-by: gichan <gichan2.jang@samsung.com>
Jaeyun [Wed, 5 Oct 2022 05:20:02 +0000 (14:20 +0900)]
[Test] dependency to tf-lite ver
Check dependency to tf-lite version to run unittest.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Tue, 4 Oct 2022 10:49:20 +0000 (19:49 +0900)]
filter/armnn: fp16 support macro fix
The preprocessor macro has type. Fix it.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yelin Jeong [Fri, 30 Sep 2022 07:37:51 +0000 (16:37 +0900)]
[Doc] fix broken table in html
This patch fixed broken table in data-type-and-flow-control documentation.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Junhwan Kim [Thu, 19 Aug 2021 08:45:10 +0000 (17:45 +0900)]
[Test] Unittest for filter shared key
Unittest to validate filter with shared key
Signed-off-by: Junhwan Kim <jejudo.kim@samsung.com>
MyungJoo Ham [Tue, 27 Sep 2022 03:09:16 +0000 (12:09 +0900)]
Start of 2.3.0, the new unstable devel version for 2023
This is a new start for a devel release for 2023.
This acts as a start of 2.4.0-RC1.
2.2.0 -> 2.3.0
- 2.3.0 is a devel version for 2.4.0 release. Unstable and experimental features are welcomed in this version.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Thu, 22 Sep 2022 08:15:13 +0000 (17:15 +0900)]
Release of 2.2.0, the new LTS for 2022
This is a new LTS release for 2022.
The next RC development starts with 2.3.0, and
the hotfixes for 2022 releases will be kept in 2.2.y.
2.1.1 -> 2.2.0
- This is NNStreamer 2.2.0 Tizen 7.0 M2 release.
- NNStreamer-Edge.
- Edge-AI (Among-Device AI) implementation is moved to nnstreamer-edge so that non-nnstreamer/gstreamer systems can connect to nnstreamer pipelines.
- NNStreamer-Edge provides inter-pipeline stream connections with various protocols transparently.
- NNStreamer-Edge does not depend on gstreamer/nnstreamer; thus, non-gstreamer systems may connect to nnstreamer/gstreamer pipelines via nnstreamer-edge.
- The "MQTT-Hybrid" protocol for high bandwidth communication w/ mqtt features included.
- ML-Service API phase 2 is completed and released via api.git
- New Subplugins
- tensor_filter / DeepViewRT (NXP)
- tensor_filter / MXNet
- tensor_filter / tensorflow2-lite-custom (allow to designate user-supplied tf2-lite binaries)
- Major features
- tensor-query-client, tensor-query-serversrc/sink use nnstreamer-edge. Protocols are handled at nnstreamer-edge and it now support aitt as one of its backends.
- Float16 (FP16) tensor stream support.
- Rank limit of tensor stream increased: 4 --> 8 (experimental. with known issues)
- Error messages, exception handling, and documentations are improved for application / pipeline writers.
- Minor features
- Added several workarounds for glitches of Qualcomm-SNPE's libraries.
- Support additional .ini file for subplugin configuration. Required by clients who want to separate permissions for controlling user-installable subplugins and system-installable core files.
- Ability to run multiple instances of unit tests in a single machine.
- Add gcc >= 11 support
- Fixed multithreading error in tensor_filter::python
- Python2 dropped. Only Python3 is supported.
- Refactored to increase SAM score (architecture quality assessment).
- Query, GRPC: added minor features requested by users.
- A lot of test cases and fixes introduced.
- Ubuntu 22.04 published.
- Python >= 3.10 support.
- Tensor-decoder::bounding-box. ssd-mobilenet v3 support
- Experimental features
- edgesrc, edgesink. stream pub/sub elements based on nnstreamer-edge
- Known issues
- Multithreading errors in tensor_decoder::python and tensor_converter::python
- FP16 in x64/x86 is not tested. (tested in armv7l/aarch64 only)
- Rank > 4 support is not activated by default. Dimension properties of GSTCAP is not fully backward compatible (to be fixed).
