platform/core/ml/nnfw.git
4 years ago[exo-tflite] Add EltwiseConverter to conversion list (#7463)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 08:15:37 +0000 (17:15 +0900)]
[exo-tflite] Add EltwiseConverter to conversion list (#7463)

This will add EltwiseConverter to conversion list from knob status

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[locomotiv] Introduce Eltwise Binary Node Helper (#7461)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 16 Sep 2019 07:49:37 +0000 (16:49 +0900)]
[locomotiv] Introduce Eltwise Binary Node Helper (#7461)

* [locomotiv] Introduce Eltwise Binary Node Helper

This commit introduces a shared helper method for for element-wise
binary nodes, and rewrites the "execute" method for these nodes using
this helper.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Add a blank line

4 years ago[moco-tf] Remove unused includes (#7462)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 07:44:20 +0000 (16:44 +0900)]
[moco-tf] Remove unused includes (#7462)

This commit removes unused includes for TFConv2D and
TFConv2DBackpropInput.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[exo-tflite] adding knob for loco::FeatureBiasAdd (#7460)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 07:41:22 +0000 (16:41 +0900)]
[exo-tflite] adding knob for loco::FeatureBiasAdd (#7460)

A knob for loco::FeatureBiasAdd is added.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[loco] Adding shape inference for loco::BiasDecode (#7456)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 07:12:10 +0000 (16:12 +0900)]
[loco] Adding shape inference for loco::BiasDecode (#7456)

This adds shape inference for loco::BiasDecode

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[loco] Adding type inference for loco::BiasDecode (#7455)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 06:57:42 +0000 (15:57 +0900)]
[loco] Adding type inference for loco::BiasDecode (#7455)

This adds type inference for loco::BiasDecode.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Add TFFormattedGraph for TFMean (#7453)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 06:55:05 +0000 (15:55 +0900)]
[moco-tf] Add TFFormattedGraph for TFMean (#7453)

This commit will add `TFFormattedGraph` for `TFMean`

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[exo-tflite] Adding AvgPool2DConverter into convert.cpp (#7389)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 06:52:34 +0000 (15:52 +0900)]
[exo-tflite] Adding AvgPool2DConverter into convert.cpp (#7389)

AvgPool2DConverter is added into Convert.cpp. After this, turning on the knob will convert loco::AvgPool2D to TFLAveragePool2D.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Replace Pad.h with Padding2D.h (#7438)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 06:52:18 +0000 (15:52 +0900)]
[moco-tf] Replace Pad.h with Padding2D.h (#7438)

This commit replaces Pad.h with Padding2D.h in moco-tf.

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[loco] PlaneInference by direction (#7452)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 06:50:46 +0000 (15:50 +0900)]
[loco] PlaneInference by direction (#7452)

This commit fixed PlaneInference into template with argument 'Direction'

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[moco-tf] Remove unused in Conv2D and DWConv2D (#7451)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 06:49:35 +0000 (15:49 +0900)]
[moco-tf] Remove unused in Conv2D and DWConv2D (#7451)

This will remove not used anymore codes in Conv2D and DepthwiseConv2dNative IR

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Handle export for TensorBroadcast (#7450)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 06:48:19 +0000 (15:48 +0900)]
[exo-tflite] Handle export for TensorBroadcast (#7450)

This will add handler for loco::TensorBroadcast that throws an error

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Export for TFLMul (#7449)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 06:46:45 +0000 (15:46 +0900)]
[exo-tflite] Export for TFLMul (#7449)

This will add exporter for TFLMul node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[loco] make_HWCN_perm helper (#7442)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 06:46:31 +0000 (15:46 +0900)]
[loco] make_HWCN_perm helper (#7442)

This commit introduces make_HWCN_perm helper for filter domain for test
case build.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[locomotiv] Introduce UserData (#7397)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 16 Sep 2019 06:31:28 +0000 (15:31 +0900)]
[locomotiv] Introduce UserData (#7397)

* [locomotiv] Introduce UserData

This commit introduces UserData management module and rewrites Pull node
executor using this UserData management module.

