platform/core/ml/nnfw.git
4 years ago[moco-tf] Enable canonicalization for Add and Mul (#6096)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 05:44:53 +0000 (14:44 +0900)]
[moco-tf] Enable canonicalization for Add and Mul (#6096)

This will enable Canonicalization for TFAdd and TFMul node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Import Mul node (#6086)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 05:34:14 +0000 (14:34 +0900)]
[moco-tf] Import Mul node (#6086)

* [moco-tf] Import Mul node

This will enable import TensorFlow Mul node as TF dialect TFMul node

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

4 years ago[moco-tf] Import Add node (#6083)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 05:28:10 +0000 (14:28 +0900)]
[moco-tf] Import Add node (#6083)

* [moco-tf] Import Add node

This will enable import TensorFlow Add node as TF dialect TFAdd node

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

4 years ago[moco-tf] Introduce AddCanonicalizer (#6081)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 05:15:37 +0000 (14:15 +0900)]
[moco-tf] Introduce AddCanonicalizer (#6081)

This will introduce Canonicalizier for Add node. Supports only for Elementwise add for now.

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Import as TF dialect (#6091)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 05:10:43 +0000 (14:10 +0900)]
[moco-tf] Import as TF dialect (#6091)

This will change import as TF dialects for AvgPool, MaxPool and Identity

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[locop] Extract NodeSummary (#6076)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 1 Aug 2019 05:10:07 +0000 (14:10 +0900)]
[locop] Extract NodeSummary (#6076)

This commit introduces a dedicated header/source file for NodeSummary class.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[loco] Introduce NodeShape class (#6078)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 1 Aug 2019 05:09:20 +0000 (14:09 +0900)]
[loco] Introduce NodeShape class (#6078)

* [loco] Introduce NodeShape class

This commit introduces NodeShape class which serves as a variant over
various Shape classes.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix bugs and add tests

4 years ago[locomotiv] execution for elementwise add (#6079)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 05:01:12 +0000 (14:01 +0900)]
[locomotiv] execution for elementwise add (#6079)

* [locomotiv] execution for elementwise add

This will introduce execution for EltwiseAdd node

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

* remove using namespace

* check if same domain not tensor

4 years ago[moco-tf] Introduce MulCanonicalizer (#6082)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 04:21:40 +0000 (13:21 +0900)]
[moco-tf] Introduce MulCanonicalizer (#6082)

This will introduce Canonicalizer for Mul node. Supports only for Elementwise mul for now.

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Simplify TFFormattedGraph using pepper::str (#6080)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 1 Aug 2019 04:08:46 +0000 (13:08 +0900)]
[moco-tf] Simplify TFFormattedGraph using pepper::str (#6080)

This commit simplifies TFFormattedGraph implementation using
"pepper::str" helper.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] use plier method (#6090)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 04:07:48 +0000 (13:07 +0900)]
[moco-tf] use plier method (#6090)

This will fix to use plier method from old internal method

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Import as TFMaxPool with a knob (#6043)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 03:34:50 +0000 (12:34 +0900)]
[moco-tf] Import as TFMaxPool with a knob (#6043)

* [moco-tf] Import as TFMaxPool with a knob

This will revise import to load MaxPool node as TFMaxPool with a knob

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* use plier and rename variable

4 years ago[tf2tflite] Schema for additional info of Custom Op from user (#5939)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 03:34:33 +0000 (12:34 +0900)]
[tf2tflite] Schema for additional info of Custom Op from user (#5939)

* [tf2tflite] Schema for additional info of Custom Op from user

This is a schema for additional info of Custom Op from user.
It was committed into _moco-tf_ but moved to here.
The name was renamed to CompileInfo.pbtxt (Previous name was Model.MetaInfo.pbtxt), which seems more friendlier. :-)

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* renaming CompileInfo to CustomInfo && move ./proto/CMakeFiles.txt to ./CMakeFiles.txt

* modify DT_INT32 to 15

4 years ago[exo/tflite] prevent ceil_div function from overflow (#6088)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 1 Aug 2019 03:34:16 +0000 (03:34 +0000)]
[exo/tflite] prevent ceil_div function from overflow (#6088)

This commit prevents ceil_div function from overflow.

