박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 10:03:38 +0000 (19:03 +0900)]
Fix Tizen cross-build break (#628)
This commit inserts explicit type instantiation on abs method to fix
Tizen cross-build break.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 12 Apr 2018 08:43:49 +0000 (17:43 +0900)]
Add handling options to test_driver.sh (#622)
Enables test_driver.sh to handle options properly. Now test_driver.sh
can run only for unittest, frameworktest or verification.
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 08:03:17 +0000 (17:03 +0900)]
Introduce TensorWrapper for unittesting (#619)
This commit introduces TensorWrapper for unittesting.
This class can be used various test cases in `src/kernel`.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 12 Apr 2018 07:47:07 +0000 (16:47 +0900)]
Initial version of ACL pooling with NEON (#621)
* remove unnecessary blanks
Signed-off-by: lotieye.choi <lotieye.choi@samsung.com>
* Initial version of ACL pooling with NEON
Signed-off-by: lotieye.choi <lotieye.choi@samsung.com>
* add pooing with NEON in cmake
Signed-off-by: lotieye.choi <lotieye.choi@samsung.com>
* remove blanks
Signed-off-by: lotieye.choi <lotieye.choi@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 04:55:06 +0000 (13:55 +0900)]
[Pure ACL NN Runtime] Add Source/Sink (#615)
This commit introduces the concept of Source and Sink which sets inputs
before execution, and gets outputs after execution.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
최형규/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 04:52:26 +0000 (13:52 +0900)]
Use CPU kernel as a default kernel (#614)
* Use CPU kernel as a default kernel
- Use CPU kernel as a default kernel
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
* Apply review feedback
- restrict scope of it variable
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 04:50:53 +0000 (13:50 +0900)]
[Pure ACL Runtime] Set Conv2D strides (#608)
This commit set Conv2D stride parameter with values read from operands.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 12 Apr 2018 04:48:29 +0000 (13:48 +0900)]
Add missed TestGenerated.cpp in Android NN tests (#616)
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 12 Apr 2018 04:31:53 +0000 (13:31 +0900)]
[NNOP]Introduce average pooling (#610)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 12 Apr 2018 02:50:53 +0000 (11:50 +0900)]
Clean include section of Callbacks.h (#600)
This commit cleans include section of Callbacks.h
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 12 Apr 2018 02:21:17 +0000 (11:21 +0900)]
Initial version of ACL Conv2D with NEON (#602)
This will add Conv2D with NEON backend.
- implementation will be moved to another module after common codes are moved
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 02:03:18 +0000 (11:03 +0900)]
[Pure ACL] Allow model to include MaxPool2D op (#606)
This commit revises Pure ACL NN Runtime to include MaxPool2D operation
while constructing a model.
Note that execution is not supported, yet.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 02:03:12 +0000 (11:03 +0900)]
Use correct ANeuralNetworksExecution_setOutput signature (#605)
ANeuralNetworksExecution_setOutput should take void * (not const void *)
according to NNAPI specification.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 02:03:06 +0000 (11:03 +0900)]
[NNOP] The first version of NEON FC layer (#573)
This commit introduces the first version of NEON FC Layer.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 01:17:23 +0000 (10:17 +0900)]
Introduce nnfw_support_nnapi (#603)
This commit introduces 'nnfw_support_nnapi' library which provides
various helpers for implementing NNAPI.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 00:44:49 +0000 (09:44 +0900)]
Extract CLUniqueTensor to another file (#578)
This commit extracts CLUniqueTensor to another file
in order to use this class in other OpenCL NN Layers.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 00:14:05 +0000 (09:14 +0900)]
[Pure ACL NN Runtime] Implement basic compilation (#596)
This commit implements basic compilation phase for (experiemntal) pure
ACL NN runtime.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 00:07:50 +0000 (09:07 +0900)]
FIX: build fail due to fromNNShape() (#599)
Build fail due to fromNNShape() is moved to namespace nnfw::kernel::acl::util.