This is the first step to decouple locomotiv-internal data structures from
public user-level data structures.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Remove extra token after #endif

4 years ago[moco-tf] Clean up deprecated code (#7398)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 16 Sep 2019 06:29:36 +0000 (15:29 +0900)]
[moco-tf] Clean up deprecated code (#7398)

Let's clean up deprecate codes from Add/Sub/Mul/RealDiv canonicalizer
implementations.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[loco] Context-based ForwardShapeInferenceAlgorithm (#7431)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 16 Sep 2019 06:29:21 +0000 (15:29 +0900)]
[loco] Context-based ForwardShapeInferenceAlgorithm (#7431)

This commit revises ForwardShapeInferenceAlgorithm to access NodeShape
through ShapeInferenceRule::Context instead of global shape helpers.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[locop] Show TensorShape if possible (#7437)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 16 Sep 2019 06:28:44 +0000 (15:28 +0900)]
[locop] Show TensorShape if possible (#7437)

With this change, Linear V1 Graph Formtter now shows some details of
TensorShape if possible.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[loco] In PlaneInference, fix public memebers to private (#7448)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 06:10:49 +0000 (15:10 +0900)]
[loco] In PlaneInference, fix public memebers to private (#7448)

This commit fixes public members to be private, as intended.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[loco] Introduce DialectService (#7439)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 16 Sep 2019 06:08:42 +0000 (15:08 +0900)]
[loco] Introduce DialectService (#7439)

* [loco] Introduce DialectService

This commit introduces DialectServices class and extends Dialect class
to support service registration.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Update per feedback

4 years ago[exo-tflite] Knob for convert EltwiseMul and TensorBroadcast (#7443)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 05:28:33 +0000 (14:28 +0900)]
[exo-tflite] Knob for convert EltwiseMul and TensorBroadcast (#7443)

This will knob for convert EltwiseMul and TensorBroadcast to TFL dialect

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Adding optimization passes (#7402)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 05:25:37 +0000 (14:25 +0900)]
[exo-tflite] Adding optimization passes (#7402)

This adds SimplifyDomainConversionPass, RemoveForwardNodePass, and RemoveDeadNodePass into Convert.cpp.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] TF dialect TFConv2DBackpropInput (#7401)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 05:25:27 +0000 (14:25 +0900)]
[moco-tf] TF dialect TFConv2DBackpropInput (#7401)

This commit introduces TF dialect TFConv2DBackpropInput.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[locomotiv] Support TransposedConv2D (#7348)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 05:25:16 +0000 (14:25 +0900)]
[locomotiv] Support TransposedConv2D (#7348)

This commit adds execution for TransposedConv2D and its test.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[exo-tflite] Test graph builder (#7399)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 05:20:58 +0000 (14:20 +0900)]
[exo-tflite] Test graph builder (#7399)

Adding test graph builder for easier and shorter test code

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Use getter input and filter for Conv2D (#7445)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 05:14:54 +0000 (14:14 +0900)]
[moco-tf] Use getter input and filter for Conv2D (#7445)

This will update to use input and filter getter for Conv2D and DepthwiseConv2dNative

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] input setters for DepthwiseConv2dNative (#7441)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 04:51:00 +0000 (13:51 +0900)]
[moco-tf] input setters for DepthwiseConv2dNative (#7441)

This will add new input setters for DepthwiseConv2dNative to match current convention of input node setter methods

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] shape inference for broadcast and TFLAdd (#7429)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 04:32:34 +0000 (13:32 +0900)]
[exo-tflite] shape inference for broadcast and TFLAdd (#7429)

* [exo-tflite] shape inference for broadcast

This will add helper functions for broadcast and shape inference of TFLAdd using them

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* make compiler happy

* fix message

4 years agoRename pacl run script (#7259)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 16 Sep 2019 04:19:45 +0000 (13:19 +0900)]
Rename pacl run script (#7259)

Raname script test_arm.sh to test_arm_pacl.sh

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[neurun] Add document for xu3 on tizen (#7331)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 04:18:31 +0000 (13:18 +0900)]
[neurun] Add document for xu3 on tizen (#7331)

Add document for xu3 on tizen. This doc comes from xu4_tizen.md.