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[moco-tf] Logging with TFNodeSummaryBuilderFactory (#6064)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 03:25:48 +0000 (12:25 +0900)]
[moco-tf] Logging with TFNodeSummaryBuilderFactory (#6064)

TFNodeSummaryBuilderFactory is used to print all nodes (including unlinked TFNodes)

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years agoIntroduce PermuteFactor into LowerInfo of operation (#6028)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 1 Aug 2019 02:30:32 +0000 (11:30 +0900)]
Introduce PermuteFactor into LowerInfo of operation (#6028)

This commit introduces PermuteFactor into LowerInfo of operation.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years agoRefactor Backend to support sessions (#5894)
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 1 Aug 2019 02:29:58 +0000 (11:29 +0900)]
Refactor Backend to support sessions (#5894)

Backend had been only one object there cannot be more than one session.
This commit introduces `BackendContext` which depends on a specific
model and `Backend` object represents the backend itself(a singleton).

Resolve #5723

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
4 years ago[moco/tf] Introduce DepthwiseConv2D Canonicalizer (#6047)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 1 Aug 2019 01:50:47 +0000 (01:50 +0000)]
[moco/tf] Introduce DepthwiseConv2D Canonicalizer (#6047)

* [moco/tf] Introduce DepthwiseConv2D Canonicalizer

This commit introcude DepthwiseConv2D Canonicalizer to moco-tf.

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* apply comment.

* add codes for log.

4 years ago[moco-tf] Fix build break (#6087)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 1 Aug 2019 01:45:06 +0000 (10:45 +0900)]
[moco-tf] Fix build break (#6087)

This commit fixes build break related with API deisgn changes.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Add a complex test case into ConstantFoldingTransform (#5936)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 01:37:38 +0000 (10:37 +0900)]
[moco-tf] Add a complex test case into ConstantFoldingTransform (#5936)

* [moco-tf] Add a complex test case into ConstantFoldingTransform

This commit adds a complex test case into ConstantFoldingTransform

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* using TFNodeSummerBuilderFactory

4 years ago[moco-tf] Transform to resolve wildcard dimesion of TFReshape (#6019)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 1 Aug 2019 01:36:01 +0000 (10:36 +0900)]
[moco-tf] Transform to resolve wildcard dimesion of TFReshape (#6019)

* [moco-tf] Transform to resolve wildcard dimesion of TFReshape

This commit introduces ResolveReshapeWildcardDim transform, which tries
to resolve wildcard dimension of TFReshape.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Clarify by docs and function name

4 years ago[res] Add small network test case for ResolveReshapeWildcardDim (#6020)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 1 Aug 2019 01:35:26 +0000 (10:35 +0900)]
[res] Add small network test case for ResolveReshapeWildcardDim (#6020)

* [res] Add small network test case for ResolveReshapeWildcardDim

This commit adds small network test case for ResolveReshapeWildcardDim.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Edit brief description

4 years ago[moco-tf] Remove functions in Convert.h that were moved to plier-tf (#5935)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 01:11:29 +0000 (10:11 +0900)]
[moco-tf] Remove functions in Convert.h that were moved to plier-tf (#5935)

* [moco-tf] Remove functions in Convert.h that were moved to plier-tf

This commit removes functions in Convert.h that were moved to plier-tf.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remaining asDataLayout

* remove unused header

4 years ago[moco-tf] Adding more methods into ModelSignature (#5897)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 1 Aug 2019 00:04:45 +0000 (09:04 +0900)]
[moco-tf] Adding more methods into ModelSignature (#5897)

* [moco-tf] Adding more methods into ModelSignature

This commit adds more methods into ModelSignature to make info from users (regarding custom op) be stored.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* format checked

* use angkor::TensorShape

* renaming customop(..) -> add_customop(..) && Fix comment

4 years ago[loco] Add BiasShape class (#6060)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 31 Jul 2019 23:48:16 +0000 (08:48 +0900)]
[loco] Add BiasShape class (#6060)

