platform/core/ml/nnfw.git
5 years agoRemove un-necessary header files from Equal CL kernel config files (#3875)
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>
5 years agoChanges in PACK GTest as per specifications in NNAPI (#3866)
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>
5 years agoMove include/util (#3872)
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

5 years ago[neurun] Remove usage of internal/nnapi/kernel (#3862)
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>
5 years agoChange operator TENSORFLOW_SUM name (#3747)
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>
5 years agoCorrection in gtests for unpack op (#3869)
Devansh Bansal/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 01:47:01 +0000 (07:17 +0530)]
Correction in gtests for unpack op (#3869)

This patch corrects the gtests for unpack op.

Signed-off-by: b.devansh <b.devansh@samsung.com>
5 years agoCorrecting the order of input in unpack op (#3868)
Devansh Bansal/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 01:46:05 +0000 (07:16 +0530)]
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>
5 years agoRemove Mobilenet_quantized gtest from skiplist (#3836)
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>
5 years agoCode realignment for namespace to seperate it from CLass func (#3792)
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>
5 years agoRemove deperecated kernel header (#3860)
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>
5 years ago[tfltool] Enable select operator for LogicalNot op (#3819)
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>
5 years agoAdd generatedtests for TransposeConv (#3710)
Devansh Bansal/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 5 Dec 2018 00:17:31 +0000 (05:47 +0530)]
Add generatedtests for TransposeConv (#3710)

This patch adds generatedtests for TransposeConv.

Signed-off-by: b.devansh <b.devansh@samsung.com>
5 years agoRemove space_to_batch_quant gtests from skiplist (#3780)
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>
5 years agoCorrection in the commnets in gtest filees (#3834)
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>
5 years agoReplace ambiguous comments in Gather GTests (#3832)
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>
5 years ago[tfltool] Correction in select operator for ArgMax op (#3854)
Devansh Bansal/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 11:01:36 +0000 (16:31 +0530)]
[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>
5 years agoRedefining ArgMinMax CPU implementation as SimpleArgMinMax (#3812)
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>
5 years agoUpdate Dockerfile (#3856)
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>
5 years agoRevise nnfw.spec for tizen (#3857)
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>
5 years agoRedefine HashTableLookup CPU implementation as SimpleHashTableLookup (#3804)
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>
5 years ago[tflkit] Fix bug tflite_convert.sh for version<2 (#3704)
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>
5 years agoRevise build flags for contrib (#3855)
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>
5 years ago[tfltool] Correction in select operator for RNN op (#3852)
Devansh Bansal/SNAP /SRI-Bangalore/Engineer/삼성전자 [Tue, 4 Dec 2018 08:58:05 +0000 (14:28 +0530)]
[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>
5 years ago[neurun] Remove backend dependency in View (#3821)
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

