박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 09:58:56 +0000 (18:58 +0900)]
[moco-tf] Remove Shape Type inference header (#8270)
This will remove deprecated Shape and Type inference header use that of moco
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 09:40:50 +0000 (18:40 +0900)]
[moco-tf] Update input accessor (#8276)
This will update to use correct input accessor for MaxPool and FusedBatchNorm node and related variables
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 17 Oct 2019 08:27:09 +0000 (17:27 +0900)]
[tool] Support SquaredDifferene in select operator (#8263)
- Support SquaredDifferene in select operator
- Add comment: not supporting options on schema v1.13.1
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 07:38:31 +0000 (16:38 +0900)]
[exo] Register TransposedConv2DConverter (#8271)
This commit registers TransposedConv2DConverter to convert stage.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 07:23:06 +0000 (16:23 +0900)]
[exo] adds loop to fuse the nodes for FuseReluPass (#8266)
This completes FuseReluPass.cpp by add loops that performs fusing selected nodes.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 06:49:36 +0000 (15:49 +0900)]
[plier-tf] Introduce parse_nodedef (#8261)
This will introduce parse_nodedef() method to parse tensorflow::NodeDef object
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 06:49:26 +0000 (15:49 +0900)]
[exo] Introduce TFLConcatenation exporter (#8259)
This commit will introduce `TFLConcatenation` exporter in `exo`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 06:35:25 +0000 (15:35 +0900)]
[exo] Convert canonical TransposedConv2D (#8267)
This commit introduces convert stage for canonical TransposedConv2D.
This conversion would apply to TransposedConv2D to make TFL-dialect
TFLTransposeConv with additional auxiliary nodes.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 06:26:13 +0000 (15:26 +0900)]
[exo] Export TFLTransposeConv (#8260)
This commit introduces export stage of TFLTransposeConv operator
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 06:25:28 +0000 (15:25 +0900)]
[moco-tf] Redirect to moco Service (#8265)
This will update Shape and Type inference class to be redirected to moco Service and remove unused source files
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 05:28:38 +0000 (14:28 +0900)]
[exo] TransposeConv type & shape inference (#8258)
This commit introduces type and shape inferences of TFLTransposeConv
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 04:41:16 +0000 (13:41 +0900)]
[nnpkg-spec] Add instance_norm and revise structure and level (#8148)
It updates nnpackage specification to define `instance_norm` operator.
Also, it updates the document structure since it begin to have additional
operator. I move operators to same level of model for user to find them easily.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 04:28:44 +0000 (13:28 +0900)]
[exo] adding TFLRelu6Converter into convert.cpp (#8253)
This adds TFLRelu6Converter into convert.cpp with related knob on.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 04:18:11 +0000 (13:18 +0900)]
[exo] TransposeConv IR (#8237)
* [exo] TransposeConv IR
This commit introduces TFLTransposeConv IR, TFL-dialect of loco node
representing TFlite TransposedConv operator.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Use camel case member name
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 03:19:23 +0000 (12:19 +0900)]
[res] Add simple network of placeholder with unknown dimension. (#8229)
It is a simple network of placeholder with unknown dimension.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 03:18:38 +0000 (12:18 +0900)]
[exo] refactoring using new function (`create_fused_bias()`) (#8230)
This replaces body with a statement that calls extracted function. (`create_fused_bias()`)
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 17 Oct 2019 02:15:45 +0000 (11:15 +0900)]
[lib/tflite] Update nnapi delegate (#8238)
Update nnapi delegate to match with v1.13.1
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
여지환/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 17 Oct 2019 01:50:06 +0000 (10:50 +0900)]
Rename srcn backend shape (#8120)
Rename srcn backend Shape class into TensorDescriptor
- Use same class name as cpu backend
- Rename variables according to new class name
Signed-off-by: JiHwan Yeo <jihwan.yeo@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 01:07:01 +0000 (10:07 +0900)]
[moco] Introduce Shape and Type inference Service (#8228)
* [moco] Introduce Shape and Type inference Service
This will introduce Shape and Type inference Service from copied from moco-tf
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* make compiler happy
* another for compiler
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 17 Oct 2019 00:22:20 +0000 (09:22 +0900)]
