오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 6 Dec 2018 08:11:38 +0000 (17:11 +0900)]
Define GENERATE_FILES for test generation (#3890)
Introduce GENERATE_FILES environment variable to skip running generate_test.sh
If you set GENERATE_FILES 0, makefile skip running generate_test.sh. Default is 1 (run generate_test.sh default)
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 6 Dec 2018 08:09:41 +0000 (17:09 +0900)]
Move include/nnfw/std (#3892)
Move include/nnfw/std to libs/cpp14/
Update include path
Update cmake to include cpp14 library using interface
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 6 Dec 2018 08:08:54 +0000 (17:08 +0900)]
[neurun] Move Swizzle.h to acl backend dir (#3893)
Move Swizzle.h to acl backend dir since it is only used there.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
[neurun] Remove backend/cpu dependancy from PermutateSource/Sink (#3889)
Related issue: #3888
Remove backend/cpu dependancy from PermutateSource/Sink
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 6 Dec 2018 06:39:36 +0000 (15:39 +0900)]
Fix wrong radius of LRN cl kernel (#3861)
* Fix wrong radius setting of LRN cl kernel
Fix wrong radius setting for LRN
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* Remove unused variables
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 6 Dec 2018 06:07:22 +0000 (11:37 +0530)]
Change the order of Unpack Input parameter in NeuralNetworksEx.h (#3865)
This patch changes the order of Unpack Input parameter in NeuralNetworksEx.h
The num is seconds and axis is third param.
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 6 Dec 2018 06:06:56 +0000 (11:36 +0530)]
Redefine PACK_EX in NeuralNetworksEx.h (#3864)
As per @hseok82-oh's words
>I found out runtime is updated to use additional parameter num and this PR will use this change. Please update comment PACK_EX in NeuralNetworksEx.h using another PR.
This patch redefines PACK_EX in NeuralNetworksEx.h.
Signed-off-by: prasannar <prasanna.r@samsung.com>
[neurun] Do backends as shared and update BackendManager to support plugin (#3793)
Related issue: #3703
This is the initial step of converting backends to plugins
Update BackendManager to creage a map using plugins
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 6 Dec 2018 06:04:19 +0000 (11:34 +0530)]
Remove #failed comment from skiplist (#3878)
This pacth will remove #failed comment from skiplist
Signed-off-by: shubham <shub98.gupta@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 6 Dec 2018 05:13:31 +0000 (10:43 +0530)]
Introduce enum for EQUALITY op. (#3853)
This patch introduces an enum for EQUALITY operations
like EQUAL, NOT_EQUAL.
This is related to #3851.
This is reduce code redundancy to a good extent in future.
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 6 Dec 2018 04:37:23 +0000 (10:07 +0530)]
Disable nnapi_test of Custom/TensorflowMax (#3850)
This patch disables nnapi_test of Custom/TensorflowMax.
Since TensorFlowMax is builtin op as REDUCE_MAX from V1.12,
we are removing the trace of TensorFlowMax as a custom op.
This is required for PRs #3849 #3846
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 6 Dec 2018 01:49:02 +0000 (10:49 +0900)]
Remove UPDATE_MODULE in makefile (#3891)
Remove UPDATE_MODULE environment variable to ignore submodule update: deprecated feature because we don't use submodule
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 6 Dec 2018 00:57:36 +0000 (06:27 +0530)]
[tfltool] Enable select operator for Pack op (#3817)
This patch will enable select operator tflitetool for pack op
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 6 Dec 2018 00:57:23 +0000 (06:27 +0530)]
[tfltool] Enable select operator for transpose op (#3811)
This patch will enable transpose op in tflitetool in select_operator.py
Signed-off-by: shubham <shub98.gupta@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 6 Dec 2018 00:56:50 +0000 (06:26 +0530)]
Add unified CL Kernels for Binary LOGICAL OPS (AND & OR) (#3752)
This issue tracks the implementation of unified CL Kernels for Binary LOGICAL OPS (AND & OR).
Unified CL kernel can be implemented.
This patch is an implementation of unified CL Kernel for Binary LOGICAL OPS (AND & OR).