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
gichan [Wed, 14 Sep 2022 09:51:33 +0000 (18:51 +0900)]
[Edge] Support MQTT-hybrid connection
- Support MQTT-hybrid connection for edgesrc and edgesink.
Signed-off-by: gichan <gichan2.jang@samsung.com>
Jaeyun [Mon, 26 Sep 2022 01:57:57 +0000 (10:57 +0900)]
[Spec] dependency to nns-edge
Check dependency to nnstreamer-edge library.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
gichan [Wed, 14 Sep 2022 04:34:17 +0000 (13:34 +0900)]
[EDGE] Support AITT as connection type.
Edgesrc/sink support AITT as connection type.
Add unit test cases.
Signed-off-by: gichan <gichan2.jang@samsung.com>
MyungJoo Ham [Thu, 15 Sep 2022 03:03:06 +0000 (12:03 +0900)]
Edge: allow edgesrc/sink in Tizen
With #3864, edgesrc/sink are added; however, in Tizen API,
apps are restricted to use the allowed elements only.
Add edgesrc/edgesink to that list.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yechan Choi [Thu, 11 Aug 2022 10:18:21 +0000 (19:18 +0900)]
[Gst/Edge] Add edgesrc and edgesink
- Add new elements: edgesrc and edgesink.
- Modify Test for edgesrc and edgesink.
Signed-off-by: Yechan Choi <yechan9.choi@samsung.com>
Signed-off-by: gichan <gichan2.jang@samsung.com>
Yechan Choi [Thu, 4 Aug 2022 05:12:35 +0000 (14:12 +0900)]
[Gst/Edge] Init edgesrc and edgesink
Init skelton of edgesrc and edgesink.
Signed-off-by: Yechan Choi <yechan9.choi@samsung.com>
gichan [Tue, 6 Sep 2022 04:45:34 +0000 (13:45 +0900)]
[Edge] Update changed flag and API
Update changed flag and API of the nnstreamer-edge
After https://github.com/nnstreamer/nnstreamer-edge/pull/60
Signed-off-by: gichan <gichan2.jang@samsung.com>
Yelin Jeong [Thu, 1 Sep 2022 04:56:14 +0000 (13:56 +0900)]
[doxygen] add brief tag on refrain_from_heavy_op_on_float16
This patch adds brief tag on function refrain_from_heavy_op_on_float16
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yelin Jeong [Fri, 5 Aug 2022 08:03:00 +0000 (17:03 +0900)]
[transform] fix transform transpose rank to 4
This patch fixes transform transpose rank to 4.
Increasing NNS_TENSOR_RANK_LIMIT will affect transform transpose.
It should be fixed to 4 until transform transpose supports rank N.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
Yongjoo Ahn [Wed, 14 Sep 2022 06:21:13 +0000 (15:21 +0900)]
[query] Fix client_id type to long long in query_serversink
- Fix client_id type to long long in query_serversink.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Jaeyun [Tue, 6 Sep 2022 08:54:37 +0000 (17:54 +0900)]
[Query] replace deprecated function
Replace deprecated function of edge library.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Tue, 6 Sep 2022 05:07:47 +0000 (14:07 +0900)]
github-action/gbs: Tizen build infra update
The build infra has updated and its binary repository URL
has been updated.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yongjoo Ahn [Tue, 13 Sep 2022 05:28:10 +0000 (14:28 +0900)]
[conf] Update gbs.conf to new repos
- Update repo urls to new ones.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
gichan [Tue, 6 Sep 2022 08:23:53 +0000 (17:23 +0900)]
[TEST] Update query test
- Add timeout option to precent stuck during test.
- Set random available port for query client.