5 years agoDefine Gather_Ex op in NeuralNetworkEx.h (#3756)
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>
5 years agoAdd nnapi_delegation for PACK n UNPACK (#3787)
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>
5 years agoUpdate pack input parameters (#3848)
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>
5 years agoRemove deprecated contrib directories (#3844)
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>
5 years agoAdd nnapi delegates for reduce_xx ops (#3786)
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>
5 years agoRemove Reduce Min GTest from skiplist (#3842)
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>
5 years agoAdd tf_classify reference application (#3642)
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>
5 years agoAdd CL kernel calls for ReduceMin from PACL. (#3772)
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>
5 years agoRemove EQUAL delegated as custom op in nnapi_delegate (#3833)
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>
5 years agoCollect optional operand index (#3768)
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>
5 years agoIntroduce permission checker (#3831)
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>
5 years agoRemove unnecessary headers files inclusion (#3839)
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>
5 years agoAdd license comments to SimplePackLayer* (#3838)
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>
5 years agoRemove not req headers from SquarredDiff CL file (#3837)
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>
5 years agoRemove not req headers from the layers in internal folder (#3840)
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>
5 years ago[tfltool] Enable select operator for LogicalOr op (#3824)
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>
5 years ago[tfltool] Enable select operator for NotEqual op (#3814)
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>
5 years agoRenaming of Logical_AND op to LogicalAnd (#3800)
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>
5 years agoAdd gtest to test Neg op for 3D and 4D Tensors (#3796)
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>
5 years ago[tfltool] Enable select operator for ArgMax op (#3813)
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>
5 years ago[tfltool] Enable select operator for LogicalAND op (#3815)
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>
5 years ago[tfltool] Enable select operator for Dequantize op (#3818)
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>
5 years ago[tfltool] Enable select operator for Unpack op (#3820)
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>
5 years agoRedefining input parameters in reduce_operations.cl Kernel (#3789)
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>
5 years agoRemove execution permission for command and configure (#3830)
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>
5 years agoCorrection in data type supported by neg_tensor.cl (#3790)
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>
5 years ago[tool] Enable select operator for reduce operators (#3810)
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>
5 years ago[tfltool] Enable select operator for RNN op (#3825)
Devansh Bansal/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 11:27:31 +0000 (16:57 +0530)]
[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>
5 years agoAdd NNAPI delegation to PRELU op (#3807)
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>
5 years agoHandle optional input & output on frontend (#3763)
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>
5 years agoAdd a generated test for SpaceToBatchND (#3637)
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>
5 years agoInitialize and reset for bool type in Diff.cpp (#3777)
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>
5 years agoRemove registraton of EQUAL, RSQRT as custom op. (#3809)
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>
5 years agoRename topk_v2 gtests to topk_v2_ex (#3765)
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>
5 years agoRename split Generated test to split_ex (#3766)
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>
5 years agoRenaming Gather GTests to gather_ex (#3767)
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>
5 years ago[neurun] Extract Coordinate4D from ParentInfo (#3806)
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>
5 years agoIntroduce PReLU op in PACL (#3791)
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>
5 years agoSupport boolean tensor input and output (#3808)
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>
5 years agoRemove SQRT and RSQRT delegated as CUSTOM OP in nnapi_delegate (#3788)
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>
5 years agoFix typo to path lcov-to-cobertura-xml (#3803)
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>
5 years agoInsert LogicalOr case in Model.cc (#3801)
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>
5 years agoDefine SPLIT_EX in NeuralNetworkEx.h (#3755)
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>
5 years agoDefine TOPK_V2_EX in NeuralNetworkEx.h (#3759)
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>
5 years agoAdd nnapi_delegation for Equal and NOT_Equal (#3745)
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>
5 years agoImplement SQRT_EX op in CPU (#3760)
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>
5 years agoIntroduce PRELU_EX in NeuralNetworksEx.h (#3769)
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>
5 years agoUpdate generated test files (#3749)
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>
5 years agoAdd gtest to test Logical_OR_Ex op (#3781)
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>
5 years agoRemove Passing mean gtest from skiplist (#3782)
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>
5 years agoRegister reduce_xx operator for internal tflite interpreter (#3785)
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>
5 years agoDefine TRANSPOSE_CONV_EX in NeuralNetworksEx.h (#3773)
Devansh Bansal/SNAP /SRI-Bangalore/Engineer/삼성전자 [Mon, 3 Dec 2018 01:28:11 +0000 (06:58 +0530)]
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>
5 years ago[neurun] Move Convert to backend/acl_cl (#3778)
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>
5 years agoAdd Quant8 support to NotEqual CL (#3754)
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Fri, 30 Nov 2018 07:38:52 +0000 (13:08 +0530)]
Add Quant8 support to NotEqual CL (#3754)

This patch will provide quant8 support for NotEqual Op

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoHandle boolean for nnapi delegate (#3775)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Nov 2018 07:38:29 +0000 (16:38 +0900)]
Handle boolean for nnapi delegate (#3775)

To handle boolean for nnapi delegate, change type to quantized tensor and call NNAPI

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoDefine Abs_Ex op in NeuralNetworksEx.h (#3758)
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Fri, 30 Nov 2018 07:38:08 +0000 (13:08 +0530)]
Define Abs_Ex op in NeuralNetworksEx.h (#3758)

This patch will define Abs_Ex op in NeuralNetworksEx.h

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoMove benchmark into contrib (#3774)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Nov 2018 06:58:49 +0000 (15:58 +0900)]
Move benchmark into contrib (#3774)

Move benchmark into contrib
Revise directory structure: use src directory
Revise cmake to reference src directory and check build option

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoIntroduce LOGICAL_AND op in runtime (#3564)
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Fri, 30 Nov 2018 06:23:07 +0000 (11:53 +0530)]
Introduce LOGICAL_AND op in runtime (#3564)

This patch introduces LOGICAL_AND op in our runtime.
Related issue: #3459

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoAdd delegate for SQRT and RSQRT (#3742)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Nov 2018 06:08:11 +0000 (15:08 +0900)]
Add delegate for SQRT and RSQRT (#3742)

* Add delegate for SQRT and RSQRT

With tensorflow v1.12, SQRT and RSQRT are built-in operator.
This commit adds delegate for built-in SQRT and RSQRT.

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* Add macro to avoid GBS build fail

tizen(obs) has tensorflow v1.9 while this commit requires v1.12.

5 years agoIntroduce optional operand set on frontent (#3751)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Nov 2018 04:13:08 +0000 (13:13 +0900)]
Introduce optional operand set on frontent (#3751)

Introduce unordered_set field for optional operand
Define API to insert optional operand
Introduce process to handle optional operand at model finish (cannot handle yet)

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[neurun] Replace ITensor to our own (#3739)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 30 Nov 2018 04:10:00 +0000 (13:10 +0900)]
[neurun] Replace ITensor to our own (#3739)

Related : #3273
Part of : #3700

This commit replaces `arm_compute::ITensor` to `neurun::operand::ITensor` finally.