[neurun] Introduce build option for default config (#8167)
- Introduce ENVVAR_NEURUN_CONFIG option: use default neurun config using environment (default: on)
- Default off on tizen, and introduce gbs build option "test_build" to enable environment variable setting
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
[nnc] Explicitly declare some variables as `Operation::Input *` (#8247)
This is needed for transition period.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir-tflite-importer] Fixed a bug (wrong Deconv2d constructir). (#8248)
Setting attributes values is corrected.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir-caffe-importer] Fixed a bug in CaffeOpCreator (#8243)
Setting attributes values is corrected.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[nnc/interpreter] Fix Transpose for quantization (#8242)
* Fixed quantization for output
* Fixed work with every DataType
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[mir2loco] Replace getInputProducer with getInput (#8245)
Replace calls to `getInputProducer` with equivalent `getInput`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] Replace getInputProducer with getInput (#8244)
Replace calls to `getInputProducer` with equivalent `getInput`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir] Make getInput the same as getInputProducer (#8236)
Make `getInput` the same as `getInputProducer`. The latter will be removed.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir-onnx-importer] Use new operations interface in importer. (#8182)
* Using new operations interface in importer.
Changes due to new operations constructors signatures.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir2loco] Switch to `getInputProducer` (#8190)
Replace calls to `getInput()->getProducer()` with calls to `getInputProducer()`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] Switch to `getInputProducer` method (#8189)
Replace calls to `getInput()->getProducer()` with calls to `getInputProducer()`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 10:40:57 +0000 (19:40 +0900)]
[angkor] Overload operator== (#8233)
* [angkor] Overload operator==
This commit overloads operator== to index class.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* apply commnet.
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 09:50:16 +0000 (18:50 +0900)]
[angkor] Overload operator+ (#8210)
* [angkor] Overload operator+
This commit overloads operator+ to Index class.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* add out_of_range thorw exception.
* remove unnecessary header.
* change error type.
* change operator+ from member function to non-member.
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 09:09:17 +0000 (18:09 +0900)]
locomotiv is static library (#8212)
This commit changes locomotiv from shared to static library.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 08:27:19 +0000 (17:27 +0900)]
[moco-tf] Remove VariadicArityNode (#8227)
This will remove not used anymore VariadicArityNode and its test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 08:23:47 +0000 (17:23 +0900)]
[moco-tf] Remove IR tests (#8225)
This will remove IR test codes that already moved to moco-lang
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 08:03:58 +0000 (17:03 +0900)]
[exo] Introduce TFLConcatenation converter (#8221)
This commit will introduce `TFLConcatenation` converter in `exo`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 08:03:47 +0000 (17:03 +0900)]
[exo] Refactoring: Extract code from big method (Fuse) (#8179)
A piece of code is extracted as a method (`create_fused_bias()`) from big method (`Fuse`).
For diff difficulty, old code will be replace with one single call in next PR.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 07:53:35 +0000 (16:53 +0900)]
[exo] TFLMixin for classes that have fused activation function (#8223)
This adds TFLMixin class for TFL nodes that have fused activation function
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 07:51:49 +0000 (16:51 +0900)]
[nnfw-api] use circle loader for circle model (#8222)
It uses model_types from MANIFEST to determine loader.
It also added missing namespace neurun for circle_loader.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 16 Oct 2019 07:51:33 +0000 (16:51 +0900)]
[nnpkg-test] Remove conv test (#8220)
Remove fail conv test: neurun cannot run convolution with input weight
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 07:48:34 +0000 (16:48 +0900)]
[exo] TODO rigorous padding conversion (#8219)
This commit adds TODO comments for rigorous padding conversion
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 07:48:10 +0000 (16:48 +0900)]
[exo] Introducing FuseReluPass (#8176)
* [exo] Introducing FuseReluPass
This introduces FuseReluPass, which fuse relu/relu6 into 10 TensorFlow Lite ops.