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[exo-tflite] Introduce TFLMul (#7430)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 04:09:57 +0000 (13:09 +0900)]
[exo-tflite] Introduce TFLMul (#7430)

This will introduce TFLMul IR for TensorFlow lite MUL node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] input setters for Conv2D (#7433)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 03:45:31 +0000 (12:45 +0900)]
[moco-tf] input setters for Conv2D (#7433)

This will add new input setters for Conv2D to match current convention of input node setter methods

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[loco] Replace Pad.h with Padding2D.h (#7440)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 03:26:53 +0000 (12:26 +0900)]
[loco] Replace Pad.h with Padding2D.h (#7440)

This commit replaces Pad.h with Padding2D.h in loco.

Related: #7357

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[moco-tf] Use generated opname (#7435)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 16 Sep 2019 02:27:19 +0000 (11:27 +0900)]
[moco-tf] Use generated opname (#7435)

This commit revises TFFormattedGraph to use generated opname instead of
hardcoded one.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Introduce TFDialect for Mean (#7320)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 01:44:48 +0000 (10:44 +0900)]
[moco-tf] Introduce TFDialect for Mean (#7320)

* [moco-tf] Introduce TFDialect for Mean

This commit will introduce TFDialect for `Mean`

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* apply comments

4 years agoMake to support PReLU op for acl neon (#7330)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 01:32:37 +0000 (10:32 +0900)]
Make to support PReLU op for acl neon (#7330)

This commit makes to support PReLU op for acl neon.
  - Add PReLU kernel of acl neon
  - Make neurun supports PReLU op for acl neon

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[loco] Rename Pad class to Padding2D (#7395)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 01:30:38 +0000 (10:30 +0900)]
[loco] Rename Pad class to Padding2D (#7395)

This commit is for renaming existing Pad class to Padding2D in loco.

Related: #7357

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years agoEnable QASYMM8 of PReLU op for acl cl (#7292)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 16 Sep 2019 01:24:31 +0000 (10:24 +0900)]
Enable QASYMM8 of PReLU op for acl cl (#7292)

This commit enables QASYMM8 of PReLU op for acl cl.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[exo-tflite] Adding MaxPool2DConverter into convert.cpp (#7400)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 16 Sep 2019 00:35:16 +0000 (09:35 +0900)]
[exo-tflite] Adding MaxPool2DConverter into convert.cpp (#7400)

Now MaxPool2DConverter will work with knob on.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[nnc] Remove frontend passes (#7423)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 13 Sep 2019 20:02:36 +0000 (23:02 +0300)]
[nnc] Remove frontend passes (#7423)

Remove frontend passes. Call importers directly instead.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Remove frontend passes in tests (#7424)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 13 Sep 2019 18:47:44 +0000 (21:47 +0300)]
[nnc] Remove frontend passes in tests (#7424)

Remove frontend passes. Call importers directly instead.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Remove frontend passes in utils (#7425)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 13 Sep 2019 18:44:29 +0000 (21:44 +0300)]
[nnc] Remove frontend passes in utils (#7425)

Remove frontend passes. Call importers directly instead.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir] Remove DTYPE (#7422)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 13 Sep 2019 16:51:39 +0000 (19:51 +0300)]
[mir] Remove DTYPE (#7422)

Remove no longer used type alias `DTYPE`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Replace DTYPE with DataType. (#7421)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 13 Sep 2019 14:44:19 +0000 (17:44 +0300)]
[mir_onnx] Replace DTYPE with DataType. (#7421)

Replace deprecated `DTYPE` with `DataType`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Eliminate TransposeOp in Gemm when weights is ConstantOp (#7416)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 12 Sep 2019 17:04:41 +0000 (20:04 +0300)]
[mir_onnx] Eliminate TransposeOp in Gemm when weights is ConstantOp (#7416)

* Fixed Gemm importer for elimination extra Transposes

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[mir] Remove default value of `data_format` parameter (#7420)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 12 Sep 2019 17:00:29 +0000 (20:00 +0300)]
[mir] Remove default value of `data_format` parameter (#7420)