Signed-off-by: gichan <gichan2.jang@samsung.com>
Jaeyun [Wed, 7 Sep 2022 05:45:05 +0000 (14:45 +0900)]
[CodeClean] coverity issues
Fix coverity issues, remove unnecessary header includes and std-move to mem ptr.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Fri, 19 Aug 2022 06:36:07 +0000 (15:36 +0900)]
test:python3 multithreaded python script as a filter (CV2)
With the fear of regressions related with #3822 as
described in #3885, added a test case for multithreaded python
script of CV2.
TODO: add similar cases for converter and decoder
TODO: add negative cases
Fixes #3885
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yongjoo Ahn [Wed, 31 Aug 2022 08:38:28 +0000 (17:38 +0900)]
[query] Add timeout prop for tensor_query_client
- Add timeout prop to decide how much time to wait message from
query server after sending buffer
- Default value is 0, no wait.
- Add simple unittests.
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
Wook Song [Wed, 31 Aug 2022 07:51:17 +0000 (16:51 +0900)]
Tools/Parser: Silence a warning about using a deprecated directive
This patch fixes the following warning about using a deprecated
directive, '%pure-parser'. Note that '%pure-parser' is deprecated since
Bison 2.3b (bison_min_version defined in meson.build is 2.4).
../tools/development/parser/grammar.y:372.1-12: warning: deprecated directive: ‘%pure-parser’, use ‘%define api.pure’ [-Wdeprecated]
372 | %pure-parser
| ^~~~~~~~~~~~
| %define api.pure
../tools/development/parser/grammar.y: warning: fix-its can be applied. Rerun with option '--update'. [-Wother]
Signed-off-by: Wook Song <wook16.song@samsung.com>
MyungJoo Ham [Thu, 18 Aug 2022 04:03:27 +0000 (13:03 +0900)]
test:query launch mosquitto for testing
Launch mosquitto with a random port for testing
and terminate it after testing.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Thu, 18 Aug 2022 02:15:42 +0000 (11:15 +0900)]
Tizen: add mosquitto at build-time for unit testing
Mosquitto is not used for building nnstreamer.
It is used for unit testing; thus, the built binaries
shouldn't have dependencies on Mosquitto.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun [Mon, 1 Aug 2022 09:54:58 +0000 (18:54 +0900)]
[Py/Dims] error case to handle dimension
Handle error case if rank from python script is larger than max rank value.
Update log message in python helper.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
gichan [Tue, 30 Aug 2022 04:27:58 +0000 (13:27 +0900)]
[Doc] Fix incorrect docement link
Fix incorrect file path and names.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Tue, 30 Aug 2022 02:15:04 +0000 (11:15 +0900)]
[TEST] Check more properties of query server.
Check more properties of query server.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Tue, 23 Aug 2022 07:29:40 +0000 (16:29 +0900)]
[TEST] Enable edge releated test only.
If "unit_test" is disabled and "edge_test" is enabled, run query and
edge test.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Fri, 26 Aug 2022 01:47:33 +0000 (10:47 +0900)]
[TEST] Change test name.
To fix xml parser error, change the test name.
Error message: Unescaped '<' not allowed in attributes values
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Tue, 23 Aug 2022 07:45:58 +0000 (16:45 +0900)]
[Query/Test] Set listener port for query client
tensor client of TEST 5-2 and 5-3 use same default port for listener.
Set random available port for query client.
Signed-off-by: gichan <gichan2.jang@samsung.com>
MyungJoo Ham [Tue, 16 Aug 2022 09:39:54 +0000 (18:39 +0900)]
test/query: revive pid retrieval
In recent commits, pid assignment after invoking background processes
has disappeared. Revivde pid assignment so that we can kill unnecessary
processes and avoid indefinite waits.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Sangjung Woo [Thu, 18 Aug 2022 04:28:01 +0000 (13:28 +0900)]
[spec] Disable AI Offloading on VD Cosmos infra
This patch disables the AI offloading feature on VD Cosmos infra.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
MyungJoo Ham [Thu, 11 Aug 2022 04:33:35 +0000 (13:33 +0900)]
proto/flat/flex buffers: reorganize common data structure.
