이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 23 Aug 2019 05:35:32 +0000 (01:35 -0400)]
[nnpkg_run] verify input and output before prepare and run (#6857)
Check input number and input/output types first so that we can do
early exit before prepare.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 23 Aug 2019 05:34:50 +0000 (14:34 +0900)]
[moco-tf] Enable importing Tanh (#6849)
This commit will enable importing `Tanh` as `TFTanh`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 23 Aug 2019 05:34:19 +0000 (14:34 +0900)]
[locop] Remove symbol lookup helper (#6863)
This helper was introduced to reduce code diff during refactoring, and
is no longer necessary.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 23 Aug 2019 04:32:54 +0000 (13:32 +0900)]
Fix svace: deref of nullptr (#6862)
* Fix svace: deref of nullptr
- Fix WGID 405901
- add assert for nullptr check
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* fix format
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 23 Aug 2019 02:16:08 +0000 (22:16 -0400)]
[nnpkg_run] Fix wrong index in randomgen (#6856)
`0` was used (instead of `i`) in loop for generating random inputs.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 23 Aug 2019 01:44:41 +0000 (10:44 +0900)]
Disable build x64 nnpkg-run build on CI (#6864)
Mismatching between installed hdf5 and custom buildtool (6.x) makes link error
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 23 Aug 2019 01:12:36 +0000 (10:12 +0900)]
[res] Add renamed NET test from Multiple_IO_XXXX (#6821)
This commit add (will-be) renamed test cases of Multiple_IO_XXXX.
NET_0022 <- Multiple_IO_000
NET_0023 <- Multiple_IO_001
NET_0024 <- Multiple_IO_002
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 23 Aug 2019 01:04:30 +0000 (10:04 +0900)]
[exo-tflite] Add Tanh visit fuction (#6847)
This commit will add `Tanh` visit function
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 23 Aug 2019 01:02:37 +0000 (10:02 +0900)]
[moco-tf] Support TFTanh Canonicalization (#6852)
This commit will enable for supporting `TFTanh` canonicalization
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 23 Aug 2019 01:01:40 +0000 (10:01 +0900)]
[moco-tf] Add TFFormattedGraph for TFTanh (#6850)
This commit will add `TFFormattedGraph` for `TFTanh`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 23 Aug 2019 01:00:57 +0000 (10:00 +0900)]
[locop] Add Tanh visit function (#6851)
This commit will add `Tanh` visit function
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 23 Aug 2019 00:52:13 +0000 (09:52 +0900)]
Fix svace : uninitialized value as parameter (#6841)
- Fix ID 405892
- Default value(false) is provided
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 23 Aug 2019 00:47:30 +0000 (09:47 +0900)]
Fix svace : deref of nullptr (#6842)
- Fix ID 405891
- add assert for nullptr check
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 23 Aug 2019 00:43:55 +0000 (09:43 +0900)]
static_cast for ARMComputeAxis constructor (#6833)
- This patch fixes aarch64 tizen build error
- assert for range check
- static_cast of size_t(64) parameter into uint32_t
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 22 Aug 2019 23:18:43 +0000 (08:18 +0900)]
[neurun] Introduced scheduler tests (#6789)
* [neurun] Introduced scheduler tests
* implemented infrastructure for scheduler tests
* implemented scheduler test with straight graph and known execution
time
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Prevented memory leak
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Run test three times - one time for each backend
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 23:16:56 +0000 (08:16 +0900)]
[neurun] Check cmd args in run_frameworktest.sh (#6813)
* [neurun] Check cmd args in run_frameworktest.sh
Check command line arguments in `run_frameworktest.sh`. If a required
argument is not given, it will show `Usage` then stop.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* FRAMEWORKTEST_LIST_FILE is not a required argument
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 23:08:14 +0000 (08:08 +0900)]