Signed-off-by: prasannar <prasanna.r@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 6 Dec 2018 00:21:33 +0000 (09:21 +0900)]
[neurun] Fix wrong ifdef guard in Sink (#3883)
This commit fixes wrong ifdef guard in `Sink`.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 6 Dec 2018 00:21:21 +0000 (09:21 +0900)]
Generate generated test cpp files on configuration (#3874)
* Rename generated dir to generated_remove
`generated` dir will be used for generated cpp files by
`generate_test.sh`. And `generated_remove` will be removed later.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Generate generated tests on demand
Generate generated tests on demand
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Dec 2018 07:29:41 +0000 (16:29 +0900)]
Fix include dir setting in cmake (#3881)
Remove libs/util/include in NNFW_INCLUDE_DIR list
Fix cmake include for libs/util
Fix cmake link for neurun cpu kernel
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Dec 2018 07:29:18 +0000 (16:29 +0900)]
Fix header files format in libs (#3879)
Fix header files format in libs except comes from public tensorflow
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 07:21:00 +0000 (12:51 +0530)]
Unify REDUCE_MIN and REDUCE_MAX kernels (#3859)
This patch unifies reduce_min and reduce_max cl kernels
Related issue: #3771
Done to reduce code redundancy.
Signed-off-by: prasannar <prasanna.r@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 07:14:35 +0000 (12:44 +0530)]
Use asPadstrideInfo utility to calc pad values in TransposeConv op (#3705)
This patch removes the internal calc of pad values during execution and uses asPadstrideInfo
utility to calc the same.
Signed-off-by: shubham <shub98.gupta@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 5 Dec 2018 07:13:44 +0000 (16:13 +0900)]
[neurun] Remove internal/nnapi (#3880)
Now that we removed the use of classes in `internal::nnapi::kernel`, we
can remove this directory.
Related PR : #3862
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Dec 2018 06:24:07 +0000 (15:24 +0900)]
Move include/support (#3876)
Move include/support to libs/support/include/support
Update cmake for include
Add .FORMATDENY to avoid format checking
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 06:08:35 +0000 (11:38 +0530)]
Remove un-necessary header files from Equal CL kernel config files (#3875)
This patch removes un-necessary header files from Equal CL kernel config files
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 06:08:02 +0000 (11:38 +0530)]
Changes in PACK GTest as per specifications in NNAPI (#3866)
This patch makes changes in PACK GTests as per specification in NNAPI.
Refer #3864 for specification.
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Dec 2018 05:47:14 +0000 (14:47 +0900)]
Move include/util (#3872)
* Move include/util
Move include/util to libs/util/include/util
Update cmake for include
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Add .FORMATDENY file
Format for header will be fixed later
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 5 Dec 2018 04:25:53 +0000 (13:25 +0900)]
[neurun] Remove usage of internal/nnapi/kernel (#3862)
Now that feature is 4D, so this commit removes kernel usage for unifying
kernel and feature. This commit includes removal of dynamic_cast to
backend implementations, which had to be done with this work.
Removing files in `internal/nnapi/kernel` will be done in another
commit.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Dec 2018 03:08:23 +0000 (12:08 +0900)]
Change operator TENSORFLOW_SUM name (#3747)
Change operator ANEURALNETWORKS_TENSORFLOW_SUM_EX name to ANEURALNETWORKS_REDUCE_SUM_EX
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Correction in gtests for unpack op (#3869)
This patch corrects the gtests for unpack op.
Signed-off-by: b.devansh <b.devansh@samsung.com>
Correcting the order of input in unpack op (#3868)
This patch corrects the order in which the unpack op takes the input as suggested in #3787.
Signed-off-by: b.devansh <b.devansh@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 01:01:23 +0000 (06:31 +0530)]
Remove Mobilenet_quantized gtest from skiplist (#3836)
This patch will remove Mobilenet_quantized gtest from skiplist
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 01:00:36 +0000 (06:30 +0530)]
Code realignment for namespace to seperate it from CLass func (#3792)
This patch will realign the code in the namespace so as to have
greater readablity and clear seperation from the class member funcs.