Do not have common data structures of ext modules in the
global-common directory. Put them in the ext modules
to avoid convoluted dependency.
Fixes #3837
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Tue, 16 Aug 2022 06:57:58 +0000 (15:57 +0900)]
filter:pytorch allow gcc only.
Do not allow to build with other compilers.
Refer to #3873 and https://lfscanning.org/reports/lfai/nnstreamer-2022-07-02-
8eb54f0b-f36e-43ff-826f-
80e9f251e17e.html
This is to comply with GPL-3.0 GCC Runtime Exception License of a few headers in PyTorch.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun [Thu, 11 Aug 2022 08:55:42 +0000 (17:55 +0900)]
[Query] fix res leak case
Fix res leak in query elements.
Add destroy-cb function in query-server table to prevent mem leak.
Prevent duplicated creation of edge-handle in event callback.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Tue, 16 Aug 2022 07:52:49 +0000 (16:52 +0900)]
[Spec] feature to enable nns-edge
Add feature to support tensor_query using nnstreamer-edge library.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 11 Aug 2022 08:58:02 +0000 (17:58 +0900)]
[Query/Test] property name in test
Update property name in testcase (connect-type).
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Jaeyun [Thu, 11 Aug 2022 10:50:36 +0000 (19:50 +0900)]
[Query/Test] caps string in query test
Add debug message to print caps string from query-server.
Prevent invalid caps when parsing tensors caps string in testcases.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
gichan [Tue, 16 Aug 2022 05:53:13 +0000 (14:53 +0900)]
[TEST] Disable query-hybrid test
Disable query-hybrid test unitl the test is fixed.
Related issue: #3877
Signed-off-by: gichan <gichan2.jang@samsung.com>
Jaeyun [Mon, 4 Jul 2022 07:09:06 +0000 (16:09 +0900)]
[Edge] remove nns-edge
nnstreamer-edge is moved to other repository.
Remove related files and build scrit.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Yechan Choi [Thu, 11 Aug 2022 16:11:32 +0000 (01:11 +0900)]
[Query] Remove unnecessary lines
This patch removes meaningless Caps releated actions from gst_tensor_query_serversink_start.
Signed-off-by: Yechan Choi <yechan9.choi@samsung.com>
Aymen Sghaier [Tue, 9 Aug 2022 09:02:42 +0000 (11:02 +0200)]
tensor-decoder: add ssd_mobilenet v3 support
This patch adds ssd_mobilent v3 support for post-processing,
it is needed for models without post-processing layer
ssd_mobilenet v3 models handle 2034 anchor boxes
while previous models v2 and v1 handles only 1917 boxes
thus updating the MAX value to 2034 adds support for v3 models
Signed-off-by: Aymen Sghaier <aymen.sghaier@nxp.com>
Yechan Choi [Mon, 1 Aug 2022 07:31:34 +0000 (16:31 +0900)]
[Gst/Edge] Add edge pipeline tests
Add edgesrc and edgesink pipeline tests.
Signed-off-by: Yechan Choi <yechan9.choi@samsung.com>
Yechan Choi [Thu, 21 Jul 2022 08:42:27 +0000 (17:42 +0900)]
[Gst/Edge] Init tests for edgesrc and edgesink
Init 'nnstreamer_edge/runTest.sh' and 'nnstreamer_edge/unittest_edge.cc'.
Modify 'tests/meson.build' for unittest_edge.
Signed-off-by: Yechan Choi <yechan9.choi@samsung.com>
Yongjoo Ahn [Fri, 5 Aug 2022 01:17:05 +0000 (10:17 +0900)]
[test][trivial] Fix return errcode EPIPE to ESTRPIPE
- Change return errcode EPIPE to ESTRPIPE according to ml-api's ret
value
Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
gichan [Fri, 29 Jul 2022 06:42:49 +0000 (15:42 +0900)]
[Query] Update query for new edge interface
- Update query for new edge interface.