* Remove default value of `data_format` parameter of conv-like op constructors.
* Rename `CommonProps.h` -> `PaddingType.h`.
* Remove deprecated enum members of `PaddingType`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_tflite] Set `data_format` parameter explicitly (#7415)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 12 Sep 2019 15:19:24 +0000 (18:19 +0300)]
[mir_tflite] Set `data_format` parameter explicitly (#7415)

* Pass `data_format` to constructors of conv-like ops explicitly.
* Replace deprecated `PaddingType::Same` with equivalent `PaddingType::SameUpper`.
* Remove unused includes.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe] Remove unused include (#7417)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 12 Sep 2019 15:15:32 +0000 (18:15 +0300)]
[mir_caffe] Remove unused include (#7417)

Remove one unused include directive

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe2] Remove unused include (#7418)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 12 Sep 2019 15:15:13 +0000 (18:15 +0300)]
[mir_caffe2] Remove unused include (#7418)

Remove one unused include directive

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir2loco] Set data format explicitly (#7419)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 12 Sep 2019 15:14:35 +0000 (18:14 +0300)]
[mir2loco] Set data format explicitly (#7419)

Pass `data_format` argument to conv-like constructors explicitly.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir] Fix padding computation (#7413)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 12 Sep 2019 13:45:29 +0000 (16:45 +0300)]
[mir] Fix padding computation (#7413)

Fix padding computation for `DeConv2DOp`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Pass data format to conv-like op constructors explicitly (#7409)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 11 Sep 2019 14:18:45 +0000 (17:18 +0300)]
[nnc] Pass data format to conv-like op constructors explicitly (#7409)

* Pass data format to constructors of `Conv2DOp`, `DeConv2DOp`, `DepthwiseConv2DOp` explicitly.
* Add missing parameter to call of `DeConv2DOp` constructor.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Unittests for Layout Switcher (#7321)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 11 Sep 2019 12:56:47 +0000 (15:56 +0300)]
[nnc] Unittests for Layout Switcher (#7321)

* Implemented tests for all layout related operations

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[mir] Remove old `DeConv2DOp` constructors (#7405)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 11 Sep 2019 12:21:28 +0000 (15:21 +0300)]
[mir] Remove old `DeConv2DOp` constructors (#7405)

* Remove old `DeConv2DOp` constructors which accept only one padding vector instead of two.
* Add enum members to `PaddingType` to match ONNX specification.
* Adjust padding and output shape calculation for `DeConv2DOp`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[exo-tflite] Make unit test use perm initialized with NHWC layout (#7396)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 08:58:00 +0000 (17:58 +0900)]
[exo-tflite] Make unit test use perm initialized with NHWC layout (#7396)

This make FeatureEncode and FeatureDecode use NHWC layout. Previous test code does not have this info and this test will fail when MaxPool2DConverter is enabled.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[exo-tflite] Introducing MaxPool2DConverter (#7387)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 08:20:08 +0000 (17:20 +0900)]
[exo-tflite] Introducing MaxPool2DConverter (#7387)

* [exo-tflite] Introducing MaxPool2DConverter

This adds MaxPool2DConverter, which converts loco::MaxPool2D to locoex::TFLMaxPool2D.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* adds template instantiation

4 years ago[loco] Add TransposedConv2DLayer for test GraphBuilder (#7392)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 08:14:33 +0000 (17:14 +0900)]
[loco] Add TransposedConv2DLayer for test GraphBuilder (#7392)

This commit adds TransposedConv2DLayer for test GraphBuilder.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[loco] Introduce Matrix Domain with its codecs (#7271)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 11 Sep 2019 08:12:43 +0000 (11:12 +0300)]
[loco] Introduce Matrix Domain with its codecs (#7271)

* Added Domain::Matrix
* Added MatrixShape, MatrixAxis, MatrixIndex
* Added and implemented MatrixEncoder and MatrixDecoder

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[mir2loco] Support DataFormat from mir in layout related ops (#7322)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 11 Sep 2019 08:08:55 +0000 (11:08 +0300)]
[mir2loco] Support DataFormat from mir in layout related ops (#7322)