This commit fixes this fail by chainging `fromNNShape()` to
`util::fromNNShape()`.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 12 Apr 2018 00:07:23 +0000 (09:07 +0900)]
Implement naive feature map and kernel update (#585)
* Implement naive feature map and kernel update
This commit implement unoptimize, naitve offset calulation (which is
easy to debug).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Remove unused variables
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Apr 2018 23:48:11 +0000 (08:48 +0900)]
[NNOP] First version of MaxPoolingFloat32 (#563)
* add softmax unittest
* fix typoes (IFM_H -> IFM_C)
* modify dims (batch_size and input_size)
* Fix softmax unnittest according to comments
-remove empty lines
-add empty lines to the end of codes
-resolve the conflict related with #472.
-modify equality between two floats by using nfw::util::fp32::epsilon_equal
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* add header files for softmax unittest
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* add new line
add new line at the end of file
* [NNOP] First version of MaxPoolingFloat32
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* initialize data with increasing value
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* Move maxpool kernel to cl folder
* add maxpool acl kernel operator prototypes
* add new line
* change maxpool names as #574
* change names to align function prototype with NN runtime.
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 12:43:32 +0000 (21:43 +0900)]
Fix tizen cross/obs build fail (#595)
1. For obs build, save downloaded_deps.tar.gz to nnfw/packaging
2. To distinguish obs build, introduce OBS_BUILD flag
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 10:20:59 +0000 (19:20 +0900)]
New inception models test and change default (#579)
- New inception models: inception module (small inception), inception slim
- Test small inception as default, and disable slim and nonslim
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 10:20:30 +0000 (19:20 +0900)]
exit when unittet fail (#587)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 11 Apr 2018 09:22:32 +0000 (18:22 +0900)]
Uncomment remaining comment of LOG in ModelBuilder (#564)
This commit uncomments remaining comment of LOG in ModelBuilder.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Apr 2018 08:42:06 +0000 (17:42 +0900)]
Enable building Android NN tests (#580)
Building Android NN tests are on by default.
In case of g++ < 6.3, it is disabled to avoid build failure in
TestGenerated.cpp.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 08:41:24 +0000 (17:41 +0900)]
Bug fix in run_test.sh (#586)
Bug fix: parsing error by '/' when test have sub-directory
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Apr 2018 07:50:59 +0000 (16:50 +0900)]
Rename acl Conv2D filename (#574)
* Rename acl Conv2D filename
This will remove _acl suffix from filename as it's inside cl folder
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove shape.cpp
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 11 Apr 2018 07:47:38 +0000 (16:47 +0900)]
Remove temporary include of ErrorStatus in ExecutionBuilder (#560)
This commit removes temporary include of ErrorStatus in ExecutionBuilder and enables that include in HallInterfaces.h
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 11 Apr 2018 07:46:46 +0000 (16:46 +0900)]
Remove unused PreparedModelCallback (#555)
This commit removes unused PreparedModelCallback.
The PreparedModelCallback class is used to receive the error status of preparing a model as well as the prepared model from a task executing asynchronously with respect to the runtime.
But in the environment of running on CPU only, it is no needed.
If it is needed later, can be copied from AndroidNN or implemented on our own.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 11 Apr 2018 07:45:58 +0000 (16:45 +0900)]
Remove partitioning(device) functions in ExecutionBuilder (#550)
This commit removes partitioning(device) functions in ExecutionBuilder.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 07:45:28 +0000 (16:45 +0900)]
Initialize CLScheduler inside NN runtime (#548)
* Initialize CLScheduler inside NN runtime
ARM Compute Library requires CLScheduler to be initialized before any CL
operations.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Use 'nnfw::kernel::acl::Initialize'
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 07:37:18 +0000 (16:37 +0900)]
[NNOP] Remove unnecessary blank line (#576)
This commit removes an unnecessary blank line in
`src/kernel/acl/src/cl/FullyConnected.test.cpp`.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 07:31:32 +0000 (16:31 +0900)]
[NNAPI Unittest Conv1] Initialize inputs correctly (#575)
This commit fixes a bug in 'nnapi_unittest_conv_1' which incorrectly
initializes inputs.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 07:19:59 +0000 (16:19 +0900)]
Apply RELU to the FC layer. (#572)
This commit adds functionality of activation RELU into the FC layer.
