윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 23:33:31 +0000 (08:33 +0900)]
[res] Tensorflow test file for Relu( Add( Conv2D, Scalar )) (#8282)
This adds Conv2D + Add + ReLU where Add's Const operand is a scalar (size 1 tensor).
To check exo handles this OK.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 23:19:27 +0000 (08:19 +0900)]
[moco-integration-test] Enable MergeConcatPass tests (#8288)
This commit will enable `MergeConcatPass` related tests
in `moco-integration-test`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 22:16:06 +0000 (07:16 +0900)]
[tf2tflite] Enable MergeConcatPass tests (#8287)
This commit will enable `MergeConcatPass` related tests
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 22:15:42 +0000 (07:15 +0900)]
[exo] Enable ConvertTensorConcat knob (#8286)
This commit will enable `ConvertTensorConcat` knob in `exo`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
[ncc/interpreter] Fix Reshape operation for quantization (#8246)
* Made Reshape independent from DataType
* Fixed setting output quantization
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[nnc] Fix constant folding optimization for quantization (#8241)
* Fixed transpose for different DataType
* Added qunatization setting on optimization
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[nnc] Fix ModelAnalyzer.linearization test (#8291)
The test relied on specific order of graph traversal.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 10:15:42 +0000 (19:15 +0900)]
[moco] Update input accessor (#8279)
This will update to use correct input accessor for MaxPool and FusedBatchNorm node in moco
and remove temporary added accessors
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 10:15:17 +0000 (19:15 +0900)]
[exo] Add tests for TFLConcatenate (#8273)
This commit will add tests for `TFLConcatenate` in `exo`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 17 Oct 2019 10:14:33 +0000 (19:14 +0900)]
[moco-tf] Introduce TFNodeBuildTester and apply BiasAdd test (#8272)
This will introduce TFNodeBuildTester test helper class for testing node's GraphBuilder class.
And applied BiasAdd test code is also shown to show how it works.
This change purpose is not to use Import class and to test only the GraphBuilder that
converts TensorFlow NodeDef to TF dialect node.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 10:14:15 +0000 (19:14 +0900)]
[exo] Introduce MergeConcatNodePass (#8264)
* [exo] Introduce MergeConcatNodePass
This commit will introduce `MergeConcatNodePass`,
which fold multiple `TFLConcatenation` nodes with same axis
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* apply comments
* add FusedActFunc check
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 17 Oct 2019 10:04:16 +0000 (19:04 +0900)]
[locomotiv] Introduce TensorConstantPad (#8027)
* [locomotiv] Introduce TensorConstantPad
This commit introduces TensorConstantPad to locomotiv.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* change algorithm of pad interpretation.
* make constant value more general.
* change assert to validate.
* modify test.
* add assert for pad_data.
* constant input can be all operator.
* fix some wrong valiate and message.
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>