* Created createHWIOFilterEncode
* Fixed createFeatureEncode, createFeatureDecode using DataFormat from
mir operations

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[ann-ref] Resolve SOLVe issues in ann-ref (#7380)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 08:06:03 +0000 (17:06 +0900)]
[ann-ref] Resolve SOLVe issues in ann-ref (#7380)

This commit will add missing Tensorflow author and source statements

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[exo-tflite] Rename existing Pad class (#7388)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 08:05:36 +0000 (17:05 +0900)]
[exo-tflite] Rename existing Pad class (#7388)

This commit is for renaming existing Pad class in exo-tflite.

Related: #7357

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[loco] Rename existing Pad class (#7393)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 08:04:55 +0000 (17:04 +0900)]
[loco] Rename existing Pad class (#7393)

This commit is for renaming existing Pad class in loco.

Related: #7357

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[exo-tflite] Fix wrong ifdef guard (#7391)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 08:01:39 +0000 (17:01 +0900)]
[exo-tflite] Fix wrong ifdef guard (#7391)

This file was previously in `conversion` directory and ifdef guard contains CONVERSION. Now the file is in `src` so `CONVERSION` was removed.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[tfkit] Resolve SOLVe issues in tfkit (#7381)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 07:58:05 +0000 (16:58 +0900)]
[tfkit] Resolve SOLVe issues in tfkit (#7381)

This commit will add Tensorflow author and remove redundant license statements

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[logo] Preparing SimplifyDomainConversionPass to add more visit() (#7157)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 07:56:52 +0000 (16:56 +0900)]
[logo] Preparing SimplifyDomainConversionPass to add more visit() (#7157)

* [logo] Preparing SimplifyDomainConversionPass to add more visit()

This is a preparation to introduce other visit(..).

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* nullifying input, etc

4 years ago[nnc] Resolve SOLVe issues in nnc (#7383)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 07:56:07 +0000 (16:56 +0900)]
[nnc] Resolve SOLVe issues in nnc (#7383)

This commit will modify Apache 2.0 License to BSD 2-Clause License
since the code itself is 100% matched with original code and
caffe is under BSD 2-Clause License

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[mir2loco] Rename existing Pad class (#7386)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 07:51:16 +0000 (16:51 +0900)]
[mir2loco] Rename existing Pad class (#7386)

This commit is for renaming existing Pad class in mir2loco.

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[mocotest-tf] Enable Some Broadcasting Tests (#7385)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 07:40:55 +0000 (16:40 +0900)]
[mocotest-tf] Enable Some Broadcasting Tests (#7385)

This commit enables supported broadcasting tests.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[nnpkg] Update specification for operators (#7355)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 07:36:33 +0000 (16:36 +0900)]
[nnpkg] Update specification for operators (#7355)

It specifies the operators will use the same input, output and
attributes from tensorflow lite.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[moco-tf] Rename existing Pad class (#7384)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 07:17:20 +0000 (16:17 +0900)]
[moco-tf] Rename existing Pad class (#7384)

This commit is for renaming existing Pad class in moco-tf.

Related: #7357

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[moco-tf] Support Broadcasting (#7378)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 07:09:36 +0000 (16:09 +0900)]
[moco-tf] Support Broadcasting (#7378)

This commit revises canonicalize_eltwise_binary_node to insert proper
boradcasting nodes if necessary.

This change will affect the canonicalization process of TFAdd, TFSub, TFMul, TFDiv.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[exo-tflite] exporting TFLMaxPool2D (#7382)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 07:09:23 +0000 (16:09 +0900)]
[exo-tflite] exporting TFLMaxPool2D (#7382)

Code to export TFLMaxPool2D was added. Since much of this code is duplicated with TFLAveragePool2D, common code was extracted into a separate method.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years agoAdd UNIT_Add_005 TensorFlow testcase (#7379)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 07:08:57 +0000 (16:08 +0900)]
Add UNIT_Add_005 TensorFlow testcase (#7379)

This commit adds UNIT_Add_005 TensorFlow testcase. This test is almost
same as UNIT_Add_001 except that it requires broadcasting over LHS (not RHS).

