platform/core/ml/nnfw.git
4 years agoRevise acl common cmake (#6340)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 00:45:46 +0000 (09:45 +0900)]
Revise acl common cmake (#6340)

- Add strict build option: nnfw_common
- Link arm_compute and arm_compute_ex library
- Include path acl_common for acl_common user (acl_cl, acl_neon)

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years agoMerge neurun kernel and backend build (#6313)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Aug 2019 00:45:27 +0000 (09:45 +0900)]
Merge neurun kernel and backend build (#6313)

- Merge neurun each backend's kernel and backend build
- Fix build error on cpu backend kernel by restrict build option
  - Invalid type comparison
  - Unused variable
  - Unused function

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[locop] FixedReshape node summary (#6354)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 8 Aug 2019 00:22:43 +0000 (09:22 +0900)]
[locop] FixedReshape node summary (#6354)

This commit adds FixedReshape node summary.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[moco-tf] Use common calc_paddata in FixShape (#6346)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 22:01:57 +0000 (07:01 +0900)]
[moco-tf] Use common calc_paddata in FixShape (#6346)

This will change calc_node_pad() and calc_annot_paddata() to use common calc_annot_paddata() in FixShapeTransform

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[nnc] Replace BiasAdd and Scale with elementwise equivalents (#6358)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 7 Aug 2019 15:08:48 +0000 (18:08 +0300)]
[nnc] Replace BiasAdd and Scale with elementwise equivalents (#6358)

`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years agoRemove TensorBuilder getter from IKernelGenerator (#6331)
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 7 Aug 2019 12:23:12 +0000 (21:23 +0900)]
Remove TensorBuilder getter from IKernelGenerator (#6331)

Now that `Backend` holds `TensorBuilder` directly, no need to have this
interface from `IkernelGenerator` any longer.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
4 years ago[mir] Add binary elementwise operations (#6351)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 7 Aug 2019 12:04:29 +0000 (15:04 +0300)]
[mir] Add binary elementwise operations (#6351)

first step of future replacement of single `ElementwiseOp` class with set of individual operations.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[moco-tf] Introduce TFConcatV2 IR (#6321)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 09:56:12 +0000 (18:56 +0900)]
[moco-tf] Introduce TFConcatV2 IR (#6321)

This will introduce TFConcatV2 IR and required codes for TensorFlow Concat node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years agoSupport asynchronous execution (#6314)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 09:44:42 +0000 (18:44 +0900)]
Support asynchronous execution (#6314)

- Introduce methods for start execution & wait finish in Execution class to support asynchronous execution
- Add test using introduced methods

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[tf2tflite] copying customop.conf into cmake build/compiler/tf2tflite (#6329)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 09:21:33 +0000 (18:21 +0900)]
[tf2tflite] copying customop.conf into cmake build/compiler/tf2tflite (#6329)

* [tf2tflite] copying customop.conf into cmake build/compiler/tf2tflite

This makes cmake to copy customop.conf into cmake build/compiler/tf2tflite.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* indent, 'xxx_customop.conf' -> 'xxx.customop.conf'

4 years ago[exo-tflite] Implement FilterShape converter (#6334)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 09:21:13 +0000 (18:21 +0900)]
[exo-tflite] Implement FilterShape converter (#6334)

This commit implement a helper which converts FilterShape as exo-tflite
internal ShapeDescription.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Remove redundant codes in FuseBinaryIntoPreceding (#6319)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 7 Aug 2019 09:14:16 +0000 (18:14 +0900)]
[moco-tf] Remove redundant codes in FuseBinaryIntoPreceding (#6319)

* [moco-tf] Remove redundant codes in FuseBinaryIntoPreceding

There are some redundant codes in `FuseBinaryIntoPreceding.cpp`
This commit will remove them.
- Exactly only one of variables(`xc` and `yc`) is `nullptr` because `is_only_one_valid` already checks.
- Then `addparam` and `mulparam` cannot be `nullptr`.
- After removing above condition, there can be only one case that `bchanged` can be returned, that is when `biasadd` is `nullptr`. However when `biasadd` is `nullptr`, bchanged is always `false`.

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

* add missing codes

* fix comments

* apply comments

4 years ago[moco-tf] Common method for calculation of PadData (#6338)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 09:10:30 +0000 (18:10 +0900)]
[moco-tf] Common method for calculation of PadData (#6338)

This will introduce common method for calculation of PadData that exist in calc_node_pad() and calc_annot_paddata() of FixShapeTransform

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[loco] Introduce GraphBuilder helper class (#6308)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 08:22:09 +0000 (17:22 +0900)]
[loco] Introduce GraphBuilder helper class (#6308)

* [loco] Introduce GraphBuilder helper class

This commit introduces GraphBuilder helper class which faciliates
testcase implementation.

