박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 02:41:36 +0000 (11:41 +0900)]
[NNAPI test] Introduce asserts on input types (#1457)
This commit introduces asserts on input types as float32 is the only
input type that nnapi_test supports currently.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
최형규/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 02:33:04 +0000 (11:33 +0900)]
Do not delegate temporary tensors to NNAPI. (#1359)
- also added delegation for MUL, and set the default scale to be 0.0f.
PiperOrigin-RevId:
195288948
This is a cherrypick of https://github.sec.samsung.net/RS7-STAR/Tensorflow/pull/41
with modification to (1) resolve conflict and (2) apply new format.
Therefore this is a modification of cherrypick of origitnal Tensorflow from
https://github.com/tensorflow/tensorflow/commit/
a16ba4fc0d3faec077c689f3f361264978a2d3cb#diff-
f4a5031c0f2ec4e55c3a89bf4c21c7f8
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 02:28:49 +0000 (11:28 +0900)]
CAST_EX nnapi_delegate (#1429)
1. Add add_cast_ex_params
2. Add nnapi call from nnapi_delagate.cpp
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 31 May 2018 01:24:49 +0000 (10:24 +0900)]
Build Android TFLite JNI shared library (#1442)
* Build Android TFLite JNI shared library
This will change cmake to drop Android JNI including Tensorflow Lite
- current drop will work same as vanilla TFLite library
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* apply comments
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 31 May 2018 01:24:25 +0000 (10:24 +0900)]
Fix linking error on arm compute library (#1456)
Recently introduced `ARMCompute` removed link to dl and pthread.
So it produces linking error like following:
```
arm-linux-gnueabihf/bin/ld:
warning: libdl.so.2, needed by
/home/brian/z/nnfw/Product/armv7l-linux.debug/out/lib/libarm_compute.so,
not found (try using -rpath or -rpath-link)
/home/brian/z/nnfw/Product/armv7l-linux.debug/out/lib/libarm_compute_core.so:
undefined reference to `dlopen@GLIBC_2.4'
/home/brian/z/nnfw/Product/armv7l-linux.debug/out/lib/libarm_compute_core.so:
undefined reference to `dlsym@GLIBC_2.4'
/home/brian/z/nnfw/Product/armv7l-linux.debug/out/lib/libarm_compute_core.so:
undefined reference to `dlerror@GLIBC_2.4'
collect2: error: ld returned 1 exit status
```
By specifying dl and pthread as dependency of arm_compute_xxx, the
linking error could be fixed.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
서상민/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 01:21:49 +0000 (10:21 +0900)]
Update ACL submodule hash (#1454)
This patch updates the submodule hash for ACL to the latest one.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 01:05:56 +0000 (10:05 +0900)]
Use submodule on tizen cross build (#1437)
* Use submodule on tizen cross build
1. Let OBS_BUILD have ON/OFF
2. Use submodule on tizen cross build
In summary, tizen cross build works in the same way of arm cross build.
* Change submodule during tizen cross build
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 31 May 2018 00:59:02 +0000 (09:59 +0900)]
Enable test_driver to catch failed test (#1409)
* Enable test_driver to catch failed test
Enable tools/test_driver/test_driver.sh to catch failed test, so that
now do not pass any failed test cases. To do this, run_benchmark*.sh and
run_unittest.sh will stop when the tests catch fail.
run_frameworktest.sh will stop after the tests run all models.
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 00:56:31 +0000 (09:56 +0900)]
[Pure CL] Support Tensor Sinks (#1440)
This commit revises pure CL runtime to support generic tensor outputs.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
서상민/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 00:47:06 +0000 (09:47 +0900)]
Make iterate() static inline (#1451)
This patch makes iterate() static inline function in order to avoid
multiple definition issue that could be caused when IndexIterator.h is
included in multiple files.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
서상민/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 23:57:33 +0000 (08:57 +0900)]
Add hasData() to class Object (#1450)
Object::hasData() will be used to check if Object has data internally.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
서상민/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 23:57:16 +0000 (08:57 +0900)]
Add a DIV unit test (#1448)
This patch adds a DIV unit test where two tensors with the same same are
passed as inputs.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 23:41:31 +0000 (08:41 +0900)]
Introduce 'tf_test' tool (#1421)
This commit introduce experimental 'tf_test' tool. This tool loads
tensorflow lite model and corresponding tensorflow model, run
inferences, and compare the result.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 23:41:01 +0000 (08:41 +0900)]
TensorFlowMax nnapi_delegate (#1432)
Add nnapi call from nnapi_delegate.cpp for TensorFlowMax
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 22:24:51 +0000 (07:24 +0900)]
TFLite interpreter: Custom operator max (#1419)
General implementation for custom operator max
Similar with mean
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 22:23:38 +0000 (07:23 +0900)]
Operator selector: cast operator bug fix (#1428)
Fix bug about generating cast operator's option
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 30 May 2018 22:23:15 +0000 (07:23 +0900)]
[newrt] Apply fix to newrt (#1444)
Apply fixed that were applied to pure_arm_compute
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 30 May 2018 11:06:45 +0000 (20:06 +0900)]
[Topk_v2 Op] support other operation types (#1314)
* [Topk_v2 Op] add uint8 types
This commit adds other types.