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[neurun] Rename Scheduler to HEScheduler (#7340)
Дилшоджон Пошшоев/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 11 Sep 2019 07:08:36 +0000 (10:08 +0300)]
[neurun] Rename Scheduler to HEScheduler (#7340)

Since this is a scheduler for heterogeneous execution scheduling,
it must be called appropriately

Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
4 years ago[exo-tflite] Introduce TensorShapeExpander (#7373)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 07:02:06 +0000 (16:02 +0900)]
[exo-tflite] Introduce TensorShapeExpander (#7373)

* [exo-tflite] Introduce TensorShapeExpander

This will introduce TensorShapeExpander in TFLShapeInferenceRule for shape expansion for operations that has broadcasting

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove incs

4 years ago[loco] add alias before renaming pad class (#7377)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 06:31:17 +0000 (15:31 +0900)]
[loco] add alias before renaming pad class (#7377)

This commit is getting ready for renaming pad class.

Related: #7357

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years agoAdd BSD-2-Clause license (#7370)
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 05:44:58 +0000 (14:44 +0900)]
Add BSD-2-Clause license (#7370)

- Add license in nnfw.spec
- Add license text

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
4 years ago[locomotiv] Simplify Element-wise Unary Op Kernels (#7358)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 05:34:54 +0000 (14:34 +0900)]
[locomotiv] Simplify Element-wise Unary Op Kernels (#7358)

* [locomotiv] Simplify Element-wise Unary Op Kernels

This commit rewrites element-wise unary op kernels on top of shared
infrastructure.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix copy-and-paste error

* Fix error message

4 years ago[exo-tflite] Adding ReluConverter test (#7287)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 05:33:50 +0000 (14:33 +0900)]
[exo-tflite] Adding ReluConverter test (#7287)

* [exo-tflite] Adding ReluConverter test

Two test cases were added: loco::relu with tensor input/putput, loco::relu with feature input/output.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remove code that checks knob

* using plan.at(n) instead of bunch of  statements

* using find_first_node_bytype

* no loop, used iterator

4 years ago[exo-tflite] introducing knob for TFLMaxPool2D (#7376)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 05:32:47 +0000 (14:32 +0900)]
[exo-tflite] introducing knob for TFLMaxPool2D (#7376)

This adds knob for TFLMaxPool2D, for backward compatibility reason.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Introduce CanonicalEltwiseInputConnector (#7368)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 05:31:25 +0000 (14:31 +0900)]
[moco-tf] Introduce CanonicalEltwiseInputConnector (#7368)

* [moco-tf] Introduce CanonicalEltwiseInputConnector

This commit introduces CanonicalEltwiseInputConnector which facilitates
pipeline extension.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Use NodeTy

4 years ago[exo-tflite] Adding AvgPool2DConverter (#7317)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 05:29:59 +0000 (14:29 +0900)]
[exo-tflite] Adding AvgPool2DConverter (#7317)

* [exo-tflite] Adding AvgPool2DConverter

AvgPool2DConverter is added, which converts loco::AvgPool2D to locoex::TFLAveragePool2D.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* fix build error

* fix comments

* fix typo

4 years ago[exo-tflite] TypeInference for TFLMaxPool2D (#7350)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 05:29:09 +0000 (14:29 +0900)]
[exo-tflite] TypeInference for TFLMaxPool2D (#7350)

This adds type inference for `TFLMaxPool2D`.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[exo-tflite] shape inference for TFLMaxPool2D (#7374)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 05:28:25 +0000 (14:28 +0900)]
[exo-tflite] shape inference for TFLMaxPool2D (#7374)

Adding shape inference for TFLMaxPool2D

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[logo] Revise test to use make_graph (#7371)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 05:23:33 +0000 (14:23 +0900)]
[logo] Revise test to use make_graph (#7371)

This will revise ConstantFoldingPass test to use make_graph() method instead of using stack value

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[locop] Do NOT show Shape attribute of Pull node (#7338)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 05:04:50 +0000 (14:04 +0900)]
[locop] Do NOT show Shape attribute of Pull node (#7338)

