남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 19 Aug 2019 05:28:44 +0000 (14:28 +0900)]
[locomotiv] Support TensorSoftmax (#6620)
* [locomotiv] Support TensorSoftmax
This commit will enable supporting `TensorSoftmax` in `locomotiv`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* Modify domain assert
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 19 Aug 2019 05:05:22 +0000 (14:05 +0900)]
[moco-tf] Introduce Restart PhaseRunner (#6667)
This will introduce Restart type PhaseRunner that restarts from the beginning when there is any change in the transformation list
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 19 Aug 2019 04:51:14 +0000 (13:51 +0900)]
[moco-tf] Update TFConcatV2 IR to have variadic arity (#6663)
This will update TFConcatV2 IR to have variadic arity
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 19 Aug 2019 04:17:57 +0000 (13:17 +0900)]
[loco] Eq operato for NodeShape (#6661)
This will introduce Eq(==) operator for NodeShape
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 19 Aug 2019 02:21:03 +0000 (11:21 +0900)]
[neurun] Write comments for class Index (#6608)
This commit adds comments for class `util::Index`.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
[neurun] Clearify Scheduler::ESTAndExecTime with comments (#6649)
Add comments to clearify return values in case of non-parallel-executor
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 19 Aug 2019 01:42:04 +0000 (10:42 +0900)]
[moco-tf] Add TFFormattedGraph for TFSoftmax (#6647)
* [moco-tf] Add TFFormattedGraph for TFSoftmax
This commit will add `TFSoftmax` summary function in `TFFormattedGraph.cpp`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* fix name
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 19 Aug 2019 01:12:20 +0000 (10:12 +0900)]
Introduce a map storing layouts into TensorBuilders (#6641)
This commit introduces a map storing layouts for each operand into TensorBuilders.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 19 Aug 2019 01:10:57 +0000 (10:10 +0900)]
Fix to proper check on non-empty string (#6659)
Previously checking whether shell variable is non-empty worked not as
expected. This commit fixes to do this function as expected.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 19 Aug 2019 00:47:21 +0000 (09:47 +0900)]
[moco-tf] GraphBuilder for SquaredDifference (#6631)
* [moco-tf] GraphBuilder for SquaredDifference
This will introduce GraphBuilder for SquaredDifference to import SquaredDifference node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix comment
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Sun, 18 Aug 2019 23:30:57 +0000 (08:30 +0900)]
[locop] Add TensorSoftmax visit function (#6648)
This commit will add `TensorSoftmax` visit function
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Sun, 18 Aug 2019 23:30:08 +0000 (08:30 +0900)]
[res] Remove obsolete TF_SMALL_NET_XXXX tests (#6650)
This commit removes obsolete TF_SMALL_NET_XXXX test cases. Note that
they are copied to NET_XXXX
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Sun, 18 Aug 2019 23:29:05 +0000 (08:29 +0900)]
[loco] Introduce constgen layer (#6645)
This commit introduce constgen layer to GraphBuilder.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Sun, 18 Aug 2019 23:28:16 +0000 (08:28 +0900)]
[moco-tf] Enable importing Softmax (#6646)
This commit will enable importing `Softmax` in `moco-tf`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
[mir] Remove Gemm operation (#6654)
`GemmOp` is almost the same operation as `FullyConnectedOp`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Remove redundant include (#6652)
Remove inclusion of `DropoutOp.h` popped up as a result of merge conflict.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] Remove support for GemmOp (#6625)
`GemmOp` is almost the same as `FullyConnectedOp`. It will be removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 16 Aug 2019 09:07:57 +0000 (12:07 +0300)]
[mir_onnx] Introduce ConverterContext for using in NodeConverters (#6457)
* Implemented ConverterContext
* Fix NodeConverter interface to accept ConverterContext
* Fix all NodeConverters according to new interface
* Fix ONNX IR version checking.