This commit adds BiasShape class which records the length of bias
values.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[loco] Introduce EltwiseMul IR (#6055)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Jul 2019 23:33:01 +0000 (08:33 +0900)]
[loco] Introduce EltwiseMul IR (#6055)

This will introduce EltwiseMul IR for Elementwise Multiply operation

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Support TFMaxPool for Logging (#6054)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Jul 2019 23:32:38 +0000 (08:32 +0900)]
[moco-tf] Support TFMaxPool for Logging (#6054)

This will add TFMaxPool for TFNodeSummaryBuilder this dump of graph shows TFMaxPool attributes

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Update readme (#5870)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Jul 2019 23:29:31 +0000 (08:29 +0900)]
[moco-tf] Update readme (#5870)

* [moco-tf] Update readme

This will update README.md file of moco-tf project

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

* use requires.cmake

4 years ago[moco-tf] Canonicalize MaxPool (#6046)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Jul 2019 22:32:57 +0000 (07:32 +0900)]
[moco-tf] Canonicalize MaxPool (#6046)

This will enable Canonicalization of MaxPool node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years agoFix not consistent input order in concat op (#6067)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 31 Jul 2019 13:45:33 +0000 (16:45 +0300)]
Fix not consistent input order in concat op (#6067)

* Fixed asserts using check what it is Pull nodes

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years agoACL NEON Div Node (#5948)
Nikita Sizov/AI Tools Lab /SRR/Professional/삼성전자 [Wed, 31 Jul 2019 10:07:29 +0000 (13:07 +0300)]
ACL NEON Div Node (#5948)

Add support of DivNode for ACL NEON

Signed-off-by: Sizov Nikita <n.sizov@samsung.com>
4 years agoSupport Concat operation transformation from mir to loco (#5903)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 31 Jul 2019 08:58:17 +0000 (11:58 +0300)]
Support Concat operation transformation from mir to loco (#5903)

* Transform ConcatOp to TensorConcat

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[mir2loco] Support Relu operation (#5793)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 31 Jul 2019 08:56:42 +0000 (11:56 +0300)]
[mir2loco] Support Relu operation (#5793)

* Support Relu operation transformation
* Append test for Relu

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[plier-tf] Moving moco test cases regarding data_layout (#6061)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Jul 2019 07:51:07 +0000 (16:51 +0900)]
[plier-tf] Moving moco test cases regarding data_layout (#6061)

Test cases of moco were moved into plier.
These test cases are for two methods that were moved lately from moco to plier.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[pepper-str] Initial commit (#6056)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 31 Jul 2019 07:43:29 +0000 (16:43 +0900)]
[pepper-str] Initial commit (#6056)

This commit adds pepper-str module. "pepper-str" provides "str" helper
which allows users to simulate string interpolation in C++.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] TFReshape Canonicalization (#6005)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 31 Jul 2019 07:34:13 +0000 (16:34 +0900)]
[moco-tf] TFReshape Canonicalization (#6005)

* [moco-tf] TFReshape Canonicalization

This commit implements Canonicalization for TFReshape. Currently it only
supports fixed reshape case.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* TODO comment to support loco ConstGen node

4 years agoFix invalid params of CLTransposeConv (#6057)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 31 Jul 2019 06:56:29 +0000 (15:56 +0900)]
Fix invalid params of CLTransposeConv (#6057)

This commit fixes invalid params of CLTansposeConv.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[loco] Use data type attribute in Graph-level input (#5999)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 31 Jul 2019 06:33:31 +0000 (15:33 +0900)]
[loco] Use data type attribute in Graph-level input (#5999)

This commit revises "Pull" node implementation to use Graph-level
"dtype" attribute.

This commit includes some workaround not to impact the current clients.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[neurun] Rename "make_subgraph" helper (#6042)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 31 Jul 2019 06:19:51 +0000 (15:19 +0900)]
[neurun] Rename "make_subgraph" helper (#6042)

Graph::lower internally declares "make_subgraph", but its role is more
than subgraph construction.