This commit also adds a test case for RELU.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 07:18:10 +0000 (16:18 +0900)]
[NNOP] Introduce module shape (#570)
This commit introduces a module shape. This module includes
getSizeOfDimension(), fromVectorNNShape(), and fromNNShape().
These functions are commonly used in various layer implementations.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 06:26:06 +0000 (15:26 +0900)]
Support ReLU activation (#571)
This commit revises Conv2D operation kernel to support ReLU activation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Apr 2018 06:07:13 +0000 (15:07 +0900)]
Gather acl kernel operator prototypes (#569)
* Gather acl kernel operator prototypes
This will gather acl kernel operator prototypes to root include folder
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add reshape
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Apr 2018 05:44:34 +0000 (14:44 +0900)]
Update convolution manual calculation xls (#562)
This will update xls file with 3x5 input with 2 kernels
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 05:36:37 +0000 (14:36 +0900)]
[NNOP] The first version of reshape layer (#566)
This commit introduces the first version of reshape layer using ACL.
Unit test will be added more in later commits.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 05:32:51 +0000 (14:32 +0900)]
Remove ext libs used to build TF Lite (#541)
For issue #491
This patch is to remove external libs that were used to build TF Lite and to use a script that brings
those libraries from the tensorflow directory.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Apr 2018 05:00:51 +0000 (14:00 +0900)]
Move conv kernel to cl folder (#561)
This will move Conv kernel source into cl folder for cl implementations
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 04:38:26 +0000 (13:38 +0900)]
tflite_run: initialize _elapsed in ElapsedTime (#559)
Fixes issue #540
This patch initializes _elapsed in ElapsedTime as 0.0 to set a correct
time value.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Apr 2018 04:22:59 +0000 (13:22 +0900)]
Add 3x5 2 kernel convolution test (#552)
* Add 3x5 2 kernel convolution test
This will add 3x5 with 2 kernel convolution test and fix format conversions
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* apply review comments
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 04:03:03 +0000 (13:03 +0900)]
Introduce interactive docker option (#545)
To build and test continuously in the docker environment, run as below:
`$ DOCKER_INTERACTIVE=1 ./docker/Docker_build_cross_arm_ubuntu_without_aclbuild.sh`
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 03:57:38 +0000 (12:57 +0900)]
[Pure ACL] Fix build break (#556)
This commit removes inputs/outputs field from Plan class (as it now has
a reference to Model class which has inputs/outputs) to fix build break.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Apr 2018 03:57:16 +0000 (12:57 +0900)]
Fix convolution kernel test failure (#557)
This will fix convolution kernel on acl test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 01:55:51 +0000 (10:55 +0900)]
[NNOP] The first version of fullyConnectedFloat32 (#547)
This commit introduces the first version of fullyConnectedFloat32
to integrate ACL with NN runtime.
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 11 Apr 2018 01:51:24 +0000 (10:51 +0900)]
Remove functions used in only ExecutionPlan in ExecutionBuilder (#546)
This commit removes functions used in only ExecutionPlan in ExecutionBuilder
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 01:47:21 +0000 (10:47 +0900)]
Introduce CLUniqueTensor (#551)
This commit introduces CLUniqueTensor which initialize and allocate
buffer in its constructor, and free that buffer in its destructor.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 01:31:23 +0000 (10:31 +0900)]
[Pure ACL] Pass NNAPI model to execution (#544)
The following functions need to access model information through
ANeuralNetworksExecution object:
- ANeuralNetworksExecution_setInput
- ANeuralNetworksExecution_setOutput
This commit renames class Model in internal::arm_compute namespace as
Plan, revises it to include a reference to NNAPI model.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 00:56:28 +0000 (09:56 +0900)]
Set arm_compute::TensorShape for bias correctly (#549)
This commit revises convFloat32 implementation based on ARM Compute to
correctly set bias shape. This change fixes clBuffer exception during
bias memory allocation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 00:30:40 +0000 (09:30 +0900)]
Remove comment from test_driver.sh (#542)
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 11 Apr 2018 00:13:42 +0000 (09:13 +0900)]
Invoke NNFW ACL kernels via runtime (#535)
* Invoke NNFW ACL kernels via runtime
This commit allows users to invoke NNFW ACL Conv2D kernel via runtime.