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

4 years ago[loco] TensorConcat Shape Inference (#6315)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 08:18:58 +0000 (17:18 +0900)]
[loco] TensorConcat Shape Inference (#6315)

* [loco] TensorConcat Shape Inference

CanonicalShapeInferenceRule is now able to infer the shape of  TensorConcat
nodes.

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

4 years ago[moco-tf] Deprecate FixPaddingTransform (#6335)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 08:18:46 +0000 (17:18 +0900)]
[moco-tf] Deprecate FixPaddingTransform (#6335)

This will remove using FixPaddingTransform.

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years agoRename pacl build script (#6336)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 08:11:06 +0000 (17:11 +0900)]
Rename pacl build script (#6336)

Rename pacl build script: suffix pacl
Rename to avoid default runtime confusion
Update build introduction document

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[tf2tflite] Modified as CustomOp.info renamed to customop.conf (#6328)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 07:53:50 +0000 (16:53 +0900)]
[tf2tflite] Modified as CustomOp.info renamed to customop.conf (#6328)

CMakeLists.txt file was modified as CustomOp.info renamed to customop.conf.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Fix pad for TF dialect nodes in FixShape (#6302)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 06:42:17 +0000 (15:42 +0900)]
[moco-tf] Fix pad for TF dialect nodes in FixShape (#6302)

This will merge fix pad for TF dialect nodes in FixShapeInference using calc_annot_paddata() method

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Use calc_annot_paddata for fix pad of TF dialect nods (#6301)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 06:41:48 +0000 (15:41 +0900)]
[moco-tf] Use calc_annot_paddata for fix pad of TF dialect nods (#6301)

This will change to use calc_annot_paddata() method to fix pad in FixShapeInference for TFAvgPool node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[tf2tflite] driver can takes customop.conf as param (#6272)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 06:39:22 +0000 (15:39 +0900)]
[tf2tflite] driver can takes customop.conf as param (#6272)

* [tf2tflite] driver can takes customop.conf as param

This commit enable Driver to take customop.conf as the 5th param.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* optional param: '--customop <customop.conf path>'

* remove strcmp, parse conf before calling import

* nyi error

4 years ago[exo-tflite] Exporting Operator Code table including code of custom op (#6323)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 06:38:31 +0000 (15:38 +0900)]
[exo-tflite] Exporting Operator Code table including code of custom op (#6323)

Now when tflite opcode table is created, name and code for custom op is included.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[exo-tflite] type inferencing including custom op (#6320)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 05:52:28 +0000 (14:52 +0900)]
[exo-tflite] type inferencing including custom op (#6320)

This commit enables exo-tflite to infer type canonical nodes as well as custop op.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[tf2tflite] Enable test RealDiv and Sub (#6325)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 05:41:48 +0000 (14:41 +0900)]
[tf2tflite] Enable test RealDiv and Sub (#6325)

This will enable tf2tflite test of RealDiv and Sub

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[mocotest-tf] Enable RealDiv and Sub test (#6324)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 05:40:43 +0000 (14:40 +0900)]
[mocotest-tf] Enable RealDiv and Sub test (#6324)

This will enable mocotest-tf test for RealDiv and Sub

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[loco] Identity Graph Testcase with Input Shape (#6307)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 05:40:25 +0000 (14:40 +0900)]
[loco] Identity Graph Testcase with Input Shape (#6307)

This commit allows users to build an identity graph testcase with
explicit input shape.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Enable Canonicalization of Sub and RealDiv (#6316)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 05:16:27 +0000 (14:16 +0900)]
[moco-tf] Enable Canonicalization of Sub and RealDiv (#6316)

This will enable Canonicalizaton of TFSub and TFRealDiv nodes

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Canonicalizer for RealDiv (#6306)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 04:15:57 +0000 (13:15 +0900)]
[moco-tf] Canonicalizer for RealDiv (#6306)

This will introduce Canonicalizer for TFRealDiv to EltwiseDiv

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[mir-tflite-importer] Perform operation sanity checks while converting it (#6069)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 7 Aug 2019 04:09:53 +0000 (07:09 +0300)]
[mir-tflite-importer] Perform operation sanity checks while converting it (#6069)