Replaced below classes
- ITensor
- ICLTensor
- CLTensor
- CLSubTensor

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoImplement CL Kernel for ReduceMin op (#3744)
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Fri, 30 Nov 2018 02:17:27 +0000 (07:47 +0530)]
Implement CL Kernel for ReduceMin op (#3744)

This patch implements CL Kernel for ReduceMin op.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoCorrection in SpaceToBatch CPU version for quant8 datatype (#3686)
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Fri, 30 Nov 2018 02:07:32 +0000 (07:37 +0530)]
Correction in SpaceToBatch CPU version for quant8 datatype (#3686)

This patch will set correct zero_value for quant8 datatype in spaceToBatch.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoAdding nnapi delegation changes regarding TransposeConv (#3427)
Devansh Bansal/SNAP /SRI-Bangalore/Engineer/삼성전자 [Fri, 30 Nov 2018 01:08:48 +0000 (06:38 +0530)]
Adding nnapi delegation changes regarding TransposeConv (#3427)

This patch adds required changes to nnapi delegate to run transpose conv

Signed-off-by: b.devansh <b.devansh@samsung.com>
5 years agoRemove passing pad_quant8 gtest from skiplist (#3694)
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 29 Nov 2018 22:19:49 +0000 (03:49 +0530)]
Remove passing pad_quant8 gtest from skiplist (#3694)

This patch will remove pad_quant8 gtest from skiplist

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoAdd GTest for ReduceMin op. (#3732)
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 29 Nov 2018 22:19:35 +0000 (03:49 +0530)]
Add GTest for ReduceMin op. (#3732)

This patch adds GTest for reduce_min op.
Added files:
```
reduce_min_ex
reduce_min_ex_float_1
reduce_min_ex_float_2
```

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoAdd GTest for LogicalAND op (#3567)
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 29 Nov 2018 06:38:18 +0000 (12:08 +0530)]
Add GTest for LogicalAND op (#3567)

This patch adds GTest for LogicalAND op.
Related issue: 3459

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoAdd validation function & missing broadcast related code in NOTEQUAL (#3715)
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Thu, 29 Nov 2018 00:58:12 +0000 (06:28 +0530)]
Add validation function & missing broadcast related code in NOTEQUAL (#3715)

This patch will add validation function and missing broadcast related code.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoIntroduce ReduceMin in PACL (#3729)
Prasanna R/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 28 Nov 2018 10:43:47 +0000 (16:13 +0530)]
Introduce ReduceMin in PACL (#3729)

This patch introduces ReduceMin in PACL.
Related issue: #3459

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years ago[neurun] Introduce Node.Include.h (#3740)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 28 Nov 2018 09:34:23 +0000 (18:34 +0900)]
[neurun] Introduce Node.Include.h (#3740)

This file includes headers of all the nodes

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Change dot_dumper input/output shape (#3741)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 28 Nov 2018 09:18:25 +0000 (18:18 +0900)]
[neurun] Change dot_dumper input/output shape (#3741)

This commit changes `input`/`output` shape of dot_dumper graph to `doublecircle`.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoRemoving the not required Pad op files (#3625)
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 28 Nov 2018 07:58:19 +0000 (13:28 +0530)]
Removing the not required Pad op files (#3625)

After PR #3428 merged
These PadLayer files are not required.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoUpdate build-docker command (#3697)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 28 Nov 2018 06:42:17 +0000 (15:42 +0900)]
Update build-docker command (#3697)

- Change command: build_docker -> build-docker
- Can use docker build options
- Update docker file: restrict yapf version to 0.22.0
- Update document

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoSave pointer to buffer for operand value setting (#3736)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 28 Nov 2018 04:54:13 +0000 (13:54 +0900)]
Save pointer to buffer for operand value setting (#3736)

For operand value setting, save pointer to buffer instead of copy when size is greater than
ANEURALNETWORKS_MAX_SIZE_OF_IMMEDIATELY_COPIED_VALUES defined in NeuralNetworks.h

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoCorrection in pad CPU version for quant8 datatype (#3687)
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 28 Nov 2018 04:22:14 +0000 (09:52 +0530)]
Correction in pad CPU version for quant8 datatype (#3687)

This patch set the correct padding value which is offset for quant8 dataypes.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoAdd CLkernel for Generic Padding (#3428)
Shubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 [Wed, 28 Nov 2018 01:34:54 +0000 (07:04 +0530)]
Add CLkernel for Generic Padding (#3428)

This patch will add cl kernel to execute pad op on GPU

Signed-off-by: shubham <shub98.gupta@samsung.com>