It also adds link directory for ARM Compute Library.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
TANUJ TEKRIWAL/SRI-Bangalore-System SW/./삼성전자 [Tue, 10 Apr 2018 23:40:25 +0000 (05:10 +0530)]
Enable RESHAPE of CpuExecutor. (#496)
Add the RESHAPE operation file and enable the
operation in CpuExecutor.
Signed-off-by: Tanuj Tekriwal <tanuj.tekri@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 10 Apr 2018 23:39:34 +0000 (08:39 +0900)]
Bring Android NN Runtime Generated Tests (#463)
C++ Tests generated from python specs are added.
Its build is default off since it requires g++ >= 7.
You can enable it by defining BUILD_ANDROID_NN_RUNTIME_TEST=ON.
Simple tests (float_xxx and add) pass.
For others (conv_quants_xxx, depthwise_xxx, etc), we have to enable
the code from android NN (currently enclosed with comment).
I included generated C++ not python spec file and generator script.
Because i) It tooks about 12 sec in my machine to generate.
ii) I belive the tests seldom change.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 23:36:03 +0000 (08:36 +0900)]
[Pure ACL] Store Network Inputs/Ouputs (#543)
This commit revises tflite::Model and arm_comput::Model to store the
inputs and outputs of a given network.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 22:29:29 +0000 (07:29 +0900)]
Extract general functions from Conv2D_acl.test.cpp (#539)
- TestEnvironment -> gtest_env.cpp
- initData() and compareData() -> util.cpp
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
서상민/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 09:12:59 +0000 (18:12 +0900)]
Update the TensorFlow submodule to the latest commit (#537)
This patch updates the TensorFlow submodule to the latest commit in the
nnfw branch.
Signed-off-by: Sangmin Seo <sangmin7.seo@samsung.com>
최형규/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 09:12:51 +0000 (18:12 +0900)]
Fix broken links to tensorflow (#538)
- Fix broken links to tensorflow
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 08:46:22 +0000 (17:46 +0900)]
Fix obs build fail on libkernelacl (#531)
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 08:41:57 +0000 (17:41 +0900)]
Return correctly on NNAPI test failure (#536)
This commit revises TfLiteInterpMatchApp to return boolean instead of
integer.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 08:41:25 +0000 (17:41 +0900)]
[Pure ACL NNRT] Introduce Conv2D Param Constructor (#528)
This commit introduces a constructor for implicit Conv2D Param class
which initializes parameters using arrays.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 08:41:16 +0000 (17:41 +0900)]
Use N/H/W/C ordering for fromNNShape (#530)
NNAPI assumes that N/H/W/C binding for 3D feature map tensor.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 08:31:52 +0000 (17:31 +0900)]
generate xml test result for unittest (#527)
test results with xml format are generated on report dir.
This files will be used on junit of CI.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Apr 2018 08:29:42 +0000 (17:29 +0900)]
Clean includes in NeuralNetworks.cpp (#533)
This commit cleans includes in NeuralNetworks.cpp (except NeuralNetworksOEM.h)
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Apr 2018 08:29:05 +0000 (17:29 +0900)]
Remove unused includes and codes in CompilationBuilder (#529)
This commit removes unused includes and codes in CompilationBuilder.
- Remove partition codes
- enable VLOG in constructor
- Remove ExecutionPlan codes
- Remove unused includes
Related : #503
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Apr 2018 08:27:47 +0000 (17:27 +0900)]
Remove unused functions and includes in ModelBuilder (#512)
This commit removes unused functions and includes in ModelBuilder.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 08:10:12 +0000 (17:10 +0900)]
Introduce nnfw::util::tensor::Object (#505)
This commit introduces nnfw::util::tensor::Object, which makes it easy
to generate a random tensor object for testing.