Make backend::operand::ITensor::calcOffset to const member function (#6825)
This commit makes backend::operand::ITensor::calcOffset to const member function.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
[mir_caffe] Inherit tensor names (#6845)
Set `Operation::Output`s names based on model tensor names.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe2] Inherit tensor names (#6853)
Set `Operation::Output`s names based on model tensor names.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Inherit tensor names (#6854)
Set `Operation::Output`s names based on model tensor names.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Inherit tensor names (#6855)
Set `Operation::Output`s names based on model tensor names.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 11:55:23 +0000 (20:55 +0900)]
[moco-tf] Enable RemoveTFIdentityNode Transform (#6834)
This commit will enable `RemoveTFIdentityNode` transform
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Aug 2019 11:11:07 +0000 (20:11 +0900)]
[exo-tflite] TFLFormattedGraph to print TFLNodes (#6836)
TFLFormattedGraph was added to print the info of TFLNodes.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
[mir] Add a name field to Operation::Output (#6844)
Add a name field to `Operation::Output` along with getter and setter.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 22 Aug 2019 10:07:07 +0000 (13:07 +0300)]
[custom op] Bind custom kernel registry to each backend context at creation time (#6788)
Make backend context hold information about registered custom kernels
This will be later used by `CustomOperationManager`
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 10:05:32 +0000 (19:05 +0900)]
[res] Remove renamed inception tests (#6838)
TF_IV3_XXXX tests are fully replaced by NET_0017~0021. These renamed
tests are safely removed by this commit.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 09:56:25 +0000 (18:56 +0900)]
[res] Add UNIT_Tanh_000 testcase (#6839)
This commit will add `UNIT_Tanh_000` testcase
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 09:54:13 +0000 (18:54 +0900)]
[moco-tf] Introduce TFDialect for Tanh (#6835)
* [moco-tf] Introduce TFDialect for Tanh
This commit will introduce TFDialect for `Tanh`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* Add missing code
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 09:50:49 +0000 (18:50 +0900)]
[res] Shrinked TF Inception_v3_002 test (#6817)
This commit make TF Inception_v3_002 test to have slim dimensions so
that suitable to be tested.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
[mir] Remove old PadOp interface (#6808)
Remove deprecated `PadOp` constructor and getters.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Remove unused include (#6809)
Remove unused include of `Scalar.h`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 08:05:42 +0000 (17:05 +0900)]
[res] Shrinked TF Inception_v3_001 test (#6815)
This commit makes TF Inception_v3_001 test to have slim dimensions so
that suitable to be tested.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 08:05:04 +0000 (17:05 +0900)]
[loco] Introduce Tanh Operation (#6830)
This commit will introduce `Tanh` operation in loco
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Aug 2019 07:21:26 +0000 (16:21 +0900)]
[moco-tf] suporting custom op when inferencing shape and type (#6818)
Added shape and type support for custom op.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 07:12:00 +0000 (16:12 +0900)]
[tf2tflite] Replace TF_IV3-XXX with new name NET_XXX (#6806)
This commit replaces TF_IV3-XXX with new name NET_XXX for tf2tflite.
Note that test contents are same.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 07:04:34 +0000 (16:04 +0900)]
[mir_onnx] Comment out extra token after #endif (#6820)
This commit comments out extra token after #endif, which generates
compile warning on build procedure
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Aug 2019 06:08:55 +0000 (02:08 -0400)]
[nnpkg_run] use uint64_t for num_element (#6807)
- use uint64_t for num_element.