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 16 Aug 2019 05:55:43 +0000 (14:55 +0900)]
[tf2tflite] Use NET_XXXX for test list (#6639)
This commit use NET_XXXX for tf2tflite test listing instead of
TF_SMALL_NET_XXXX
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 16 Aug 2019 05:55:33 +0000 (14:55 +0900)]
[mocotest-tf] Use NET_XXXX for test list (#6638)
This commit uses NET_XXXX for mocotest-tf test list instead of
TF_SMALL_NET_XXXX
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 16 Aug 2019 04:39:51 +0000 (13:39 +0900)]
[nnpackage_run] Introduce tensor_dumper (#6602)
- Introduce `dump` option in args.*
- Introduce tensor_dumper
- Use tensor_dumper in nnpackage_run
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 16 Aug 2019 04:28:12 +0000 (13:28 +0900)]
[nnpackage_run] Fix wrong allocation size for output (#6640)
outputs[i] is vector<float>. sizeof(float) should not be multiplied.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 16 Aug 2019 04:27:08 +0000 (13:27 +0900)]
Add missing copyright for tflite_run's tensor dumper (#6600)
Add copyright in tensor_dumper.cc and tensor_dumper.h .
It has 2018 year since this files were created in 2018.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 16 Aug 2019 04:12:49 +0000 (13:12 +0900)]
[neurun] Refactor scheduler a little bit (#6636)
* Simplified makeRank method
* Renamed some variables
* Fixed some typos
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 16 Aug 2019 03:43:31 +0000 (12:43 +0900)]
[moco-tf] Enable SquaredDifference canonicalizer (#6629)
This will enable SquaredDifference canonicalizer
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 16 Aug 2019 03:43:06 +0000 (12:43 +0900)]
[moco-tf] Enable type inf for TFSquaredDifference (#6628)
This will enable type inference for TFSquaredDifference node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 16 Aug 2019 03:41:45 +0000 (12:41 +0900)]
[exo-tflite] Enable EltwiseSqrt (#6610)
* [exo-tflite] Enable EltwiseSqrt
This will enable export for EltwiseSqrt node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove for shapeinf
* remove not related new line
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 16 Aug 2019 01:46:33 +0000 (10:46 +0900)]
[res] NET_XXXX to replace SMALL_NET_XXXX (#6621)
This commit adds NET_XXXX tests which copies SMALL_NET_XXXX tests
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 16 Aug 2019 01:43:42 +0000 (10:43 +0900)]
[moco-tf] Register Reshape elimination transforms (#6624)
This commit registers following Reshape elimination transforms to
canonical optimization stage:
- ResolveDuplicateReshape
- ResolveRedundantReshape
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 16 Aug 2019 01:23:20 +0000 (10:23 +0900)]
[moco-tf] Introduce TFDialect for Softmax (#6568)
* [moco-tf] Introduce TFDialect for Softmax
This commit will introduce `TFSoftmax`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* add fix transforms
* remove fix_pad
* use logits instead of input
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 16 Aug 2019 00:37:03 +0000 (09:37 +0900)]
Make helper converting functions support NCHW (#6606)
This commit makes converting functions support NCHW.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 16 Aug 2019 00:35:10 +0000 (03:35 +0300)]
[bug] [custom op] Add back _t suffix for size_t type (#6619)
Was previously removed by error
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 16 Aug 2019 00:34:35 +0000 (09:34 +0900)]
Make cpu KernelGenerator supports NCHW frontend layout (#6605)
This commit makes cpu KernelGenerator supports NCHW frontend layout.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 16 Aug 2019 00:33:54 +0000 (09:33 +0900)]
Make ContantInitializers support NCHW frontend layout (#6555)
This commit makes ContantInitializers support NCHW frontend layout.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 15 Aug 2019 19:08:05 +0000 (22:08 +0300)]
[mir_onnx] Fix border type in Average pooling (#6637)
* Fix come from debuging InceptionV3
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[mir_onnx] Remove Scale converter (#6633)
This operation is not a part of the ONNX specification. It is probably a copy&paste from the Caffe2 importer.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] Remove batchnorm code snippet (#6626)
It was left behind when the rest of the support of `BatchNormOp` was removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 12:01:47 +0000 (21:01 +0900)]
[neurun] Refine neurun-core CMakeLists (#6635)
Refine `target_link_libraries`.