Signed-off-by: shubham <shub98.gupta@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Dec 2018 00:48:32 +0000 (09:48 +0900)]
Remove deperecated kernel header (#3860)
Remove deperecated kernel header in include/kernel/acl
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 00:21:42 +0000 (05:51 +0530)]
[tfltool] Enable select operator for LogicalNot op (#3819)
This patch enables LogicalNot in tflitetool in select_operator.py
Signed-off-by: prasannar <prasanna.r@samsung.com>
Add generatedtests for TransposeConv (#3710)
This patch adds generatedtests for TransposeConv.
Signed-off-by: b.devansh <b.devansh@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 11:04:26 +0000 (16:34 +0530)]
Remove space_to_batch_quant gtests from skiplist (#3780)
this patch will remove space_to_batch_quant gtests from skiplist
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 11:03:52 +0000 (16:33 +0530)]
Correction in the commnets in gtest filees (#3834)
This patch will correct the commnets for number of values for input
and output in the gtests.
Signed-off-by: shubham <shub98.gupta@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 11:02:49 +0000 (16:32 +0530)]
Replace ambiguous comments in Gather GTests (#3832)
This patch replaces ambiguous comments in Gather GTests
Signed-off-by: prasannar <prasanna.r@samsung.com>
[tfltool] Correction in select operator for ArgMax op (#3854)
This patch removes "not supported" for ArgMax in tflitetool in select_operator.py
Signed-off-by: b.devansh <b.devansh@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 10:57:06 +0000 (16:27 +0530)]
Redefining ArgMinMax CPU implementation as SimpleArgMinMax (#3812)
This patch redefines ArgMinMax CPU implementation as SimpleArgMinMax,
Since we follow adding 'Simple' as prefix for CPU implementation as a naming convention.
Signed-off-by: prasannar <prasanna.r@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 4 Dec 2018 10:50:42 +0000 (19:50 +0900)]
Update Dockerfile (#3856)
Update Dockerfile to have python3 in the docker image.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 4 Dec 2018 10:49:00 +0000 (19:49 +0900)]
Revise nnfw.spec for tizen (#3857)
Add a required package python 3.
This is for test generation on build time.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 10:47:57 +0000 (16:17 +0530)]
Redefine HashTableLookup CPU implementation as SimpleHashTableLookup (#3804)
This patch redefines HashTableLookup CPU implementation as SimpleHashTableLookup.
Since we follow a naming convention for CPU implementation with prefix 'Simple'.
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Dec 2018 10:40:07 +0000 (19:40 +0900)]
[tflkit] Fix bug tflite_convert.sh for version<2 (#3704)
Fix bug tflite_convert.sh for version<2 setting allow_custom_ops
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Dec 2018 10:39:18 +0000 (19:39 +0900)]
Revise build flags for contrib (#3855)
Revise build flags order for contrib in CfgOptionFlags.cmake
Introduce build flag for tf_test
Use build flag BUILD_LAB for opencl_test build
Change build flags' default for contrib off
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
[tfltool] Correction in select operator for RNN op (#3852)
This patch rectifies RNN in tflitetool in select_operator.py
Signed-off-by: b.devansh <b.devansh@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 4 Dec 2018 08:14:35 +0000 (17:14 +0900)]
[neurun] Remove backend dependency in View (#3821)
* [neurun] Remove backend dependency in View
This commit removes `backend dependency` in `View` classes.
- Add `offset_element_in_bytes` abstract function to `ITensor`
- Make `View` gets `ITensor`
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
* Change offset_element_in_bytes to calcOffset
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 08:00:28 +0000 (13:30 +0530)]
Define Gather_Ex op in NeuralNetworkEx.h (#3756)
This patch defines Gather_Ex op in NeuralNetworkEx.h
Related issue: #3347
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 07:58:30 +0000 (13:28 +0530)]
Add nnapi_delegation for PACK n UNPACK (#3787)
This patch adds nnapi_delegation for pack and unpack op.