- check each element is not negative.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 22 Aug 2019 05:38:17 +0000 (14:38 +0900)]
Helper library for NNAPI v1.2 (#6823)
Introduce helper library for NNAPI v1.2 (almost copy from v1.1, and update)
Change default helper
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 05:26:16 +0000 (14:26 +0900)]
[mocotest-tf] Replace TF_IV3-XXX with new name NET_XXX (#6805)
This commit replaces TF_IV3-XXX with new name NET_XXX. Note that test
contents are same
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 22 Aug 2019 05:21:53 +0000 (14:21 +0900)]
[neurun] Removed uses of BackendManager in BackendResolver and Scheduler (#6785)
Removed uses of BackendManager in BackendResolver and Scheduler
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 22 Aug 2019 04:52:19 +0000 (13:52 +0900)]
Fix copyright year ShapeInference (#6800)
Fix copyright year of ShapeInference.cc to 2019
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 03:02:09 +0000 (12:02 +0900)]
[neurun] Update Usage msg for run_frameworktest.sh (#6811)
Update Usage message to be verbose for `run_frameworktest.sh`.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 22 Aug 2019 01:50:21 +0000 (10:50 +0900)]
Add missing copyright for nnpackage-run dumper (#6801)
Add missing copyright phrase for nnpackage-run's tensor_dumper.h
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 22 Aug 2019 01:47:33 +0000 (10:47 +0900)]
Fix build fail by signed integer compare with unsigned (#6804)
Fix build fail by type change of num_elements() to unsigned
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 22 Aug 2019 01:39:41 +0000 (10:39 +0900)]
Replace how-to-contribute documentation (#6802)
Replace two how-to-contribute documentation and remove duplication
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 01:19:54 +0000 (10:19 +0900)]
[res] Add renamed NET test from TF_IV3_XXXX (#6794)
This commit add (will-be) renamed test cases of TF_IV3_XXXX.
NET_0017 <- TF_IV3_AvgPool_GlobalPooling
NET_0018 <- TF_IV3_AvgPool_Module
NET_0019 <- TF_IV3_Conv2D_000
NET_0020 <- TF_IV3_Epilogue
NET_0021 <- TF_IV3_MaxPool
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 22 Aug 2019 01:19:39 +0000 (10:19 +0900)]
[res] Shrinked TF Inception_v3_000 test (#6792)
This commit make TF Inception_v3_000 test to have slim dimensions so
that suitable to be tested.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 22 Aug 2019 01:16:31 +0000 (10:16 +0900)]
Use unsigned int for num_elements of Shape (#6507)
- This fixes build break on tizen aarch64
- Assert for non-negative check
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Aug 2019 00:53:38 +0000 (20:53 -0400)]
[nnpkg_run] prepare hdf5 for arm (#6677)
- Install hdf5f and dependent libraries on arm rootfs
- Update CMakeLists.txt
- Create HDF5Config.cmake
- Update nnpackage_run's dump with dummy hdf5 creating code.
- To test whether hdf5 works.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 22:26:28 +0000 (07:26 +0900)]
[mocotest-tf] Enable valid NET tests (#6790)
This commit enables NET_0005 and NET_0006 tests for mocotest-tf
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 19:13:06 +0000 (22:13 +0300)]
[mir_onnx] Fix checking some attributes (#6796)
* Added checking that dilations is equal 1 in Conv and MaxPool
* Removed spatial attribute from BatchNormalization
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 17:42:31 +0000 (20:42 +0300)]
[mir_onnx] Support Flatten operation (#6795)
* Supported V1 and V9 Flatten op versions
* Added Flatten on registration and cmake
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[mir_onnx] Add support for Transpose operator (#6764)
Add support for `Transpose` operator.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 13:03:34 +0000 (16:03 +0300)]
Add virtual dtor to ITimer class (#6786)
Fix failed build while using clang 9.0
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
[mir_onnx] Add missing include guards (#6762)
Add include guards to operator converter headers.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Support Identity operator (#6761)
Add support for `Identity` operator.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Use new PadOp constructor (#6753)
Switch to the new `PadOp` constructor.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 11:43:36 +0000 (20:43 +0900)]