This commit also simplifies nnapi_test and nnapi_unintest_conv_1
implementations using this new helper class.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 07:38:48 +0000 (16:38 +0900)]
[Pure ACL NN Runtime] Add Execution Placeholder (#526)
This commit partially implements functions related with ANeuralNetworksExecution
struct.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
최형규/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 07:17:24 +0000 (16:17 +0900)]
Introduce nnfw_kernels (#517)
- Introduce nnfw_kernels to choose kernel for various target at runtime
- Apply nnfw_kernels to convFloat32 used at OperationType::CONV_2D
- Introduce environment variable NNFW_KERNEL_convFloat32 to select target of convFloat32
- Tested with convolution_test2.tflite
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 10 Apr 2018 06:54:51 +0000 (15:54 +0900)]
[NNAPI Unittest] Add softmax (#471)
This commit adds softmax NNAPI unittest. It is related with #374.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 10 Apr 2018 06:49:30 +0000 (15:49 +0900)]
Implement convolution kernel with ACL (#521)
This will implement convolution kernel with ACL in the simplest way.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 10 Apr 2018 06:47:50 +0000 (15:47 +0900)]
Early version of freezer ( Tensorflow model (code level) to frozen model ) (#419)
This commit introduces a tool to convert Tensorflow model (in code level) to frozen model file.
This could be used in future to generate many frozen model files for test cases.
The following samples to generate frozen model are included.
- relu(wx+b)
- softmax(wx+b)
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 03:28:12 +0000 (12:28 +0900)]
Enable tizen cross/obs build (#482)
1. setup tizen cross/obs build
2. add tizen cross build script
Build assumes that libarmcl-devel, gtest-devel and tensorflow-lite are installed
on tizen's rootfs. Since libarmcl and tensorflow-lite is not present
on public tizen repo, please use private local repo like
`http://10.113.61.134/repo/` for obs build. For cross build, rootfs is
uploaded on `http://npuarchive.mooo.com/archive/nnfw/rootfs/rootfs_arm_tizen.tar.gz`.
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 02:43:38 +0000 (11:43 +0900)]
[NNAPI Unittest] Use random kernel/bias for conv_1 (#524)
* [NNAPI Unittest] Use random kernel/bias for conv_1
This commit revises 'nnapi_unittest_conv_1' to use random kernel and
bias values for testing.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 02:12:03 +0000 (11:12 +0900)]
[Pure ACL NN Runtime] Implement Compilation (#522)
This commit partially implements ANeuralNetworksCompilation_create with
partially defined ANeuralNetworksCompilation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 01:52:11 +0000 (10:52 +0900)]
Use common test driver for NN API tests (#514)
This commit extracts test driver implemented in 'nnapi_test' as utility,
and uses it to revises 'nnapi_unittest_conv_1'.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 10 Apr 2018 01:49:57 +0000 (10:49 +0900)]
[Pure ACL NN Runtime] Support casting operations over Shape (#519)
This commit introduces various casting operations over operand::Shape
class in pure ACL NN runtime.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
최형규/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 23:26:58 +0000 (08:26 +0900)]
Resolve TODO-NNRT (#518)
- Resolve TODO-NNRT
- Remove including <limit> header file
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
오형석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 14:13:53 +0000 (23:13 +0900)]
Handle reshape and depthwise convolution in operator selector (#476)
Operator selector (select_operator.py) can handle new two operators
- Reshape
- Depthwise convolution
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Apr 2018 13:21:39 +0000 (22:21 +0900)]
Clean declaration section in ModelBuilder.h (#511)
This commit cleans declaration section in ModelBuilder.h
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Apr 2018 13:20:46 +0000 (22:20 +0900)]
Revert remaining commented LOG codes to original (#506)
This commit reverts remaining commented LOG codes to original.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Apr 2018 10:20:03 +0000 (19:20 +0900)]
Enable static_assert in NeuralNetwors.cpp (#508)
This commit enables static_assert in NeuralNetwors.cpp