* [mir-tflite-importer] Perform operation sanity checks while creating

Perform operation sanity checks while creating it

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
4 years agoRemove format check warning by deleted file (#6312)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 03:45:29 +0000 (12:45 +0900)]
Remove format check warning by deleted file (#6312)

By filter out deleted file, remove warning on format checker's diff with master mode

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years agoEnable DETECTION_POSTPROCESS kernel in TFLite interpreter (#6214)
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 02:26:31 +0000 (11:26 +0900)]
Enable DETECTION_POSTPROCESS kernel in TFLite interpreter (#6214)

- Enable DETECTION_POSTPROCESS in interpreter

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
4 years ago[moco-tf] Canonicalizer for Sub (#6305)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:55:30 +0000 (10:55 +0900)]
[moco-tf] Canonicalizer for Sub (#6305)

This will introduce Canonicalizer for TFSub node to EltwiseSub

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Graph build for RealDiv node (#6304)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:54:52 +0000 (10:54 +0900)]
[moco-tf] Graph build for RealDiv node (#6304)

This will enable graph building of RealDiv node for importer

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Graph build for Sub node (#6303)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:54:29 +0000 (10:54 +0900)]
[moco-tf] Graph build for Sub node (#6303)

This will enable graph building of Sub node for importer

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Use calc_node_pad for fix pad of loco nodes (#6300)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:42:35 +0000 (10:42 +0900)]
[moco-tf] Use calc_node_pad for fix pad of loco nodes (#6300)

This will change to use calc_node_pad() method to fix pad in FixShapeInference for loco nodes

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Fix pad for TFConv2D in fix shape (#6250)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 01:42:10 +0000 (10:42 +0900)]
[moco-tf] Fix pad for TFConv2D in fix shape (#6250)

This will merge fix pad for TFConv2D node in fix shape transform

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[loco] Support ConstGen shape inference (#6290)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 01:31:28 +0000 (10:31 +0900)]
[loco] Support ConstGen shape inference (#6290)

CanonicalShapeInferenceRule is now able to infer the shape of ConstGen
nodes.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[exo-tflite] BiasShape to ShapeDescription Converter (#6289)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 01:30:01 +0000 (10:30 +0900)]
[exo-tflite] BiasShape to ShapeDescription Converter (#6289)

This commit implements BiasShape -> ShapeDescription converter.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years agoIntroduce "xtrace" (#6158)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 01:16:30 +0000 (10:16 +0900)]
Introduce "xtrace" (#6158)

* Introduce "xtrace"

This commit introduces "xtract" which collects trace/benchmark events
via xray pipe and records it as Chrome Trace Event file format.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Add missing copyright

4 years ago[loco] MaxPool2D Shape Inference (#6287)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 00:44:41 +0000 (09:44 +0900)]
[loco] MaxPool2D Shape Inference (#6287)

CanonicalShapeInferenceRule is now able to infer the shape of MaxPool2D
nodes.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[nnpackage] Add an nnpackage example (one op, tflite) (#5929)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 00:43:24 +0000 (09:43 +0900)]
[nnpackage] Add an nnpackage example (one op, tflite) (#5929)

Add first minimal nnpackage example.
It has no custom op, one operator, uses tflite model.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[nnpackage] nnpackager -c will create compressed nnpackage (#6278)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 7 Aug 2019 00:42:59 +0000 (09:42 +0900)]
[nnpackage] nnpackager -c will create compressed nnpackage (#6278)

Use "nnpackage -c path_to_nnpackage_root" to get compressed nnpackage.
Also it removed redundant parenthesis in if condition.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years agoReplace strict build flag setting in neurun frontend & core (#6279)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Aug 2019 00:40:54 +0000 (09:40 +0900)]
Replace strict build flag setting in neurun frontend & core (#6279)

- Replace neurun frontends and core strict build setting cmake from using compile option to linking nnfw_common interface
- Add strict build setting for nnfw api frontend and fix unused parameter warning

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[moco-tf] Introduce function to create BiasAdd operation (#6292)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 7 Aug 2019 00:03:26 +0000 (09:03 +0900)]
[moco-tf] Introduce function to create BiasAdd operation (#6292)

This commit will introduce a new function to create `BiasAdd` operation
and insert it after preceding operation.