[tf2tflite] Enable valid NET tests (#6791)
This commit enables valid small network tests for tf2tflite:
NET_0004, NET_0005, NET_0006, NET_0011
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 10:31:40 +0000 (19:31 +0900)]
[neurun] Change CMake target name for neurun core (#6782)
Change target name to `neurun_core` from `neurun-core` for consistency
of target name.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 10:15:58 +0000 (13:15 +0300)]
Fix a typo in benchmark runner include guard (#6787)
__BENCHMAKR_RUNNER_H__ used instead of __BENCHMARK_RUNNER_H__
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 10:14:25 +0000 (19:14 +0900)]
Remove jsoncpp from line coverage (#6779)
- Remove jsoncpp from line coverage
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 10:12:27 +0000 (19:12 +0900)]
Change dimension of ACLTensor to start from higher dimension (#6765)
This commit changes dimension function of ACLTensor to start from higher dimension.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 09:45:10 +0000 (18:45 +0900)]
[res] Remove old TF unit tests (#6781)
This commit removes old Tensorflow unit tests
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 09:32:52 +0000 (18:32 +0900)]
[moco-tf] Add RemoveTFIdentityNodeTransform (#6783)
This will add RemoveTFIdentityNodeTransform to transforms list
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[nnc] Use new interface of PadOp (#6713)
Switch to new interface of `PadOp`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Use new PadOp constructor (#6752)
Switch to the new `PadOp` constructor.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Insert TransposeOp to shuffle constants (#6734)
Insert `TransposeOp`s instead of direct permutation of constants to allow non-constant weights.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 07:38:49 +0000 (16:38 +0900)]
[mocotest-tf] Enable UNIT_StopGradient_000 (#6777)
This will enable UNIT_StopGradient_000 unit test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 07:17:57 +0000 (16:17 +0900)]
[mocotest-tf] Enable UNIT_Rsqrt_000 (#6776)
This will enable UNIT_Rsqrt_000 unit test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 07:17:38 +0000 (16:17 +0900)]
[tf2tflite] Enable UNIT_StopGradient_000 (#6778)
This will enable UNIT_StopGradient_000 unit test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 07:16:49 +0000 (16:16 +0900)]
[tf2tflite] Enable UNIT_Rsqrt_000 (#6775)
This will enable UNIT_Rsqrt_000 unit test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 06:41:31 +0000 (15:41 +0900)]
Update NNAPI spec to v1.2 (#6735)
Update NNAPI spec header NeuralNetworks.h
Add new NNAPI spec header NeuralNetworksExtensions.h
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 05:54:16 +0000 (14:54 +0900)]
[res] TF NET_0016 (#6770)
* [res] NET_0016
This will introdude NET_0016 test material having Conv2D + FusedBatchNorm with Identity
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove attr use_cudnn_on_gpu
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 05:49:28 +0000 (14:49 +0900)]
[tfgraph-xform] Support constant folding (#6152)
Now, tfgraph-xform is able to fold constants in TensorFlow GraphDef.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 05:37:51 +0000 (14:37 +0900)]
[moco-tf] RemoveDeadNode for TF dialects (#6773)
This will add RemoveDeadNode optimization for TF dialect node transforms
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 05:37:39 +0000 (14:37 +0900)]
[tf2tflite] Edit unit tests into renamed one (#6769)
This commit edits unit tests into renamed one in tf2tflite
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 05:37:28 +0000 (14:37 +0900)]
[mocotest-tf] Edit unit tests into renamed one (#6768)
This commit edits unit tests into renamed one in mocotest-tf project.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 05:36:52 +0000 (14:36 +0900)]
[moco-tf] Introduce RemoveTFIdentityNodeTransform (#6772)
This will introduce RemoveTFIdentityNodeTransform that disconnects TFIdentity for optimization
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 05:35:44 +0000 (14:35 +0900)]
[moco-tf] RemoveTFIdentityNode Knob (#6771)
This will add RemoveTFIdentityNode Knob to switch RemoveTFIdentityNode optimization
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 04:41:58 +0000 (13:41 +0900)]
[moco-tf] Remove unused files (#6756)