-uint8
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* [Topk_v2 Op] add int32 operation types
This commit adds other types.
-int32
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* [Topk_v2 Op] add an comment that explains topk_v2 operation
This commit adds comments.
- TopK_v2 of NN Runtime supports TENSOR_FLOAT32, TENSOR_QUANT8_ASYMM, TENSOR_INT32 other than TFLite.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* [Top[Topk_v2 Op] add 2D test cases for other types
This commit adds 2D test cases for other types (int32, uint8)
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 10:53:59 +0000 (19:53 +0900)]
[Pure CL] Inheric nnfw::utils::tensor::Shape (#1438)
This commit revises internal::tflite::operand::Shape to inherit
nnfw::utils::tensor::Shape (to reduce code duplication).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 08:49:00 +0000 (17:49 +0900)]
[Pure CL runtime] Support reshape/softmax over tensors (#1436)
This commit removes asserts in reshape/softmax compilation
implementation to support ADAS model.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 08:04:43 +0000 (17:04 +0900)]
Introduce 'tensor::Diff' class (#1422)
This commit extracts general 'tensor::Diff' clss from
'TfLiteTensorDiff'.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 07:53:27 +0000 (16:53 +0900)]
Fix format for pure acl runtime (#1435)
Fix format for pure acl runtime
Enable format check for pure acl runtime
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 07:47:00 +0000 (16:47 +0900)]
Ignore compiler warnings from ARMCompute (#1434)
This commit adds -Wno-ignored-attributes option when building pure CL
runtime to ignore compiler warnings due to the code in ARMCompute
library (CL.h).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 07:31:16 +0000 (16:31 +0900)]
Fix build break on debug build (#1427)
Fix debug build break for pure acl runtime
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 06:21:44 +0000 (15:21 +0900)]
Update TensorFlow submodule for topk_v2 (#1420)
This patch updates the submodule hash for tensorflow to handle topk_v2
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 05:36:53 +0000 (14:36 +0900)]
[Pure CL runtime] Fix CMakeLists.txt indentation (#1424)
This commit fixes CMakeLists.txt indentation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 02:25:51 +0000 (11:25 +0900)]
Add 'TFLITE_ENSURE' macro (#1418)
This commit introduces 'TFLITE_ENSURE' macro, and use it for tflite_run
and tflite_benchmark.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 02:23:54 +0000 (11:23 +0900)]
[Pure CL Runtime] Use SimpleArithmeticAdditionLayer (#1414)
This commit introduces SimpleArithmeticAddationLayer, and uses it by
default kernel on pure CL runtime.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 02:20:56 +0000 (11:20 +0900)]
Introduce 'ARMCompute' package (#1400)
This commit introduces 'ARMCompute' package which provides uniform
interface over imported/built ARMCompute libraries.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 30 May 2018 02:12:32 +0000 (11:12 +0900)]
Update xu4 documentations to more detail about minicom (#1334)
* Update xu4 documentations for using keyboard control
This commit updates xu4 documentations to more detail for using keyboard control
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
* Change comments
* Change comments to more cleary
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 30 May 2018 01:32:10 +0000 (10:32 +0900)]
Enable Android build of tflite_benchmark, disable tflite_run (#1413)
Enable/Disable build for Android
- Enable build of tflite_benchmark
- Disable tflite_run since it has boost library build issue
(Related to standard library - gnustl/libc++)
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 01:30:28 +0000 (10:30 +0900)]
Support Strided Slice Ex on nnapi_delegate.cc (#1399)
* Support Strided Slice Ex on nnapi_delegate.cc
Add Strided Slice Ex conversion to nnapi_delegate.cc
Note that stride_slide on nn runtime does not support 2 parameters : ellipsis_mask
and new_axis_mask.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* add CHECK_NN, remove break
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 29 May 2018 22:33:08 +0000 (07:33 +0900)]
Remove CXX_STANDARD workaround (#1405)
* Remove CXX_STANDARD workaround
CXX_STANDARD is no longer necessary as the minimum required version of
CMake is 3.1 (which supports CXX_STANDARD feature).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Apply the same change to 'libs/kernel/acl/CMakeLists.txt'
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 29 May 2018 11:09:00 +0000 (20:09 +0900)]
[Pure CL runtime] Add symbolcheck test (#1397)
This commit introduces 'pure_arm_compute_symbolcheck' executable which
allows us to detect undefined references in pure CL runtimes during
build.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 29 May 2018 05:51:07 +0000 (14:51 +0900)]
Revert "Update validation in runtime (#1351)" (#1406)
This reverts commit
86bbecea1fce90cac87a40782900eb24ff09db95.