This commit renames "make_subgraph" as "append_fresh_single_op_subgraph"
to make it easy to understand its behavior.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Support TFAvgPool for Logging (#6045)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Jul 2019 01:20:40 +0000 (10:20 +0900)]
[moco-tf] Support TFAvgPool for Logging (#6045)

This will add TFAvgPool for TFNodeSummaryBuilder thus dump of graph shows TFAvgPool attributes

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Canonicalizer for MaxPool (#6027)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Jul 2019 00:41:36 +0000 (09:41 +0900)]
[moco-tf] Canonicalizer for MaxPool (#6027)

This will introduce MaxPoolCanonicalizer to canonicalize MaxPool node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[loco] Introduce EltwiseAdd IR (#6026)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Jul 2019 00:30:12 +0000 (09:30 +0900)]
[loco] Introduce EltwiseAdd IR (#6026)

* [loco] Introduce EltwiseAdd IR

This will introduce EltwiseAdd IR for Elementwise Add operation

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* use lhs, rhs

* remove Tensor in comment

4 years agoDR1 Detailed level documentation (#5896)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Wed, 31 Jul 2019 00:00:50 +0000 (03:00 +0300)]
DR1 Detailed level documentation (#5896)

* DR1 Detailed level documentation

Add detailed level documentation for DR1 milestone

* update 2019 goals
* initial structure description
* add compiler flow
* add description of components including compiler and runtime
* add description to high level directories, and add line breaks
* remove redundant data, fix references
* fix typos and wording
* DR1 DLD SE member in-charge review and fixes
  - Expanded OSS pre-review table with new columns
  - Added SW Code Structure using `tree` tool
  - Updated Revision history and Table of contents

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
4 years agoDR1 sw requirement document fixes (#5992)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Tue, 30 Jul 2019 23:53:55 +0000 (02:53 +0300)]
DR1 sw requirement document fixes (#5992)

* DR1 sw requirement document fixes

- Fix sw requirement document number version
- Fixed non-function requirements numeration

Signed-off-by: Aleksei Kondrashov <a.kondrashov@partner.samsung.com>
4 years agoAdd High Level Documentation (#5665)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Tue, 30 Jul 2019 23:51:05 +0000 (02:51 +0300)]
Add High Level Documentation (#5665)

* Add High Level Documentation

- Added image of overall architecture of project
- Added image with data flow through the pipeline
- Added Core Structure component
- Added and mapped non-functional requirements
- Updated revision history

* add overview of components
* add initial version of API secton
* add IR description
* add runtime behavior
* add structural description of IRs
* add compiler structure and behavioral description
* add structure diagram about nn runtime
* add constraints and scope items
* add Traceability Matrix
* add table of contents and items required by template
* add description about gray and white modules on component diagram
* update images to eliminate ambiguous interpretation
* change heading, rename nn Compute component
* break sections in more items
* bring back nnapi part
* rename NNFW IR into neurun IR and fix naming of other components
* fix formatting of subsystem description & abbreviations
* remove redundant item from compiler description
* fix typos and wording

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
4 years ago[moco-tf] Fix shape for TFMaxPool (#6025)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 30 Jul 2019 23:39:48 +0000 (08:39 +0900)]
[moco-tf] Fix shape for TFMaxPool (#6025)

This will implement FixShape for TFMaxPool node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Fix pad for TFMaxPool (#6023)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 30 Jul 2019 22:17:27 +0000 (07:17 +0900)]
[moco-tf] Fix pad for TFMaxPool (#6023)

This will implement FixPad for TFMaxPool node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[mir] Add support for 0-dimensional tensors (#6039)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 30 Jul 2019 19:19:11 +0000 (22:19 +0300)]
[mir] Add support for 0-dimensional tensors (#6039)

Fixes compilation error of SuperResolution and StyleTransfer networks.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir/TFLite importer] Cleanup after changing interface (#6036)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 30 Jul 2019 19:11:39 +0000 (22:11 +0300)]
[mir/TFLite importer] Cleanup after changing interface (#6036)

* Remove `cleanup` method.
* Move `import` and `createIR` methods into private section.
* Use `make_unique` to deal with `unique_ptr`s.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir/ONNX importer] Cleanup after changing interface (#6035)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 30 Jul 2019 19:11:08 +0000 (22:11 +0300)]
[mir/ONNX importer] Cleanup after changing interface (#6035)