Signed-off-by: prasannar <prasanna.r@samsung.com>
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 4 Dec 2018 06:46:20 +0000 (15:46 +0900)]
Update pack input parameters (#3848)
The values_count is added by nnapi_delegate
but it is not necessary because it can be replaced with ifm_indexes.size()
So it will be ignored
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Dec 2018 05:38:32 +0000 (14:38 +0900)]
Remove deprecated contrib directories (#3844)
Remove example, bindacl, and convacl directories
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Dec 2018 05:21:31 +0000 (14:21 +0900)]
Add nnapi delegates for reduce_xx ops (#3786)
Add delegates for tflite::BuiltinOperator_SUM,
tflite::BuiltinOperator_REDUCE_MAX, and tflite::BuiltinOperator_REDUCE_MIN
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 04:45:09 +0000 (10:15 +0530)]
Remove Reduce Min GTest from skiplist (#3842)
This patch removes Reduce Min GTest from skiplist.
Signed-off-by: prasannar <prasanna.r@samsung.com>
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 4 Dec 2018 04:44:49 +0000 (13:44 +0900)]
Add tf_classify reference application (#3642)
* Add tf_classify reference application
This patch creates an `example` directory
The tf_classify application is based on TendofFlow Android Camera Demo.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Change application name and move the location
Use tflite_classify instead of tf_classify
Move application under contrib directory
Do not support to download files
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Add const keyword and remove unnecessary library link
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Use std::vector instead of c-style array
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Use OpenCV C++ apis
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 03:32:17 +0000 (09:02 +0530)]
Add CL kernel calls for ReduceMin from PACL. (#3772)
This patch adds CL kernel calls for ReduceMin from PACL.
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 02:40:49 +0000 (08:10 +0530)]
Remove EQUAL delegated as custom op in nnapi_delegate (#3833)
This patch removes EQUAL delegated as custom op in nnapi_delegate
Since EQUAL is built in op as far as v1.12 is concerned.
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Dec 2018 01:16:30 +0000 (10:16 +0900)]
Collect optional operand index (#3768)
Collect optional operand index using defined API in frontend
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Dec 2018 01:14:34 +0000 (10:14 +0900)]
Introduce permission checker (#3831)
Introduce permission checker in format checker
It check execution permission except script files
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 01:14:23 +0000 (06:44 +0530)]
Remove unnecessary headers files inclusion (#3839)
This patch will remove not req headers inclusion in the following files:
ArgMinMax.cc
ArgMinMax.h
GenericFullyConnectedLayer.cc
GenericFullyConnectedLayer.h
HashtableLookupLayer.cc
HashtableLookupLayer.h
SimpleBatchToSpaceNd.h
SimpleDepthToSpace.h
SimpleEmbeddingLookup.h
SimpleNeg.h
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 01:14:11 +0000 (06:44 +0530)]
Add license comments to SimplePackLayer* (#3838)
This patch will add license comments to SimplePackLayer.cpp and
SimplePackLayer.h
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 01:13:55 +0000 (06:43 +0530)]
Remove not req headers from SquarredDiff CL file (#3837)
This patch will remove not req headers in CLSquaredDifferenceKernel.cpp
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 01:13:42 +0000 (06:43 +0530)]
Remove not req headers from the layers in internal folder (#3840)
This patch will remove unnecessary headers for the follwing files
from the internal/layers :
SimplePackLayer.cc
SimplePackLayer.h
SimplePadLayer.h
SimpleSQRT.cc
SimpleSQRT.h
SimpleSpaceToBatchND.h
SimpleSpaceToDepth.h
SimpleTransposeConv.cc
SimpleTransposeConv.h
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 01:04:24 +0000 (06:34 +0530)]
[tfltool] Enable select operator for LogicalOr op (#3824)
This patch will enalbe select operator for Logicalor op
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 01:02:54 +0000 (06:32 +0530)]
[tfltool] Enable select operator for NotEqual op (#3814)
This patch will enable select operator for NotEqual op
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 01:02:11 +0000 (06:32 +0530)]
Renaming of Logical_AND op to LogicalAnd (#3800)
To maintain uniformity and naming convention,
This patch renames the Logical_AND to LogicalAnd
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 01:01:11 +0000 (06:31 +0530)]
Add gtest to test Neg op for 3D and 4D Tensors (#3796)
This patch will add gtest to test Neg op for 3D/4D tensors.