PR #1351 caused many test failures, which were not noticed by our CI.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 29 May 2018 02:01:53 +0000 (11:01 +0900)]
Update validation in runtime (#1351)
This commit updates validation in runtime.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 29 May 2018 01:25:00 +0000 (10:25 +0900)]
Install arm_compute_XXX and libnueralnetworks.so on pure_arm_compute … (#1393)
* Install arm_compute_XXX and libnueralnetworks.so on pure_arm_compute build
1. On pure_arm_compute runtime build, install arm_compute_XXX.so into lib
2. DO NOT build NN Runtime if BUILD_ACL=ON
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* Add option BUILD_PURE_ARM_COMPUTE and change install dir
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* Remove `BUILD_NN_RUNTIME` option off
Since pure_acl_compute runtime is installed to lib/pureacl, we do not need turn
off option BUILD_NN_RUNTIME.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* Apply suggestion
In summary,
1. install arm_compute_xxx to lib
2. install libnn.so to lib/pureacl
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 29 May 2018 01:22:40 +0000 (10:22 +0900)]
Convert TF Lite's DIV to NN API's (#1398)
For #1199 and #1366
This commit links TF Lite's DIV operation to NN API's. It also enables
the Div test in the framework test.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 29 May 2018 00:47:33 +0000 (09:47 +0900)]
[pure_arm_compute] Fix no return value (Context &) (#1396)
`Context::set()` is non-void but did not return a value.
Make it to return `*this`.
Similar to #1382
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 29 May 2018 00:47:11 +0000 (09:47 +0900)]
Enable SUB NNAPI delegation and SUB broadcast test (#1394)
Tensorflow is updated to v.1.8 so we can run SUB broadcast.
I pave the way to NN runtime for Sub, (It's same to ADD.)
and enabled the corresponding test.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 11:13:50 +0000 (20:13 +0900)]
Introduce 'Tensorflow' package (#1387)
This commit introduces 'Tensorflow' package which allows users to use
externally built libtensorflow-core.a as if CMake targets.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 28 May 2018 10:43:11 +0000 (19:43 +0900)]
Make Tensorflow Lite calls MUL CPU fallback (#1360)
1. Modified `NNAPIDelegate` to build graph with `MUL`
2. Test with ADAS 'MUL' graph by nnapi_test
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 08:32:50 +0000 (17:32 +0900)]
Update TensorFlow submodule to v1.8 (#1388)
For #1383
This patch updates the submodule hash for TensorFlow to v1.8 branch in
RS7-STAR/Tensorflow.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 07:27:21 +0000 (16:27 +0900)]
Include model.h in nnapi_delegate.cpp (#1386)
For #1383
Although TF Lite's `nnapi_delegate.cc` includes
`tensorflow/contrib/lite/model.h`, our nnapi_delegate.cpp did not
include `model.h` because we were able to compile `nnapi_delegate.cpp`
without the header file. However, it is not the case with the latest
TensorFlow v1.8, which we will be using soon. This patch is to prevent
the build failure that could be caused by not including `model.h` when
building with TensorFlow v1.8.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 07:19:56 +0000 (16:19 +0900)]
Introduce nnfw's BuiltinOpResolver (#1384)
For issue #1383
This patch introduces our own BuiltinOpResolver, which is basically
copied from externals/tensorflow, in order to manage which builtin
operators in TF Lite are used with nnfw.