* Move `import` and `createIR` methods into private section.
* Use `make_unique` to deal with `unique_ptr`s.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir/Caffe importer] Cleanup after changing interface (#6034)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 30 Jul 2019 19:10:36 +0000 (22:10 +0300)]
[mir/Caffe importer] Cleanup after changing interface (#6034)

* Remove `cleanup` method.
* Move `import` and `createIR` methods into private section.
* Use `make_unique` to deal with `unique_ptr`s.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir/Caffe2 importer] Cleanup after changing interface (#6033)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 30 Jul 2019 19:10:10 +0000 (22:10 +0300)]
[mir/Caffe2 importer] Cleanup after changing interface (#6033)

* Remove `cleanup` method.
* Move `import` and `createIR` methods into private section.
* Use `make_unique` to deal with `unique_ptr`s.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years agoFix format script diff file only (#6007)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Jul 2019 11:49:11 +0000 (20:49 +0900)]
Fix format script diff file only (#6007)

To get correct updated files when master is update after branch out, count new commits after branch out from master and compare with branch out commit

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[neurun] Introduce "simple" Subgraph emplace method (#6000)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Jul 2019 11:48:41 +0000 (20:48 +0900)]
[neurun] Introduce "simple" Subgraph emplace method (#6000)

This commit introduces "simple" Subgraph empalce method which does not
allocate a Subgraph internally but requires clients to allocate it
instead.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[neurun] Code refactoring of Scheduler::makeRank (#5881)
Дилшоджон Умронхонович Пошшоев/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 30 Jul 2019 11:48:05 +0000 (14:48 +0300)]
[neurun] Code refactoring of Scheduler::makeRank (#5881)

Split Scheduler::makeRank into smaller ones

Signed-off-by: Dilshodzhon Poshshoev <d.poshshoev@samsung.com>
4 years ago[moco-tf] ResolveFusedBatchNorm unit test to generate proper log (#6024)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 30 Jul 2019 10:07:41 +0000 (19:07 +0900)]
[moco-tf] ResolveFusedBatchNorm unit test to generate proper log (#6024)

Previously unit test for ResolveFusedBatchNorm printed unknown node
fallback logging. This commit fixes this bug to print proper format
defined by moco-tf.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[moco/tf] Import TFDepthwiseConv2d Op (#6001)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 30 Jul 2019 10:06:22 +0000 (10:06 +0000)]
[moco/tf] Import TFDepthwiseConv2d Op (#6001)

* [moco/tf] Import TFDepthwiseConv2d Op

This commit is for importing TFDepthwiseConv2d Op.

Signed-off-by: seongwoo sw4670.chae@samsung.com
* This commit makes tensor_content of pbtxt human-readable.

4 years ago[nnc] Use `importModel` methods instead of `import`, `createIR` and `cleanup` (#5990)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 30 Jul 2019 09:37:18 +0000 (12:37 +0300)]
[nnc] Use `importModel` methods instead of `import`, `createIR` and `cleanup` (#5990)

Replace uses of `import`, `createIR` and `cleanup` with newly introduced `importModel`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago DR1 test document (#5890)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Tue, 30 Jul 2019 09:18:30 +0000 (12:18 +0300)]
 DR1 test document (#5890)

* DR1 test document

- Introduced STD for DR1 milestone
- According to new requirements new tests are added

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
4 years agoFix bug in ExecInstance (#6017)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Jul 2019 08:52:30 +0000 (17:52 +0900)]
Fix bug in ExecInstance (#6017)

Delete compiler generated by new
Fix typo input buffer name in twoThreads test

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years agoReplace pylint command (#6002)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Jul 2019 08:51:45 +0000 (17:51 +0900)]
Replace pylint command (#6002)

Replace infra/nnfw/command/pylint command into infra/command

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years agoACL NEON Comparison Node (#5951)
Nikita Sizov/AI Tools Lab /SRR/Professional/삼성전자 [Tue, 30 Jul 2019 08:03:28 +0000 (11:03 +0300)]
ACL NEON Comparison Node (#5951)