- One target per line
- Remove duplicated lib - `dl`
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 11:46:21 +0000 (20:46 +0900)]
[neurun] Let xdata and xprobe be installed (#6634)
Update `CMakeLists.txt` to install xdata and xprobe.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 11:22:58 +0000 (20:22 +0900)]
[neurun] Introduce CMakeLists.txt for test lib (#6615)
This commit moves test library build from `neurun/CMakeLists.txt` to
`neurun/test/CMakeLists.txt` which is newly created.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 11:22:11 +0000 (20:22 +0900)]
[neurun] Show dlerror on dlopen/dlsym failure (#6632)
Show dlerror on dlopen/dlsym failure
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 10:15:46 +0000 (19:15 +0900)]
[loco] add ctor of DepthwiseFilter PermutingEncoder (#6627)
This commit adds ctor of DepthwiseFilter PermutingEncoder.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 10:05:34 +0000 (19:05 +0900)]
[moco-tf] Canonicalizer for TFSquaredDifference (#6612)
* [moco-tf] Canonicalizer for TFSquaredDifference
This will introduce Canonicalizer for TFSquaredDifference node
For now this will decompose to EltwiseSub and EltwiseMul
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* apply comments
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 09:26:45 +0000 (18:26 +0900)]
[res] TensorFlow SquaredDifference_000 (#6618)
This will introduce TensorFlow basic test for SquaredDifference node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 09:26:26 +0000 (18:26 +0900)]
[res] TensorFlow Sqrt_000 (#6617)
This will introduce TensorFlow basic test for Sqrt node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 14 Aug 2019 09:22:37 +0000 (18:22 +0900)]
[loco] Clean up GraphTestcase (#6613)
Let's remove deprecated code in GraphTestcase.h
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
[mir_onnx] Reimplement Gemm converter through FullyConnected (#6604)
`GemmOp` is almost the same thing as `FullyConnectedOp`. It was only used in the ONNX importer.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 09:22:00 +0000 (18:22 +0900)]
[tf2tflite] Enabled test by FixedReshape support (#6609)
This commit adds several enabled tests in tf2tflite by newly supported
FixedReshape
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
[neurun] Fix fining scheduler and tryBackend (#6616)
CPU_DELAY must be just for parallel executor.
Also tryBackend: PR 5894 commented a line and this
reduced performance by 10%
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
[mir] Accout for data format in shape inference (#6584)
* Add several convenient functions to work with data format.
* Use the functions to implement data format aware shape inference.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 08:32:54 +0000 (17:32 +0900)]
[moco-tf] Enable TFSqrt Canonicalizer (#6614)
This will enable TFSqrt canonicalizer
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 08:29:58 +0000 (17:29 +0900)]
[moco-tf] Knobs for Reshape elimination transform (#6611)
This commit introduces knobs for following Reshape elimination
transforms
- ResolveDuplicateReshape
- ResolveRedundantReshape
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 08:29:12 +0000 (17:29 +0900)]
[moco-tf] TypeInference (#6593)
* [moco-tf] TypeInference
This will introduce TF dialect TypeInference and rule class
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* explicit use name space
* update commentf for TypeInference
* add todo
* update class name and comment
* comment for not supported yet node
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 14 Aug 2019 08:23:20 +0000 (17:23 +0900)]
[moco-tf] Resolve Alloc-Dealloc mismatch (#6599)
Let's use std::unique_ptr<float []> instead of std::unique_ptr<float>!