To only use nnfw's BuiltinOpResolver, this patch also excludes
register.cc in externals/tensorflow from the TF Lite build.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 28 May 2018 07:09:16 +0000 (16:09 +0900)]
[pure_arm_compute] Fix no return value (#1382)
`Sequence::emplace_back()` is non-void but did not return a variable.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 06:31:22 +0000 (15:31 +0900)]
[Pure CL runtime] Fix undefined references (#1380)
This commit fixes undefined reference issues on pure CL runtime.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 05:35:42 +0000 (14:35 +0900)]
Include cstring for memcpy (#1378)
This patch adds `#include <cstring>` to tensor_dumper.cc, since `memcpy`
is used in the file.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 05:35:23 +0000 (14:35 +0900)]
Add Extended NNAPI shim header (#1365)
* Add Extended NNAPI shim header
Add Extended NNAPI shim header. This header includes
ANEURALNETWORKS_STRIDED_SLICE_EX = 50005
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 04:33:05 +0000 (13:33 +0900)]
Include cassert in Diff.cpp (#1377)
This patch adds `#include <cassert>` to Diff.cpp, since `assert()` is
used in the file.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 04:32:49 +0000 (13:32 +0900)]
Introduce 'nnfw_find_package' (#1372)
This commit introduces 'nnfw_find_package' macro which allows users to
write and use nnfw-internal CMake modules (similarly as modules provided
via find_package).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 04:11:38 +0000 (13:11 +0900)]
Use nnfw-internal NNAPIDelegate (#1370)
This commit revises NNAPISession to use nnfw-internal NNAPIDelegate.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 04:10:33 +0000 (13:10 +0900)]
Add tensorflow-based 'detection' example (#1368)
This commit adds 'detection' sample app which loads T/F model (which
takes 1x320x320x3 input whose name is 'input_node') and measures elapsed
time for 5 runs.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 04:07:48 +0000 (13:07 +0900)]
Use common benchmark framework (#1371)
Thsi commit revises tflite_run and tflite_benchmark to use common
benchmark framework.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 04:06:45 +0000 (13:06 +0900)]
Do NOT install libtensorflow-lite.a (#1375)
libtensrflow-lite.a is used only during nnfw build.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 02:39:55 +0000 (11:39 +0900)]
[Pure CL runtime] Support general reshape (#1353)
* [Pure CL runtime] Support general reshape
This commit removes height/width restriction on reshape operation in
pure CL runtime.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 02:28:51 +0000 (11:28 +0900)]
Move to CMake 3.1 (#1369)
This commit requires CMake 3.1 as minimum required CMake version for
nnfw.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 28 May 2018 01:35:57 +0000 (10:35 +0900)]
Operator selector: support topk_v2 and gather (#1361)
Support topk_v2 and gather operator
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 10:17:49 +0000 (19:17 +0900)]
Show every tensor diffs (#1356)
* Show every tensor diffs
This commit revises TfLiteInterpMatchApp to show all the tensor matching
results even when there are unmatched tensors.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 09:18:08 +0000 (18:18 +0900)]
Add topk_v2 and gather framework test (#1362)
Add topk_v2 and gather framework test
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 08:55:32 +0000 (17:55 +0900)]
make extern C for extended NNAPI (#1336)
* make extern C for extended NNAPI
Add __BEGIN_DECLS for extended NNAPI
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 08:54:55 +0000 (17:54 +0900)]
Allow build contrib projects when BUILD_LABS is on (#1352)
This commit revises contrib/CMakeLists.txt to allow users to build
contrib porjects other than bindacl, convacl, and kerneltesting even
when BUILD_LABS is on.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 08:53:15 +0000 (17:53 +0900)]
Introduce 'tflite::Session' interface (#1350)
* Introduce 'tflite::Session' interface
This commit introduces 'nnfw::support::tflite::Session' which abstracts
how we run inference (either via pure T/F Lite interpreter, or via NN
runtime).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 25 May 2018 08:50:30 +0000 (17:50 +0900)]
elementwise 'MUL' NEON kernel (#1337)
In this commit,
1. elementwise 'MUL' NEON kernel is added
2. refactored elementwise 'MUL' *CL* kernel
3. tests for both NEON and CL kernel were added
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 25 May 2018 07:27:27 +0000 (16:27 +0900)]
Add CPU fallback for DIV and SUB (#1349)
DIV and SUB implementation is copied from tensoflow lite.