Add support of ComparisonNode for ACL NEON

Signed-off-by: Sizov Nikita <n.sizov@samsung.com>
4 years agoACL NEON SqueezeNode (#5944)
Nikita Sizov/AI Tools Lab /SRR/Professional/삼성전자 [Tue, 30 Jul 2019 08:01:25 +0000 (11:01 +0300)]
ACL NEON SqueezeNode (#5944)

Add support of SqueezeNode for ACL NEON

Signed-off-by: Sizov Nikita <n.sizov@samsung.com>
4 years ago[moco-tf] Reshape shape inference rejects dynamic case (#6013)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 30 Jul 2019 07:55:32 +0000 (16:55 +0900)]
[moco-tf] Reshape shape inference rejects dynamic case (#6013)

Previously shape inference stage for TFReshape node was erroneously
done for wildcard dimension as well. This commit fixes this bug to
reject dynamic reshape case.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years agoTranspose convolution valid padding test (#5998)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Jul 2019 07:52:30 +0000 (16:52 +0900)]
Transpose convolution valid padding test (#5998)

* Transpose convolution valid padding test

- Add transpose convolution valid padding test
- Fix bug transpoe valid padding
- Update comment

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Update comment

4 years agoFix goals for 2019 (#5994)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Tue, 30 Jul 2019 07:27:14 +0000 (10:27 +0300)]
Fix goals for 2019 (#5994)

Fix goals for 2019 in SRS and SDD documents

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
4 years agoAdd gtest to prepare multithread execution instance (#5898)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Jul 2019 07:21:41 +0000 (16:21 +0900)]
Add gtest to prepare multithread execution instance (#5898)

Introduce gtest to prepare multithread execution instance using one executor

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[moco-tf] Replace assert in FuseBinaryIntoPreceding (#6009)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 30 Jul 2019 07:20:32 +0000 (16:20 +0900)]
[moco-tf] Replace assert in FuseBinaryIntoPreceding (#6009)

This will replace assert with a log for unknown as it is now know case and can be handled by other transforms

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[neurun] Remove hiding _indexed_ranks from Dataflow (#5926)
Дилшоджон Умронхонович Пошшоев/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 30 Jul 2019 06:46:01 +0000 (09:46 +0300)]
[neurun] Remove hiding _indexed_ranks from Dataflow (#5926)

_indexed_ranks is a protected member in both ExecutorBase and Dataflow.
ExecutorBase::setIndexedRanks() sets ExecutorBase::_indexed_ranks,
but methods in Dataflow uses Dataflow::_indexed_ranks and is always nullptr

Signed-off-by: Dilshodzhon Poshshoev <d.poshshoev@samsung.com>
4 years ago[moco-tf] Import as TFAvgPool with a knob (#6006)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 30 Jul 2019 06:18:07 +0000 (15:18 +0900)]
[moco-tf] Import as TFAvgPool with a knob (#6006)

This will add a Knob to import AvgPool node as TFAvgPool or AvgPool2D

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco/tf] DepthwiseConv2D FixShapeTransform bug fix. (#6003)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 30 Jul 2019 04:52:46 +0000 (04:52 +0000)]
[moco/tf] DepthwiseConv2D FixShapeTransform bug fix. (#6003)

It needs to be modified for getting right stride data.

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[neurun] Enable {CL|NE}DepthwiseConvolutionLayer3x3 on KernelGenerator (#6008)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 30 Jul 2019 04:40:52 +0000 (13:40 +0900)]
[neurun] Enable {CL|NE}DepthwiseConvolutionLayer3x3 on KernelGenerator (#6008)

Enable {CL|NE}DepthwiseConvolutionLayer3x3 on each KernelGenerator. The
only CLDepthwiseConvolutionLayer3x3 has the parameter for the internal
buffer memory manager.

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[moco/tf] Add TFNodeSummaryBuilder for DepthwiseConv2dNative (#6004)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 30 Jul 2019 04:33:59 +0000 (04:33 +0000)]
[moco/tf] Add TFNodeSummaryBuilder for DepthwiseConv2dNative (#6004)

This commit adds a TFNodeSummaryBuilder for DepthwiseConv2dNative.