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years agoAdd default fallback for Visitor::visit (#5889)
Дилшоджон Пошшоев/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 6 Aug 2019 19:49:39 +0000 (22:49 +0300)]
Add default fallback for Visitor::visit (#5889)

This will help to escape overriding a lot of visit()
with default body: empty body or `throw std::runtime_error("NYI")`:
just override this new method

additional changes:
* added file with all mir operation headers
* refined IVisitor

Signed-off-by: Dilshodzhon Poshshoev <d.poshshoev@samsung.com>
4 years ago[mir_onnx] Replace BiasAdd and Scale with Elementwise equivalents (#6298)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 6 Aug 2019 18:49:35 +0000 (21:49 +0300)]
[mir_onnx] Replace BiasAdd and Scale with Elementwise equivalents (#6298)

`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir2loco] Replace BiasAdd and Scale with Elementwise equivalents (#6296)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 6 Aug 2019 17:07:39 +0000 (20:07 +0300)]
[mir2loco] Replace BiasAdd and Scale with Elementwise equivalents (#6296)

`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe] Replace BiasAdd and Scale with elementwise equivalents (#6295)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 6 Aug 2019 16:53:03 +0000 (19:53 +0300)]
[mir_caffe] Replace BiasAdd and Scale with elementwise equivalents (#6295)

`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_tflite] Replace BiasAdd and Scale with Elementwise equivalents (#6294)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 6 Aug 2019 16:51:00 +0000 (19:51 +0300)]
[mir_tflite] Replace BiasAdd and Scale with Elementwise equivalents (#6294)

`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe2] Replace BiasAdd and Scale with Elementwise equivalents (#6293)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 6 Aug 2019 16:50:14 +0000 (19:50 +0300)]
[mir_caffe2] Replace BiasAdd and Scale with Elementwise equivalents (#6293)

`BiasAdd` and `Scale` are restricted versions of equivalent Elementwise ops and are going to be removed.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Add NodeConverters for all supported operations from OpCreator (#6291)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 6 Aug 2019 16:48:45 +0000 (19:48 +0300)]
[mir_onnx] Add NodeConverters for all supported operations from OpCreator (#6291)

* Added OpConverters
* Register all converters
* Remove OpCreator

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[mir_onnx] Introduce NodeConverterRegistry and remove operation hash (#6241)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 6 Aug 2019 14:28:33 +0000 (17:28 +0300)]
[mir_onnx]  Introduce NodeConverterRegistry and remove operation hash (#6241)

* Introduce NodeConverterRegistry
* Remove operation hash
* Replace operation hash uses with NodeConverter

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[moco-tf] Divide into function for fused convolution node in FuseBinaryIntoPreceding...
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 6 Aug 2019 10:06:56 +0000 (19:06 +0900)]
[moco-tf] Divide into function for fused convolution node in FuseBinaryIntoPreceding (#6273)

* [moco-tf] Divide into function for fused convolution node in FuseBinaryIntoPreceding

This commit will introduce `fused_conv_node` function for dividing long code.

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* add missing code

4 years ago[loco] Use link helper (#6271)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 09:37:51 +0000 (18:37 +0900)]
[loco] Use link helper (#6271)

Let's use link helper instead of deprecated node method.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[loco] Update TensorShaped classes with initializer_list (#6284)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 09:36:10 +0000 (18:36 +0900)]
[loco] Update TensorShaped classes with initializer_list (#6284)

Now, "shape" setter in TensorShaped mixin takes initializer_list
as its input.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[mocotest-tf] Register Squeeze tests (#6265)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 6 Aug 2019 09:33:46 +0000 (18:33 +0900)]
[mocotest-tf] Register Squeeze tests (#6265)

This commit register and enable valid Squeeze tests for moco tf

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[res] Add negative squeeze dimension test case (#6262)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 6 Aug 2019 09:33:30 +0000 (18:33 +0900)]
[res] Add negative squeeze dimension test case (#6262)

This commit add Squeeze network test case with negative squeeze dimension

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[moco-tf] Extract common Pad calculation method (#6252)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 09:33:07 +0000 (18:33 +0900)]
[moco-tf] Extract common Pad calculation method (#6252)

* [moco-tf] Extract common Pad calculation method

This will extract common Pad calculation methods for Canonical and TF dialect nodes

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

* use int64_t

* add guard

4 years agonnpackager will verify when verify option is given (#6276)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 08:38:29 +0000 (17:38 +0900)]
nnpackager will verify when verify option is given (#6276)

nnpackger always verified. Now, it verifies if verify is given.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[loco] Implement AvgPool2D shape inference (#6251)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 08:16:14 +0000 (17:16 +0900)]
[loco] Implement AvgPool2D shape inference (#6251)

* [loco] Implement AvgPool2D shape inference

This commit extends CanonicalShapeInferenceRule to accept AvgPool2D nodes.