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 08:15:35 +0000 (17:15 +0900)]
[moco-tf] TFSqrt Canonicalizer (#6592)
* [moco-tf] TFSqrt Canonicalizer
This will introduce TFSqrt node Canonicalizer
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove unused header
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 08:00:24 +0000 (17:00 +0900)]
[loco] Forward Type inference (#6607)
This commit introduces type inference for forward node
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 07:40:44 +0000 (16:40 +0900)]
[moco-tf] GraphBuilder for TFSqrt (#6581)
* [moco-tf] GraphBuilder for TFSqrt
This will introduce GraphBuilder for TFSqrt to import Sqrt node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* rename var
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 07:29:40 +0000 (16:29 +0900)]
[loco/Service] FixedReshape shape inference (#6594)
This commit introduces shape inference logic of FixedReshape and its
test
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 06:58:50 +0000 (15:58 +0900)]
[loco/service] ShapeInferenceRule for multiple dialects (#6587)
* [loco/service] ShapeInferenceRule for multiple dialects
This adds a loco service, a ShapeInferenceRule for multiple dialects.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* fix typo
* modified include
* add #include <map>
* Remove always true assert
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 06:43:50 +0000 (15:43 +0900)]
[loco] remove assert cond that is always true in MultiDialectTypeInferenceRule (#6603)
This commit removes assert cond that is always true in MultiDialectTypeInferenceRule
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 06:10:42 +0000 (15:10 +0900)]
[tf2tflite] enable Const_000 (#6598)
This will enable Const_000 that was fixed in exo-tflite
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 05:43:32 +0000 (14:43 +0900)]
[moco-tf] GraphBuilder for TFRsqrt (#6579)
* [moco-tf] GraphBuilder for TFRsqrt
This will introduce GraphBuilder for TFRsqrt to import Rsqrt node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* rename var
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 05:39:02 +0000 (14:39 +0900)]
[loco/Service] FixedReshape type inference (#6595)
This commit introduces type inference of FixedReshape
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 05:23:30 +0000 (14:23 +0900)]
[locoex/customop] ShapeInference rule for custom op (#6585)
* [locoex/customop] ShapeInference rule for custom op
This commit adds COpShapeInference rule, which is shape inferring rule for custom op.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* add TODO
* wrong comment
* remove 'canonical' from comment
* wrong comment again: Type -> Shape
* wrong comment again and again... COP -> COp
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 05:21:05 +0000 (14:21 +0900)]
[exo-exporter] Remove unused header (#6596)
Let's remove unused header in OperationExporter.cpp
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 05:20:31 +0000 (14:20 +0900)]
[moco-tf] Introduce ResolveRedundantReshape transform (#6571)
* [moco-tf] Introduce ResolveRedundantReshape transform
This commit introduces ResolveRedundantReshape transform of canonical
optimize stage.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Use const arg
* Review fix: fine grained logic
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 05:18:05 +0000 (14:18 +0900)]
[moco-tf] Introduce TFSquaredDifference IR (#6580)
This will introduce TFSquaredDifference IR and required minimum changes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 04:49:07 +0000 (13:49 +0900)]
[exo-tflite] Fix buffer export with adding empty (#6576)
* [exo-tflite] Fix buffer export with adding empty
This will add one empty buffer as first buffer to follow TF lite behavior
- This makes unit Const_000 test pass
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove test list change
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 03:12:54 +0000 (12:12 +0900)]
[moco-tf] Fix missing changed tag (#6583)
This commit fixes missing 'changed' setting on ResolveDuplicateReshape
transform
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 03:11:42 +0000 (12:11 +0900)]
[moco-tf] Comment for TFRsqrt IR (#6578)
This will add comment for TFRsqrt IR
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Aug 2019 03:10:40 +0000 (12:10 +0900)]
[locomotiv] EltwiseSqrt (#6532)
* [locomotiv] EltwiseSqrt
This will introduce execution code for EltwiseSqrt node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add test
* update comment
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 14 Aug 2019 02:05:49 +0000 (05:05 +0300)]
[custom op] api addition (#6219)
* [custom op] Api addition to support custom op registration
Add nnfw_dev.h header with types required to define custom operations
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
* Roll back changes to nnfw.h, add separate header for custom kernel development
* format fix
* use limited dim count for typeinfo struct
* remove _t suffix for types
* fix missed _t suffixes for function types
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 01:56:31 +0000 (10:56 +0900)]
[loco] FixedReshape graph testcase (#6545)
This commit adds graph builder layer and testcase for FixedReshape
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 01:53:42 +0000 (10:53 +0900)]
[exo-tflite] Export FixedReshape operation (#6565)
This commit introduces export of FixedReshape operation
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 01:44:33 +0000 (10:44 +0900)]