This commit adds code that finds candidate subgraph.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remove unused var (to avoid CI error)
* Update compiler/exo/src/Pass/FuseReluPass.h
Co-Authored-By: hyunsik-yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 07:39:12 +0000 (16:39 +0900)]
[moco-tf] Revise IR to using moco::IR (#8218)
This will revise moco::tf IR and base classes to alias of moco IR and base classes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 06:59:54 +0000 (15:59 +0900)]
[exo] Register FoldTransposeOfConst pass (#8202)
This commit registers FoldTransposeOfConst pass to exo TFL-level
optimization.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 06:51:09 +0000 (15:51 +0900)]
[exo] Relu6Converter and TFL/CircleOperationExporter for TFLRelu6 (#8173)
This adds Relu6Converter and TFL/CircleOperationExporter for TFLRelu6.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 06:50:32 +0000 (15:50 +0900)]
[exo] Turn ON ConvertConv2D knob (#8153)
This commit turns on ConvertConv2D knob by default
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 05:20:51 +0000 (14:20 +0900)]
[moco-tf] Revise to use moco TF dialect (#8208)
This will revise moco_tf to use TF dialect from moco
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 05:03:39 +0000 (14:03 +0900)]
[moco-tf] Tidy unused codes (#8204)
This will remove not used anymore Concat and Padding annotations
- Remove also related codes
And remove also not used anymore ImportTarget
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 05:02:46 +0000 (14:02 +0900)]
[moco-tf] Comment for Relu and Relu6 graph builder (#8201)
This will add comments fro Relu and Relu6 GraphBuilder header
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 04:44:05 +0000 (13:44 +0900)]
[exo-tflite] Introduce TFLConcatenate node (#7978)
* [exo-tflite] Introduce TFLConcatenate node
This commit will introduce `TFLConcatenate` node in `exo-tflite`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* fix assert
* rebase and apply comments
* fix typo
* apply comments
Co-Authored-By: sk-namkoong <sk.namkoong@samsung.com>
* add assert
* fix typo
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 03:16:31 +0000 (12:16 +0900)]
[res/TensorFlow] Adding Conv2D-BiasAdd-Relu6 test case (#8172)
* [res/TensorFlow] Adding Conv2D-BiasAdd-Relu6 test case
This adds pbtxt and related files for Conv2D-BiasAdd-Relu6.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remove a term CBR since CBR is normally used with Relu
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 01:43:58 +0000 (10:43 +0900)]
[moco-tf] Remove unused knobs (#8192)
This will remove not used anymore ImportAs TF dialect knobs
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 01:35:50 +0000 (10:35 +0900)]
[moco] Revive old arg accessors (#8194)
This will revive old input argument accessors for IR migration from moco-tf to moco
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 01:35:17 +0000 (10:35 +0900)]
[moco-tf] Tidy includes in Op folder (#8198)
This will tidy includes in Op folder that is not necessary anymore
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Oct 2019 00:59:42 +0000 (09:59 +0900)]
[moco-tf] Use headers in node graph builder (#8191)
This will use node header files in graph builder and cleanup unnecessary header includes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 16 Oct 2019 00:53:01 +0000 (09:53 +0900)]
[neurun] Apply trying const dealloc on ExecutionFactory (#8064)
Apply trying const dealloc on LinearExecutor and ParallelExecutor of
ExecutionFactory
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 23:17:52 +0000 (08:17 +0900)]
[exo] remove complex if statement (#8178)
This removes complex if statement to reduce cyclomatic complexity.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
[mir-tflite-importer] Use new operations interface in importer. (#8183)
Changes due to new operations constructors signatures.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir] Add methods for accessing Operation's inputs (#8188)
The `getInput` method is always used in pair with `getProducer`.