Since old version tensorflow lite does not support DIV and SUB broadcasting,
I brought those implementation from recent one(`7ad3964`)
Related issue: #1229
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 04:10:53 +0000 (13:10 +0900)]
Use NNAPIDelegate implemented in nnfw (#1348)
* Use NNAPIDelegate implemented in nnfw
This commit introduces nnfw::NNAPIDelegate derived from tflite::NNAPIDelegate,
and revises NN API tests to use derived NNAPIDelegate to invoke NNAPI.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Add NeuralNetworksShim.h
* Update license notice
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 25 May 2018 01:56:34 +0000 (10:56 +0900)]
Enable `toString()` to print struct, class and enum in `V1_0/types.h` (#1341)
This commit enables `toString()` to print struct, class and enum in `V1_0/types.h`.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 00:30:10 +0000 (09:30 +0900)]
Fix android build bug (#1340)
Fix android build bug in CMakefile.txt
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 25 May 2018 00:29:52 +0000 (09:29 +0900)]
[ADD] make nnapi call [cl | neon]/addFloat32 (#1339)
Make nnapi call `addFloat32` `cl/neon` kernel
by adding code to check `NNFW_KERNEL_addFloat32` environment variable.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 00:26:30 +0000 (09:26 +0900)]
Operator selector: use operator range (#1327)
Can use operators' range instead of write each operator's index
ex. 1 2 3 4 5 10 => 1-5 10
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 25 May 2018 00:25:55 +0000 (09:25 +0900)]
Add explanation for building tizen package using docker (#1331)
- How to pull docker image for tizen gbs build
- How to build tizen package using docker
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 May 2018 23:49:13 +0000 (08:49 +0900)]
Add NN tests skip list for armv7l-tizen (#1335)
Skip list for armv7l-tizen is same to one for armv7l-linux.
Related Issue: #1272
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 11:36:43 +0000 (20:36 +0900)]
AddOperationEx supports extended DIV, SUB, STRIDED_SLICE (#1333)
1. add DIV, SUB enum to OperationType
- cf) There is no implementaion for DIV and SUB
2. add function mapping extended op to OperationType
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 07:59:28 +0000 (16:59 +0900)]
Add STRIDED_SLICE_EX test to generated test (#1332)
1. add python generator for strided slice ex
2. add generated cpp
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 May 2018 07:55:37 +0000 (16:55 +0900)]
[CL/NEON Kernel] add ADD operation to add two matrixes (#1305)
- adds code for two matrix addition
- 2D, 3D, 4D addition
- future work: broadcasting support and 5D
(parent issue: #1288)
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 24 May 2018 07:54:54 +0000 (16:54 +0900)]
Introduce new runtime based on pure_acl_runtime (#1325)
Related : #1306
This commit introduces new runtime based on pure_acl_runtime.
When the implementation of this runtime is done, we can replace the current `nn` runtime.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 24 May 2018 07:51:52 +0000 (16:51 +0900)]
Add the CAST_EX operation performed as CPU fall-back (#1300)
This commit adds the CAST_EX operation performed as CPU fall-back
- The cast_EX operation is implemented by referring to the tflite's code.
- The test code for this OP is changed to a test without activation.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 06:16:13 +0000 (15:16 +0900)]
[NNAPI unittest] Add 'resize_bilinear_1' (#1321)
* [NNAPI unittest] Add 'resize_bilinear_1'
This commit adds 'resize_bilinear_1' unittest which allows us to
experiments with various resize configurations.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 06:15:07 +0000 (15:15 +0900)]
[NNAPI unittest] Add 'add_1' (#1317)
* Introduce 'add_1' NNAPI unittest
This commit introduces 'add_1' NN API unittest, which allows folks to
experiments with various 4D tensor configuration.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 06:13:45 +0000 (15:13 +0900)]
Git ignore format.path (#1330)
Ignore format.path file generated by format checker
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이성재/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 May 2018 06:13:13 +0000 (15:13 +0900)]
Add option to control parallel build (#1328)
- add shell variable PARALLEL_BUILD with default value 1
- `PARALLEL_BUILD=0 make xxx` disables parallel build
Signed-off-by: Sung-Jae Lee <sj925.lee@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 06:12:43 +0000 (15:12 +0900)]
[Pure CL Runtime] Support 'RESIZE_BILINEAR' operation (#1326)
This commit implements 'RESIZE_BILINEAR' operation support in pure CL
runtime.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 06:11:12 +0000 (15:11 +0900)]
Operator selector: slim operator table (#1309)
Modify operator table from source model file
Generated model file's operator table has only used operators