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
4 years ago[neurun] Enable AclLinearMemoryManager on LinearExecutor (#5922)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 30 Jul 2019 04:07:41 +0000 (13:07 +0900)]
[neurun] Enable AclLinearMemoryManager on LinearExecutor (#5922)

Enable AclLinearMemoryManager to acl_cl and acl_neon  on LinearExecutor

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[moco-tf] Fix shape and pad for TFAvgPool (#5996)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 30 Jul 2019 03:43:35 +0000 (12:43 +0900)]
[moco-tf] Fix shape and pad for TFAvgPool (#5996)

This will implement FixShape and FixPadding for TFAvgPool node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[neurun] Fix preVisit/postVisit for double-concats (#5977)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 30 Jul 2019 03:36:57 +0000 (12:36 +0900)]
[neurun] Fix preVisit/postVisit for double-concats (#5977)

* [neurun] Fix preVisit/postVisit for double-concats

Fix preVisit and postVisit of TemplTensorBuilder to pass
double-concats(two consecutive concats) of
inception_v3_2018_04_27.tflite

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Fix comment

4 years agoMark NNPACK as NOT FOUND if PeachpySource is missing (#5995)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Jul 2019 01:21:19 +0000 (10:21 +0900)]
Mark NNPACK as NOT FOUND if PeachpySource is missing (#5995)

The current implement says that NNPACK is available even though
PeachpySource is missing.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years agoSet PeachpySource as NOT FOUND on failure (#5966)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Jul 2019 00:38:01 +0000 (09:38 +0900)]
Set PeachpySource as NOT FOUND on failure (#5966)

The current implementation of PeachpySource package reports SUCCESS
even when source code generation fails.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Revise importer test (#5960)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 30 Jul 2019 00:18:00 +0000 (09:18 +0900)]
[moco-tf] Revise importer test (#5960)

This will revise importer test to do test with TFIdentity IR that uses Identity node as a test material

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Move vector<int64_t> streamout to LogHelper (#5981)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 29 Jul 2019 23:31:35 +0000 (08:31 +0900)]
[moco-tf] Move vector<int64_t> streamout to LogHelper (#5981)

This will move vector<int64_t> streamout of TFFormattedGraph to LogHelper

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Import Reshape operation as TF dialect (#5976)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 29 Jul 2019 22:24:54 +0000 (07:24 +0900)]
[moco-tf] Import Reshape operation as TF dialect (#5976)

This commit implements import stage of tensorflow Reshape operation to
TFReshape node.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[moco-tf] Introduce as_tensor_shape with FeatureShape (#5973)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 29 Jul 2019 22:22:42 +0000 (07:22 +0900)]
[moco-tf] Introduce as_tensor_shape with FeatureShape (#5973)

This will introduce ShapeInferenceData helper to set as TensorShape with FeatureShape and TFDataLayout

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years agoFix #5978 (#5989)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 29 Jul 2019 17:41:13 +0000 (20:41 +0300)]
Fix #5978 (#5989)

Adjust tests to take into account recent changes in compiler passes.
Fixes #5978.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[mir/Caffe importer] Introduce `importModel` method (#5986)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 29 Jul 2019 17:37:38 +0000 (20:37 +0300)]
[mir/Caffe importer] Introduce `importModel` method (#5986)

Add `importModel` method as a future replacement for `import` and `createIR` methods.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[neurun] Add fine for scheduling into another backend (#5880)
Дилшоджон Умронхонович Пошшоев/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 29 Jul 2019 12:54:11 +0000 (15:54 +0300)]
[neurun] Add fine for scheduling into another backend (#5880)

Assigning to another backend will cause creating a subgraph:
one for permutation and one more if it was mergable node
if the same backend was assigned

Signed-off-by: Dilshodzhon Poshshoev <d.poshshoev@samsung.com>
5 years ago[mir/TFLite importer] Introduce `importModel` method (#5988)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 29 Jul 2019 12:49:06 +0000 (15:49 +0300)]
[mir/TFLite importer] Introduce `importModel` method (#5988)

Add `importModel` method as a future replacement for `import` and `createIR` methods.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[mir/ONNX importer] Introduce `importModel` method (#5987)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 29 Jul 2019 12:48:45 +0000 (15:48 +0300)]
[mir/ONNX importer] Introduce `importModel` method (#5987)