This PR adds `getInputProducer` method for convenience.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] Fix unittest for CombineTransposes optimization (#8187)
Get the correct IDs of Input ops.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir2loco] Use new operations interface in mir2loco.test (#8185)
Changes related to operations constructors renewal.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[nnc] Use new operations interface. (#8184)
Changes due to renewed operations constructors.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir-caffe2-importer] Use new operations interface in importer. (#8181)
Changes due to new operations constructors signatures.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir-caffe-importer] Use new operations interface in importer. (#8180)
Changes due to new operations constructors signatures.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir] Rename AffineQuantization methods (#8177)
* Remove plural variant of methods
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 15 Oct 2019 11:23:42 +0000 (20:23 +0900)]
[tool] Validation model file check in tflite_benchmark (#8149)
Pass verifier and use VerifyAndBuildFromFile in tflite_benchmark
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 15 Oct 2019 11:21:26 +0000 (20:21 +0900)]
Update HowToUseDockerImage.md (Fix broken link) (#8174)
This commit fixes broken link to relative address
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
[mir] Creation InputOp from TensorType (#8137)
* Added setOutputType in Operation
* Added InputOp constructor for TensorType
* Marked other constructor as DEPRECATED
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 10:18:34 +0000 (19:18 +0900)]
[moco-integration-test] adding NET_0034 (#8169)
NET_0034 (conv2d-sub) was added into test.lst.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 10:17:15 +0000 (19:17 +0900)]
[tf2tflite] Adding NET_0034 into test.lst (#8170)
This adds NET_0034 (conv2d-sub) into test.lst.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 10:13:43 +0000 (19:13 +0900)]
[exo] Initializing TFLAdd's fused activation func in existing test code (#8168)
Some test code does not initializes TFLAdd's fused activation func. This commit adds that.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 10:13:32 +0000 (19:13 +0900)]
[exo] type and shape inference for Relu6 (#8171)
This adds type and shape inference for Relu6.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 15 Oct 2019 08:02:57 +0000 (17:02 +0900)]
[exo] Pass to fold Transpose + Const (#8155)
This commit introduces pass to fold Transpose of Const node
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 08:02:27 +0000 (17:02 +0900)]
[moco-tf] Node GraphBuilder header (#8158)
* [moco-tf] Node GraphBuilder header
This will introduce header for GraphBuilder for nodes that doesn't have one.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix guard
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 07:49:27 +0000 (16:49 +0900)]
[exo-tflite] test cases for FuseConv2DAddSubPass (#8101)
* [exo-tflite] test cases for FuseConv2DAddSubPass
This adds four test cases for FuseConv2DAddSubPass.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* make const value 1.5, 3
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 15 Oct 2019 07:46:28 +0000 (16:46 +0900)]
[res] Remove deprecated test case (#8165)
This commit removes deprecated test case.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 07:45:57 +0000 (16:45 +0900)]
[exo] Initialize TFLConv2D member vars (#8166)
This adds an initialization of TFLConv2D member vars.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 07:42:59 +0000 (16:42 +0900)]
[exo] Add fusedActivationFunction to TFLAdd and TFLMul (#8161)
* [exo] Add fusedActivationFunction to TFLAdd and TFLMul
TFLAdd and TFLMul now has an attribute for fusedActivationFunction.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* Modify circle exporter
* remove unused param
* defined and used init_fused_act_func
* remove constructor. init member vars directly
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 15 Oct 2019 06:07:46 +0000 (15:07 +0900)]
[nncc] Remove ENABLE_CONTRIB_BUILD option (#8156)
This option was introduce when nncc has "contrib" directory, but
"contrib" directory no longer exists.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 15 Oct 2019 06:01:08 +0000 (15:01 +0900)]
[CI] Revise test report directory (#7994)
Divide test report directory for each scheduler
Use mixed backend test for graph generation test
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 15 Oct 2019 05:28:03 +0000 (14:28 +0900)]
NNAS create-package command (#8086)
* NNAS create-package command
This commit introduces create-package command.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Add TODO and some comments
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 15 Oct 2019 03:38:26 +0000 (12:38 +0900)]
[loco] Add comment to TensorConstantPad (#8022)
* [loco] Add comment to TensorConstantPad
This commit adds comment to TensorConstantPad IR in loco.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* make comment more clear.