[res] Introduce Softmax testcases (#6562)
* [res] Introduce Softmax testcases
This commit will introduce `Softmax` testcases
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* remove versions
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 00:45:11 +0000 (09:45 +0900)]
[xtrace] Hoist loop invariant code (#6566)
Hoist loop invariant code in `benchmark_runner.cc` for readability.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 00:43:01 +0000 (09:43 +0900)]
Make acl_cl KernelGenerator supports NCHW frontend layout (#6552)
This commit makes acl_cl KernelGenerator supports NCHW frontend layout.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 14 Aug 2019 00:41:41 +0000 (09:41 +0900)]
Make acl_neon KernelGenerator supports NCHW frontend layout (#6551)
This commit makes acl_neon KernelGenerator supports NCHW frontend layout.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 13 Aug 2019 22:30:41 +0000 (07:30 +0900)]
[loco] Introduce services for TensorSoftmax (#6564)
This commit will introduce loco services for `TensorSoftmax`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Aug 2019 22:24:22 +0000 (07:24 +0900)]
[moco-tf] Clear ConcatV2 graph builder (#6547)
This will erase ConcatV2 graph builder implementation to reduce complexity of diff for migration to using VariadicArityNode
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Aug 2019 22:23:49 +0000 (07:23 +0900)]
[moco-tf] Introduce TFSqrt IR (#6553)
This will introduce TFSqrt IR to represent TensorFlow Sqrt node and required minimum implementation
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[mir_onnx] Remove uses of DropoutOp (#6560)
This operation is a no-op.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 13 Aug 2019 19:54:47 +0000 (22:54 +0300)]
[mir2loco] Support Softmax operation in transformer (#6575)
* Added SoftmaxOp convertion and test for this
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 13 Aug 2019 18:50:30 +0000 (21:50 +0300)]
[mir2loco] Support Mul operation in transformer (#6573)
* Added MulOp convertion and test for this
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 13 Aug 2019 18:43:52 +0000 (21:43 +0300)]
[mir_onnx] Fix output name for softbackend (#6572)
* Setting empty output node name
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[mir] Introduce data format (#6570)
* Add `DataFormat` enum class.
* Use it in convolutional and pooling operations.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe2] Remove uses of DropoutOp (#6561)
This operation is a no-op.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe] Remove uses of DropoutOp (#6558)
This operation is a no-op.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] Remove uses of DropoutOp (#6556)
This operation is a no-op.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] Eliminate IVisitor in nnc (#6519)
Eliminate abstract IVisitor uses in nnc componet and use Visitor instead
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Aug 2019 10:40:01 +0000 (19:40 +0900)]
Don't build nnpackage_run if neurun is not built (#6557)
nnpackage_run is for neurun.
pacl should not try to build nnpackage_run.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 13 Aug 2019 10:18:46 +0000 (19:18 +0900)]
[loco] Introduce DepthwiseFilterEncode to CanonicalShapeInferenceRule (#6548)
This commit introduces DepthwiseFilterEncode to
CanonicalShapeInferenceRule.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 13 Aug 2019 09:59:28 +0000 (18:59 +0900)]
[loco/Service] Forward node shape inference (#6542)
This commit implements canonical shape inference for Forward node
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Aug 2019 09:28:02 +0000 (18:28 +0900)]
[neurun, nnpackage] Introduce nnpackage_run (#5720)
Initial version of nnpackage.
It supports only `run` with random values.
( store, compare, input are not supported yet. )
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 13 Aug 2019 08:35:35 +0000 (17:35 +0900)]
Make acl_cl KernelGenerator supports NCHW frontend layout (#6544)
This commit makes acl_cl KernelGenerator supports NCHW frontend layout.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 13 Aug 2019 08:01:41 +0000 (17:01 +0900)]
[loco] Remove "shape" setter from Push class (#6527)
This commit removes deprecated "shape" setter from Push class.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Aug 2019 07:40:22 +0000 (16:40 +0900)]
[moco-tf] Clear ConcatV2 Canonicalizer (#6521)
This will erase ConcatV2 Canonicalier implementation to reduce complexcity of diff for migration to using VariadicArityNode
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Aug 2019 07:36:43 +0000 (16:36 +0900)]
[moco-tf] Turning on the knob for ReorderDecodeTensorBiasAdd (#6535)
This commit turns on the knob for ReorderDecodeTensorBiasAdd
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 13 Aug 2019 07:33:10 +0000 (16:33 +0900)]
[exo-tflite] Introduce DepthwiseFilterEncode with exporting as reshape (#6524)
* [exo-tflite] Introduce DepthwiseFilterEncode with exporting as reshape
This commit introcude DepthwiseFilterEncode with exporting as reshape to
exo-tflite.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* remove unused function.
* add some comment.
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 13 Aug 2019 07:29:22 +0000 (16:29 +0900)]
[moco-tf] Use official FixedReshape alias (#6541)
Now loco::FixedReshape alias is official, so this commit starts to use
the alias in moco-tf module.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>