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
최형규/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 04:49:35 +0000 (13:49 +0900)]
Enable framework test for RESIZE_BILINEAR (#1324)
- Enable framework test for RESIZE_BILINEAR
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 04:42:26 +0000 (13:42 +0900)]
Add STRIDE_SLICE,DIV,SUB as extended op (#1320)
1. add DIV,SUB,STRIDED_SLICE to extended
op.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 03:55:44 +0000 (12:55 +0900)]
[Pure CL Runtime] Support 'ADD' operation (#1318)
This commit implements 'ADD' operation support in pure CL runtime.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 24 May 2018 03:47:18 +0000 (12:47 +0900)]
Add CAST_EX to the skip list (#1313)
This commit adds `CAST_EX` to the skip list.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 May 2018 02:35:47 +0000 (11:35 +0900)]
[Gather Op] add Gather-2D operation test (#1296)
This commit introduces a test for Gather-2D operation.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 24 May 2018 02:15:22 +0000 (11:15 +0900)]
Remove android dependency in TestValidation (#1316)
* Remove android dependency in TestValidation
This commit removes android dependency in TestValidation test.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
최형규/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 02:14:20 +0000 (11:14 +0900)]
Update external/tensorflow to the latest nnfw branch (#1319)
- Update external/tensorflow to the latest nnfw branch
- Added one PR
Implement RESIZE_BILINEAR using NN API
https://github.sec.samsung.net/RS7-STAR/Tensorflow/pull/37
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 May 2018 01:50:21 +0000 (10:50 +0900)]
[Gather Op] update gather operation to support Gather-2D operation (#1295)
* [Gather Op] Update outputshape's dimension to support Gather-2D
This commit updates gather operation to support Gather-2D operation in optimized_op file and
outputshape's dimension to support Gather-2D in gatherPrepare.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 May 2018 00:51:19 +0000 (09:51 +0900)]
[Topk_v2 Op] introduce topk_v2 test cases (#1304)
* [Topk_v2 Op] introduce topk_v2 test cases
This commit introduces topk_v2 test cases.
-1D float
-2D float
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* [Topk_v2 Op] add new line at the end of line
This commit adds new lines at the end of line
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 May 2018 23:52:15 +0000 (08:52 +0900)]
[ADD Op] enabled nnapi_test (#1311)
This commit enables nnapi_test for ADD operation to add 4D matrixes
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 23 May 2018 23:37:33 +0000 (08:37 +0900)]
Disable submodule update in Makefile (#1310)
Disable submodule update in Makefile
It will be useful to test submodule's PR
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 May 2018 23:34:27 +0000 (08:34 +0900)]
[Gather OP] add gather operation to nn runtime unittest (#1260)
* [Gather OP] add gather operation to nn runtime unittest
This commit adds gather operation to nn runtime unittest.
-gather 1-dimension test
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* Modify addOperation to support the new extended structure
-modify addOperation to addOpeationEx
-move gather operation file from V1.1 to Ex
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
Saurav Babu/Advanced SW Team/Engineer/삼성전자 [Wed, 23 May 2018 23:32:48 +0000 (05:02 +0530)]
TFLiteSharp: Added methods to create model and build interpreter (#1221)
* TFLiteSharp: Added methods to create model and build interpreter
This commit contains addition of 3 function definition in native code
for creating a flatbuffer model, building an interpreter instance and
setting the number of threads. The respective changes are also made in
C# code along with the addition of interop functions for shared
library(libtflite-native.so) runtime linkage. Also included are some
modification in build system, specifically adding the manifest file.
Signed-off-by: kshitiz-b <kshitiz.b@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 May 2018 07:38:50 +0000 (16:38 +0900)]
[TopK_v2] introduce topk_v2 operation (#1301)
* [TopK_v2] introduce topk_v2 operation
This commits introduces topk_v2 operation.
-currently, for float
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 23 May 2018 07:03:21 +0000 (16:03 +0900)]
Install OpenCL package for arm rootfs (#1307)
Install OpenCL package for arm rootfs
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 May 2018 04:25:26 +0000 (13:25 +0900)]
[CL kernel] element-wise mul (#1285)
This commit introduces element-wise mul for mali GPU.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 23 May 2018 04:24:28 +0000 (13:24 +0900)]
TFLiteFile tool: fix stride_slice bug (#1299)
Fix stride_slice option generation bug
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>