Add `importModel` method as a future replacement for `import` and `createIR` methods.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[mir/Caffe2 importer] Introduce `importModel` method (#5985)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 29 Jul 2019 12:48:17 +0000 (15:48 +0300)]
[mir/Caffe2 importer] Introduce `importModel` method (#5985)

Add `importModel` method as a future replacement for `import` and `createIR` methods.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[neurun] Add custom kernel registry (#5597)
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 29 Jul 2019 12:43:24 +0000 (15:43 +0300)]
[neurun] Add custom kernel registry (#5597)

Add custom kernel registry used to keep track of custom kernels used by specific backend( see #5411 )

Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
5 years ago[nnc] Join `import` and `createIR` methods into `importModel` (#5984)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 29 Jul 2019 11:35:55 +0000 (14:35 +0300)]
[nnc] Join `import` and `createIR` methods into `importModel` (#5984)

Methods `import` and `createIR` are always used together. Join them to simplify usage.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years agoFix unmatched result of tconv in NCHW (#5968)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 29 Jul 2019 11:30:43 +0000 (20:30 +0900)]
Fix unmatched result of tconv in NCHW (#5968)

This commit fixes unmatched result of tconv in NCHW
  - Change weights of tconv to OIHW in case of NCHW

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
5 years ago[moco-tf] Summary for TFReshape node (#5979)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 29 Jul 2019 11:16:12 +0000 (20:16 +0900)]
[moco-tf] Summary for TFReshape node (#5979)

This commit adds summary for TFReshape node

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[moco-tf] Enable AvgPoolCanonicalizer (#5980)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 29 Jul 2019 11:15:43 +0000 (20:15 +0900)]
[moco-tf] Enable AvgPoolCanonicalizer (#5980)

This will add AvgPoolCanonicalizer to Canonicalizer list

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[loco] Introduce const Graph getters (#5974)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 29 Jul 2019 11:13:41 +0000 (20:13 +0900)]
[loco] Introduce const Graph getters (#5974)

Now, Graph provides const "nodes", "inputs", "outputs" methods.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco] Remove unused input_nodes helper (#5972)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 29 Jul 2019 11:13:31 +0000 (20:13 +0900)]
[loco] Remove unused input_nodes helper (#5972)

* [loco] Remove unused input_nodes helper

This commit removes unused input_nodes helper. This helper is currently
unused, but its presence makes it difficult to decouple loco core from
loco canonical.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Remove the implementation

5 years ago[loco] Input/Output Index from Push/Pull node (#5961)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 29 Jul 2019 11:13:19 +0000 (20:13 +0900)]
[loco] Input/Output Index from Push/Pull node (#5961)

* [loco] Input/Output Index from Push/Pull node

This commit revises Push/Pull node to store associated Graph-level
Input/Output index in it.

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

5 years ago[moco-tf] Introduce TFMaxPool IR (#5975)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 29 Jul 2019 06:21:05 +0000 (15:21 +0900)]
[moco-tf] Introduce TFMaxPool IR (#5975)

This will introduce TFMaxPool IR in TensorFlow Dialect for MaxPool node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[neurun] Always notify ExecutionObserver (#5958)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 29 Jul 2019 06:12:12 +0000 (15:12 +0900)]
[neurun] Always notify ExecutionObserver (#5958)

Now, DataflowExecutor notifies the beginning and end of the whole
execution whenever any observer exists (even when profiling mode is
disabled).

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoFix format error in moco-tf (#5970)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 29 Jul 2019 05:38:30 +0000 (14:38 +0900)]
Fix format error in moco-tf (#5970)

Fix format error in moco-tf's FixShapeTransform.cpp

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[moco/tf] Introduce TFDepthwiseConv2D IR. (#5912)
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 29 Jul 2019 05:12:18 +0000 (05:12 +0000)]
[moco/tf] Introduce TFDepthwiseConv2D IR. (#5912)

* [moco/tf] Introduce TFDepthwiseConv2D IR.

This commit introduce TFDepthwiseConv2D IR.

Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* apply 'Native' keyword.