This will remove unused ShapeInference and TypeInference files that are replaced by transforms
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 04:34:57 +0000 (13:34 +0900)]
[loco] Remove "node" method from Graph Input/Output (#6759)
This commit removes "node" method from GraphInput/GraphOutput class.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 04:03:15 +0000 (13:03 +0900)]
[exo-tflite] Clean up deprecated code (#6757)
This commit cleans up deprecated internal shape inference implementations
in exo-tflite.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 03:44:36 +0000 (06:44 +0300)]
Fix overloaded functions being hidden by subclasses (#6697)
void IOperationVisitor::visit(const Subgraph &subgraph) was hidden by function definitions in IKernelGenerator and KernelGenerator classes
This makes nnfw fail to build using clang 9.0
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 03:43:54 +0000 (12:43 +0900)]
[res] Add renamed unit tests (#6749)
This commit adds renamed unit tests, for example, UNIT_Add_000 for
Add_000
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 03:43:07 +0000 (12:43 +0900)]
[tf2tflite] Add divide comment for refactoring (#6742)
This comment will be removed after test case convention refactoring
project.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 01:18:12 +0000 (10:18 +0900)]
Include xml converter in coverage suite (#6758)
To convert lcov report to xml, include xml converter tool into coverage suite
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 00:33:24 +0000 (09:33 +0900)]
Update EigenSource-
fd6845384b86 to read URL from file (#6746)
This commit revises EigenSource-
fd6845384b86 CMake package to read URL
from file instead of environment variable.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 23:42:51 +0000 (08:42 +0900)]
[mocotest-tf] Enable NET_0015 (#6745)
This will enable NET_0015, 1/Sqrt(x), which is same as decomposed elements of Rsqrt
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 22:18:21 +0000 (07:18 +0900)]
[mocotest-tf] Epilogue test (#6750)
This commit adds Epilogue test for mocotest-tf
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 22:18:04 +0000 (07:18 +0900)]
[tf2tflite] Epilogue test (#6751)
This commit adds Epilogue test of Inception v3 for tf2tflie
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:09:20 +0000 (07:09 +0900)]
[moco-tf] Enable RsqrtCanonicalizer (#6740)
This will enable RsqrtCanonicalizer to convert TFRsqrt to canonical nodes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:09:00 +0000 (07:09 +0900)]
[moco-tf] Reserve TFShapeInference for TFStopGradient (#6739)
This will reserve place for TFStopGradient in TFShapeInference
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:08:38 +0000 (07:08 +0900)]
[moco-tf] Enable Canonicalizer for TFStopGradient (#6737)
This will add enable TFStopGradient in Canonicalizer
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:08:17 +0000 (07:08 +0900)]
[moco-tf] Type inference for TFStopGradient (#6736)
This will add TFStopGradient in type inference rule
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:07:53 +0000 (07:07 +0900)]
[tf2tflite] Enable NET_0015 (#6744)
This will enable NET_0015, 1/Sqrt(x), which is same as decomposed elements of Rsqrt
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:07:00 +0000 (07:07 +0900)]
[moco-tf] Remove unused header in FuseBinaryIntoPreceding (#6741)
This will remove unused header in FuseBinaryIntoPreceding
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 19:24:04 +0000 (04:24 +0900)]
[mir2loco] Remove GraphIO::node method calls (#6721)
This commit removes all the GraphInput::node and GraphOutput::node
method calls in mir2loco. This is a step toward loco GraphInput/Output
class redesign.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
[mir_onnx] Rework attribute parsing (#6651)
* Make attribute parsing functions templated and extract them to a separate file.
* Move definition of `getKernelStridesPadding` into cpp file.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Update ONNX source to version 1.5.0 (#6748)
Update ONNX source version to support ONNX IR version 5.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 17:43:02 +0000 (20:43 +0300)]
[mir_onnx] Upsample operation versioning (#6755)
* Supported V1, V7, V9 and V10(deprecated) versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>