Signed-off-by: shubham <shub98.gupta@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 00:59:51 +0000 (06:29 +0530)]
[tfltool] Enable select operator for ArgMax op (#3813)
This patch will enable ArgMax op in tflitetool in select_operator.py
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 00:57:55 +0000 (06:27 +0530)]
[tfltool] Enable select operator for LogicalAND op (#3815)
This patch will enable LogicalAND in tflitetool in select_operator.py
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 00:57:08 +0000 (06:27 +0530)]
[tfltool] Enable select operator for Dequantize op (#3818)
This patch enables Dequantize in tflitetool in select_operator.py
Signed-off-by: prasannar <prasanna.r@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 00:49:12 +0000 (06:19 +0530)]
[tfltool] Enable select operator for Unpack op (#3820)
This patch will enable select operator tflitetool for unpack op
Signed-off-by: shubham <shub98.gupta@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 00:46:05 +0000 (06:16 +0530)]
Redefining input parameters in reduce_operations.cl Kernel (#3789)
This patch redefines input parameters in reduce_operations.cl Kernel.
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Dec 2018 00:45:46 +0000 (09:45 +0900)]
Remove execution permission for command and configure (#3830)
Remove execution permission for command and configure
- build-docker
- docker-shell
- image_name.configuration
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 00:45:31 +0000 (06:15 +0530)]
Correction in data type supported by neg_tensor.cl (#3790)
This patch corrects the comments on data type supported by neg_tensor.cl.
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Dec 2018 11:28:48 +0000 (20:28 +0900)]
[tool] Enable select operator for reduce operators (#3810)
Enable select operator for reduce operators: reduce_max, reduce_min, reduce_any, mean, sum,
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
[tfltool] Enable select operator for RNN op (#3825)
This patch enables RNN in tflitetool in select_operator.py
Signed-off-by: b.devansh <b.devansh@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 11:24:00 +0000 (16:54 +0530)]
Add NNAPI delegation to PRELU op (#3807)
This patch adds NNAPI delegation to PRELU op.
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Dec 2018 10:43:43 +0000 (19:43 +0900)]
Handle optional input & output on frontend (#3763)
- Throw exception when optional input is set because we cannot support this yet
- Return with do nothing for optional output
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 3 Dec 2018 10:41:46 +0000 (19:41 +0900)]
Add a generated test for SpaceToBatchND (#3637)
This commit adds a generated test for SpaceToBatchND.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Dec 2018 10:29:07 +0000 (19:29 +0900)]
Initialize and reset for bool type in Diff.cpp (#3777)
Define initializer, reseter and comparator for bool type tensor
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 09:22:32 +0000 (14:52 +0530)]
Remove registraton of EQUAL, RSQRT as custom op. (#3809)
Since ops like EQUAL, RSQRT have been introduced in TF v1.12
They need not be registered as Custom ops anymore.
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 09:20:05 +0000 (14:50 +0530)]
Rename topk_v2 gtests to topk_v2_ex (#3765)
This patch renames topk_v2 gtests to topk_v2_ex.
This is done for maintaining uniformity.
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 09:19:32 +0000 (14:49 +0530)]
Rename split Generated test to split_ex (#3766)
This patch renames split Generated test to split_ex.
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 09:19:03 +0000 (14:49 +0530)]
Renaming Gather GTests to gather_ex (#3767)
This patch renames Gather GTests to gather_ex.
This is done to maintain the uniformity.
Signed-off-by: prasannar <prasanna.r@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 3 Dec 2018 07:37:18 +0000 (16:37 +0900)]
[neurun] Extract Coordinate4D from ParentInfo (#3806)
This commit extracts `Coordinate4D` class from `ParentInfo` to use in other classes generally.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 07:28:27 +0000 (12:58 +0530)]
Introduce PReLU op in PACL (#3791)
This patch introduces PReLU op in PACL.