"shape" attribute in Pull node is deprecated.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[exo-tflite] shape inference for TFLAveragePool2D (#7345)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 05:04:37 +0000 (14:04 +0900)]
[exo-tflite] shape inference for TFLAveragePool2D (#7345)

Adding shape inference for TFLAveragePool2D and two test cases.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Introduce Broadcast Helper (#7334)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 05:02:47 +0000 (14:02 +0900)]
[moco-tf] Introduce Broadcast Helper (#7334)

* [moco-tf] Introduce Broadcast Helper

This commit introduces Broadcast Helper module which facilitates
numpy-style broadcasting support.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix a typo

4 years ago[moco-tf] Remove unused CanonicalNodes.lst (#7366)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 03:52:11 +0000 (12:52 +0900)]
[moco-tf] Remove unused CanonicalNodes.lst (#7366)

This will remove not used anymore CanonicalNodes.lst file

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Remove unused NodeShape (#7367)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 03:51:46 +0000 (12:51 +0900)]
[moco-tf] Remove unused NodeShape (#7367)

This will remove not used anymore moco::tf::NodeShape

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Convert for EltwiseAdd (#7353)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 03:34:32 +0000 (12:34 +0900)]
[exo-tflite] Convert for EltwiseAdd (#7353)

This will add converter for canonical EltwiseAdd to TFLAdd

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Type inference for TFLAdd (#7354)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Sep 2019 03:34:05 +0000 (12:34 +0900)]
[exo-tflite] Type inference for TFLAdd (#7354)

This will add type inference for TFLAdd node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[tfinfo] Rename targets (#7369)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 03:33:12 +0000 (12:33 +0900)]
[tfinfo] Rename targets (#7369)

* [tfinfo] Rename targets

This commit renames targets in tfinfo project to have tfinfo as prefix.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix a typo

4 years ago[moco-tf] Introduce canonicalize_eltwise_binary_node (#7327)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Sep 2019 00:44:03 +0000 (09:44 +0900)]
[moco-tf] Introduce canonicalize_eltwise_binary_node (#7327)

* [moco-tf] Introduce canonicalize_eltwise_binary_node

A similar pattern is repeated across several element-wise binary
operation converters.

This commit extracts this pattern as canonicalize_eltwise_binary_node
to reduce code duplication.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Put implementations in anonymous namespace

4 years ago[loco] Remove unused member of FeatureEncodeLayer (#7344)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 00:22:35 +0000 (09:22 +0900)]
[loco] Remove unused member of FeatureEncodeLayer (#7344)

This commit removes unused member '_perm' of FeatureEncodeLayer.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[loco] Add FilterEncodeLayer for test GraphBuilder (#7343)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 11 Sep 2019 00:22:13 +0000 (09:22 +0900)]
[loco] Add FilterEncodeLayer for test GraphBuilder (#7343)

This commit adds FilterEncodeLayer for test GraphBuilder.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[mir] Switch to new `DeConv2DOp` constructor (#7361)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 10 Sep 2019 13:57:28 +0000 (16:57 +0300)]
[mir] Switch to new `DeConv2DOp` constructor (#7361)

Construct `DeConv2DOp` with the new constructor.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe] Switch to new `DeConv2DOp` constructor (#7362)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 10 Sep 2019 13:57:10 +0000 (16:57 +0300)]
[mir_caffe] Switch to new `DeConv2DOp` constructor (#7362)

Construct `DeConv2DOp` with the new constructor.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir] Add a new constructor to `DeConv2DOp` (#7359)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 10 Sep 2019 13:22:24 +0000 (16:22 +0300)]
[mir] Add a new constructor to `DeConv2DOp` (#7359)

All existing constructors miss the "padding after" parameter. They will be replaced with the new one.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[cop, neurun] Use cpu backend by default for custom op (#7346)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 10 Sep 2019 09:54:17 +0000 (18:54 +0900)]
[cop, neurun] Use cpu backend by default for custom op (#7346)

`neurun` uses `acl_cl` backends by default.
However, for custom op, cpu backend will be used by default.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>