The assertions of 'OEM Operations' are commented out in current scope now.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Apr 2018 10:19:19 +0000 (19:19 +0900)]
Clean up cmake files in directory depends (#507)
This commit clean up cmake files in directory depends.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 07:53:15 +0000 (16:53 +0900)]
typo fix: NNFw_OWNER_GID -> NNFW_ (#513)
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Apr 2018 07:36:25 +0000 (16:36 +0900)]
fix a typo in nnapi_test (#510)
This commit fixes a typo in nnapi_test.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 07:19:53 +0000 (16:19 +0900)]
[Pure ACL NN Runtime] Partailly implement addOperation (#501)
This commit implements ANeuralNetworksModel_addOperation partially for
Conv2D operation with implicit paddings.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 07:19:14 +0000 (16:19 +0900)]
[NNAPI Test] Support dynamic tolerance (#509)
This commit allows 'nnapi_test' to dynamically adjust its tolerance level.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
이춘석/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 07:12:06 +0000 (16:12 +0900)]
Rename libtensorflow_lite.a to -lite.a (#504)
Makefile on tensorflow-lite repo uses -lite.a
To enable obs build, need to follow orignal naming.
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 06:52:04 +0000 (15:52 +0900)]
Extract Tensor IndexFormatter as utility (#489)
This commit extracts TensorIndexFormatter (implemented in NNAPI test) as
utility.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
최형규/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 06:50:34 +0000 (15:50 +0900)]
HowTo documentation for docker image of nnfw (#427)
* HowTo documentation for docker image of nnfw
- Add HowToUseDockerImage.md
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
* Add private registery configuration for different docker daemon
- Add private registery configuration for different docker daemon
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
* Apply review feedbacks
- Apply review feedbacks
Signed-off-by: Hyung-Kyu Choi <hk0110.choi@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 9 Apr 2018 06:49:16 +0000 (15:49 +0900)]
Introduce nnfw kernel Initialize (#502)
This will introduce initialize function for nnfw acl kernels
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 9 Apr 2018 04:10:49 +0000 (13:10 +0900)]
Labs convolution with acl runtime (#500)
This will update labs convolution test using acl runtime layer
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 02:28:58 +0000 (11:28 +0900)]
Introduce tensor::NonIncreasingStride (#499)
This commit extracts stride-related code from TensorView in nnfw::support::tflite
as NonIncreasingStride utility class (in nnfw::util::tensor).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 9 Apr 2018 02:26:43 +0000 (11:26 +0900)]
Docs tizen on xu4 (#498)
* Docs tizen on xu4
This will add how-to document about tizen on xu4 from wiki page
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 9 Apr 2018 01:36:32 +0000 (10:36 +0900)]
Introduce NNFW_GTEST_LIBS for test programs (#497)
This will introduce NNFW_GTEST_LIBS variables having gtest libraries for test programs
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 01:14:18 +0000 (10:14 +0900)]
[Pure ACL NN Runtime] Implement setOperand functions (#490)
This commit implements setOperandValue and setOperandValueFromMemory
functions for pure ACL NN Runtime.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 00:51:23 +0000 (09:51 +0900)]
Introduce an image generator (#426)
This commit introduces an image generator:
- How to execute:
`$ ./imagegen.py`
Two output images are generated: `image.bin` and `image.ppm`.
- Changing the size of the output image
Change variable `image_size` at the beginning of `imagegen.py`.
- Changing output image format
If you want to output another image format, you can use as below:
`im.save("image.jpg")`
Signed-off-by: Junghyun Kim <jh0822.kim@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 9 Apr 2018 00:30:41 +0000 (09:30 +0900)]
Introduce nnfw::util::tensor::Zipper (#495)
This commit introduces Zipper class and related helper methods.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 6 Apr 2018 07:14:26 +0000 (16:14 +0900)]
[NNAPI Test] Initialize IFM with float values (#494)
This commit revises 'nnapi_test' to initialize IFM with float values.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>