- Separate ip and port for self and destination.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Fri, 29 Jul 2022 06:41:05 +0000 (15:41 +0900)]
[Edge] Update edge lib
- Update new edge interface.
- Separate ip and port for self and destination.
Signed-off-by: gichan <gichan2.jang@samsung.com>
MyungJoo Ham [Tue, 2 Aug 2022 09:53:32 +0000 (18:53 +0900)]
ubuntu: force enable mqtt
Force-enable mqtt for PPA / pdebuild builds.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Tue, 2 Aug 2022 04:49:23 +0000 (13:49 +0900)]
python: fix python 3.10 PyObject type errors.
From Python 3.10 python->C/C++ object transfer
has stricter type checks. Floats are no more
supported by PyLong.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Yelin Jeong [Tue, 5 Jul 2022 08:31:14 +0000 (17:31 +0900)]
[Filter] support NNS_TENSOR_RANK_LIMIT 8
This patch changes filter pytorch and tensorflow lites
to support NNS_TENSOR_RANK_LIMIT 8
tensor_filter_pytorch's invoke does not have a problem when NNS_TENSOR_RANK_LIMIT is 4.
But when rank limit is 8, model->invoke has an exception while running the model.
Similarly, tensor_filter_tensorflow_lite's tflite_setInputDim has a problem.
TFLiteInterpreter::setInputTensorsInfo now iterates all possible ranks starting from MAX.
If NNS_TENSOR_RANK_LIMIT changed to 8, there is a case which ResizeInputTensor works
while AllocateTensors does not work.
So I chagned to iterate from MIN, and Allocate Tensors inside for loop.
Signed-off-by: Yelin Jeong <yelini.jeong@samsung.com>
MyungJoo Ham [Mon, 1 Aug 2022 06:58:29 +0000 (15:58 +0900)]
query: doxygen tag comment fix
Use /** for doxygen-tag comments.
@gichan-jang : please apply this to nnstreamer-edge.git .
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Mon, 1 Aug 2022 06:50:41 +0000 (15:50 +0900)]
query: fix null pointer access
After the while loop, addrs may be a nullptr.
This causes a segmentation fault found with pdebuild/ubuntu 22.04.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Jaeyun [Mon, 1 Aug 2022 07:39:34 +0000 (16:39 +0900)]
[CodeClean] fix typo, indent
Code clean, trivial, fix typo / indent and add feature for sub-plugin in meson.
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
MyungJoo Ham [Fri, 29 Jul 2022 04:25:29 +0000 (13:25 +0900)]
ubuntu: lose python 2
Python3 is no more supported in 22.04. Lose it.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
MyungJoo Ham [Wed, 20 Jul 2022 07:43:41 +0000 (16:43 +0900)]
debian: nnfw and tf-1 is now optional.
We are (temporarily?) dropping nnfw and tensorflow-1 support
from Ubuntu 22.04. Make dependencies to nnfw, tf-1 optional
in Debian build scripts.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
gichan [Fri, 22 Jul 2022 01:47:58 +0000 (10:47 +0900)]
[Query] Implement mqtt-hybrid
Implement mqtt-hybrid using nnstreamer-edge lib.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Fri, 22 Jul 2022 01:24:31 +0000 (10:24 +0900)]
[Edge] Add mqtt-hubrid feature
Add mqtt-hybrid feature to nns-edge lib.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Fri, 22 Jul 2022 00:47:54 +0000 (09:47 +0900)]
[Edge] Sync with nnst-edge repo latest
Sync with nnstreamer-edge repo latest.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Fri, 22 Jul 2022 11:05:58 +0000 (20:05 +0900)]
[Join] Don't wait all pads get eos event.
Don't wait all pad get eos event.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Fri, 22 Jul 2022 10:23:49 +0000 (19:23 +0900)]
[TEST] Enable query test on ubuntu
Let's enable query test on ubuntu.