Related issue: #3459
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Dec 2018 06:42:42 +0000 (15:42 +0900)]
Support boolean tensor input and output (#3808)
Supprot boolean tensor input and output in nnapi delegate
Use temporary buffer for casting between boolean array and quantized int array
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 06:16:12 +0000 (11:46 +0530)]
Remove SQRT and RSQRT delegated as CUSTOM OP in nnapi_delegate (#3788)
This patch removes SQRT and RSQRT delegated as CUSTOM OP in nnapi_delegate.
Since #3742 is merged.
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Dec 2018 05:49:20 +0000 (14:49 +0900)]
Fix typo to path lcov-to-cobertura-xml (#3803)
Fix typo to path lcov-to-cobertura-xml:
externals/lcov-to-covertura-xml -> externals/lcov-to-cobertura-xml
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 04:11:33 +0000 (09:41 +0530)]
Insert LogicalOr case in Model.cc (#3801)
This patch will add case for LogicalOr in Model.cc
Signed-off-by: shubham <shub98.gupta@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 04:01:35 +0000 (09:31 +0530)]
Define SPLIT_EX in NeuralNetworkEx.h (#3755)
This patch defines SPLIT_EX in NeuralNetworkEx.h
Related issue: #3347
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 03:47:07 +0000 (09:17 +0530)]
Define TOPK_V2_EX in NeuralNetworkEx.h (#3759)
This patch defines TOPK_V2_EX in NeuralNetworkEx.h.
Related issue: #3347
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 03:05:21 +0000 (08:35 +0530)]
Add nnapi_delegation for Equal and NOT_Equal (#3745)
* Add nnapi_delegation for Equal and NOT_Equal
This patch adds nnapi_delegation for Equal and NOT_Equal.
Signed-off-by: prasannar <prasanna.r@samsung.com>
* Add nnapi_delegation for Equal and NOT_Equal
This patch adds nnapi_delegation for Equal and NOT_Equal.
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 02:22:56 +0000 (07:52 +0530)]
Implement SQRT_EX op in CPU (#3760)
This patch implements SQRT_EX op in CPU.
Related issue: #3459
Signed-off-by: prasannar <prasanna.r@samsung.com>
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 02:09:37 +0000 (07:39 +0530)]
Introduce PRELU_EX in NeuralNetworksEx.h (#3769)
This patch introduces PRELU_EX in NeuralNetworksEx.h
Related issue: #3574 #3459
Signed-off-by: prasannar <prasanna.r@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Dec 2018 02:05:58 +0000 (11:05 +0900)]
Update generated test files (#3749)
* Remove deprecated generated test files
- Remove deprecated files: already recipe is removed
- Remove deprecated files by renamed: floor, tanh, and div recipe is renamed becasue of namespace conflict
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Update generated files
Update difference between generated by script and code in repo
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 01:44:35 +0000 (07:14 +0530)]
Add gtest to test Logical_OR_Ex op (#3781)
This patch will add gtest to test Logical_OR op
Signed-off-by: shubham <shub98.gupta@samsung.com>
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 01:34:06 +0000 (07:04 +0530)]
Remove Passing mean gtest from skiplist (#3782)
This patch will remove passing mean gtest from skiplist
Signed-off-by: shubham <shub98.gupta@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Dec 2018 01:31:13 +0000 (10:31 +0900)]
Register reduce_xx operator for internal tflite interpreter (#3785)
Reduce_sum, reduce_min, reduce_max builtin operators are registered
for internal tflite interpreter.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
Define TRANSPOSE_CONV_EX in NeuralNetworksEx.h (#3773)
This patch defines TRANSPOSE_CONV_EX in NeuralNetworksEx.h.
Related issue: #3347
Signed-off-by: b.devansh <b.devansh@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 3 Dec 2018 01:27:19 +0000 (10:27 +0900)]
[neurun] Move Convert to backend/acl_cl (#3778)
internal/Convert.h and the source file is acl_cl dependent, so it is
moved to `backend/acl_cl` dir.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>