* apply comment.
* modify comment.
* modify comment.
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 15 Oct 2019 03:37:00 +0000 (12:37 +0900)]
[android] Remove unncessary CMakeLists comments (#8151)
Remove comments that are no longer helpful.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 03:29:43 +0000 (12:29 +0900)]
[exo] Using C++ 11 style static_assert (#8152)
This modifies static_assert from c++ 17 style to c++ c++ 11 style.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 15 Oct 2019 03:00:25 +0000 (12:00 +0900)]
[tflite_loader] Model file verification (#8132)
Verification check before tflite model loading
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 15 Oct 2019 01:38:09 +0000 (10:38 +0900)]
[nnapi] Fix transpose conv NNAPI test (#8127)
Set kernel to constant, not model input
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 15 Oct 2019 01:36:00 +0000 (10:36 +0900)]
Apply optimized cpu kernel for SoftMaxFloat32 (#7943)
This commit applies optimized cpu kernel for SoftMaxFloat32.
- Introduce optimized cpu kernel of SoftMax for float
- Apply that kernel for cpu backend of neurun
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 01:17:18 +0000 (10:17 +0900)]
[nnpkg-run] allow --load to accept little endian (#8116)
It will allow little endianness in `nnpackage-run`.
`hdf5` internally convert endianness if necessay.
All we need is to allow little endian from if-condition.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 00:59:15 +0000 (09:59 +0900)]
[tf2circle] Initial copy from tf2tflite (#8145)
* [tf2circle] Initial copy from tf2tflite
This will add working tf2circle from copy of tf2tflite
- CustomOp support is not added cause of duplicate code for now
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* leave message
* remove test material conversion related
* fix build error, remove unused, fix comment
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 00:49:11 +0000 (09:49 +0900)]
[moco] Add naming rule as a comment (#8147)
This will add some comment for naming rule for TF dialect OPCODE and input accessor
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 00:27:23 +0000 (09:27 +0900)]
[moco-tf] Add naming rule as a comment (#8144)
* [moco-tf] Add naming rule as a comment
This will add some comment for naming rule for TF dialect OPCODE and input/output accessor
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove output
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 00:21:13 +0000 (09:21 +0900)]
[moco-tf] Graph build Relu Relu6 as TF dialect (#8141)
This will update graph builder to produce only TF dialect for Relu and Relu6 node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 00:20:56 +0000 (09:20 +0900)]
[moco-tf] Graph build MaxPool as TF dialect (#8140)
This will update graph builder to produce only TF dialect for MaxPool node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Oct 2019 00:15:30 +0000 (09:15 +0900)]
[moco-tf] Graph build Identity as TF dialect (#8139)
This will update graph builder not to produce only TF dialect for Identity node
- related Importer test is also modified to work with this change
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 14 Oct 2019 22:20:22 +0000 (07:20 +0900)]
[moco-tf] Graph build Concat as TF dialect (#8131)
This will remove Graph builder fro Concat as Canonical dialect and build only TF dialect
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 14 Oct 2019 22:19:58 +0000 (07:19 +0900)]
[moco-tf] Graph build Const as TF dialect (#8133)
This will remove Graph builder for Const as Canonical dialect and build only TF dialect
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 14 Oct 2019 22:19:37 +0000 (07:19 +0900)]
[moco-tf] Graph build Conv2D as TF dialect (#8135)
This will remove Graph builder for Conv2D as Canonical dialect and build only for TF dialect
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 14 Oct 2019 22:19:18 +0000 (07:19 +0900)]
[moco-tf] Graph build BiasAdd as TF dialect (#8130)
This will remove Graph builder for BiasAdd as Canonical dialect and build only for TF dialect
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 14 Oct 2019 22:10:00 +0000 (07:10 +0900)]
[moco-tf] Graph build for AvgPool as TF dialect (#8128)
This will remove Graph builder for AvgPool as Canonical dialect and build only for TF dialect
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
Refine [mir] operations constructors in order to simplify interface. (#8044)
Operations attributes are united into structures.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>