It seems that the problem that the test sometimes failed has now been solved.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Mon, 25 Jul 2022 05:15:51 +0000 (14:15 +0900)]
[TEST] Apply background test to grpc
- Apply background test to grpc.
Signed-off-by: gichan <gichan2.jang@samsung.com>
Jaeyun [Thu, 21 Jul 2022 02:09:36 +0000 (11:09 +0900)]
[Svace] code clean and fix svace
Code clean, fix svace issues.
- check null string when getting caps from edge handle
- fix mem leak case
- fix invalid data comparison
Signed-off-by: Jaeyun <jy1210.jung@samsung.com>
Yechan Choi [Wed, 20 Jul 2022 07:15:30 +0000 (16:15 +0900)]
[Doc] Update how-to-write-testcase.md
This patch updates 'runTest.sh' template.
Signed-off-by: Yechan Choi <yechan9.choi@samsung.com>
MyungJoo Ham [Thu, 14 Jul 2022 04:49:27 +0000 (13:49 +0900)]
tests/grpc: remove timeout command
GBS does not support timeout. Remove it.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
gichan [Tue, 19 Jul 2022 09:39:58 +0000 (18:39 +0900)]
[Edge/Query] Replace caps info when set edge info.
Replace caps info when set edge info.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Thu, 14 Jul 2022 07:35:22 +0000 (16:35 +0900)]
[Edge] Disable format warning
Disable format warning to avoid build failure on macOS
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Thu, 14 Jul 2022 05:32:02 +0000 (14:32 +0900)]
[Edge] Update edge lib
Update edge lib
- This chagnes will be removed soon.
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Wed, 8 Jun 2022 01:07:49 +0000 (10:07 +0900)]
[TEST] Modify query test
- Some parameters are removed, change the query test.
- Apply back ground test
Signed-off-by: gichan <gichan2.jang@samsung.com>
gichan [Wed, 8 Jun 2022 00:55:44 +0000 (09:55 +0900)]
[Edge] Tensor query TCP connection
Implement tensor query TCP connection using nnstreamer-edge lib.
Signed-off-by: gichan <gichan2.jang@samsung.com>
MyungJoo Ham [Thu, 14 Jul 2022 08:28:34 +0000 (17:28 +0900)]
doc/distro-features: update features per distro
Update the list of features deployed via distro releases.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Sangjung Woo [Wed, 6 Jul 2022 02:19:34 +0000 (11:19 +0900)]
[Android] Update file list of nnstreamer elements
Since the paths and names of nnstreamer elements are changed, this patch
updates the Android NDK build file.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Wed, 6 Jul 2022 01:36:55 +0000 (10:36 +0900)]
[Doc] Update markdown file list of nnstreamer elements
Since the paths and names of nnstreamer elements are changed, this patch
updates the markdown file list of nnstreamer elements.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Sangjung Woo [Sun, 3 Jul 2022 14:14:12 +0000 (23:14 +0900)]
[Common] Reduce Dependency complexity to increase the SAM score
There are lots of modules in /get/nnstreamer folder and it causes a high
dependency complexity. This patch reduces the module number by
integrating elements. Eventually it increases the DEP score from 2.73
to 5.0.
Signed-off-by: Sangjung Woo <sangjung.woo@samsung.com>
Yechan Choi [Tue, 19 Jul 2022 06:00:11 +0000 (15:00 +0900)]
[Gst/MQTT/Sink] fix: Remove duplicated g_free for the message buffer
This patch remove duplicated g_free for the message buffer(self->mqtt_msg_buf).
Signed-off-by: Yechan Choi <yechan9.choi@samsung.com>
MyungJoo Ham [Thu, 14 Jul 2022 02:40:45 +0000 (11:40 +0900)]
doc/edge-ai: update documentation
Add more explanation on edge-AI / among-device AI
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>