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

* Introduce FeatureShapeUpdater

4 years ago[moco-tf] Use public member tbl() for Squeeze log (#6282)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 6 Aug 2019 08:14:15 +0000 (17:14 +0900)]
[moco-tf] Use public member tbl() for Squeeze log (#6282)

This commit use public tbl() member funciton instead of to-be-deprecated
private member _tbl

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[loco] TypeInferenceRule to use inference rules of multiple dialects (#6198)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 08:13:10 +0000 (17:13 +0900)]
[loco] TypeInferenceRule to use inference rules of multiple dialects (#6198)

* [loco] TypeInferenceRule to use inference rules of multiple dialects

This commit adds MultiDialectTypeInferenceRule that uses inference rules of multiple dialects.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* using loco::link(..)

* using loco::link(..) for output too

* assert

* bind method

* struct to class

* //// -> ///

* modifying assert

4 years ago[exo-tflite] Exporting custom op (#6269)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 08:10:22 +0000 (17:10 +0900)]
[exo-tflite] Exporting custom op (#6269)

This commit enables exportation of custom op (Operator Codes, input, output, op with attr) into tflite file.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Introduce TFSub IR (#6275)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 08:09:41 +0000 (17:09 +0900)]
[moco-tf] Introduce TFSub IR (#6275)

This will introduce TFSub IR and required implementations

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years agoUpdate TFLITE_MINOR_VER to 13 (#6274)
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 06:04:23 +0000 (15:04 +0900)]
Update TFLITE_MINOR_VER to 13 (#6274)

- Tizen has tensorflow lite version 1.13.1
- Update TFLITE_MINOR_VER to 13 in nnfw.spec

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
4 years agoMake to distinguish frontend layout from backend layout in Graph (#6253)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 6 Aug 2019 05:34:15 +0000 (14:34 +0900)]
Make to distinguish frontend layout from backend layout in Graph (#6253)

This commit makes to distinguish frontend layout fron backend layout in Gragh.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[moco-tf] Introduce TFRealDiv IR (#6270)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 04:52:34 +0000 (13:52 +0900)]
[moco-tf] Introduce TFRealDiv IR (#6270)

* [moco-tf] Introduce TFRealDiv IR

This will introduce TFRealDiv IR and required implementations

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

4 years ago[exo-tflite] Export EltwiseSub and EltwiseDiv (#6263)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 03:53:56 +0000 (12:53 +0900)]
[exo-tflite] Export EltwiseSub and EltwiseDiv (#6263)

This will enable export of EltwiseSub and EltwiseDiv node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Shape inf. for EltwiseSub and EltwiseDiv (#6264)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 03:53:31 +0000 (12:53 +0900)]
[exo-tflite] Shape inf. for EltwiseSub and EltwiseDiv (#6264)

This will enable shape inference of EltwiseSub and EltwiseDiv node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Enable Squeeze Canonicalizer (#6261)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 6 Aug 2019 03:39:05 +0000 (12:39 +0900)]
[moco-tf] Enable Squeeze Canonicalizer (#6261)

This commit register and enables SqueezeCanonicalizer

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[loco] Shape Inference for Eltwise Arithmetic Nodes (#6256)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 03:32:31 +0000 (12:32 +0900)]
[loco] Shape Inference for Eltwise Arithmetic Nodes (#6256)

This commit implements shape inference for eltwise arithmetic nodes.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[locomotiv] Support EltwiseDiv (#6258)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 01:54:21 +0000 (10:54 +0900)]
[locomotiv] Support EltwiseDiv (#6258)

This will support EltwiseDiv node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[locomotiv] Support EltwiseSub (#6257)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 6 Aug 2019 01:54:01 +0000 (10:54 +0900)]
[locomotiv] Support EltwiseSub (#6257)

This will support EltwiseSub node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years agoUpdate replaced scripts path (#6255)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 01:53:02 +0000 (10:53 +0900)]
Update replaced scripts path (#6255)

Update replaced scripts path reference in script or document: scripts/standalone -> infra/scripts

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[moco-tf] Squeeze Canonicalizer (#6234)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 6 Aug 2019 01:46:21 +0000 (10:46 +0900)]
[moco-tf] Squeeze Canonicalizer (#6234)

Squeeze canonicalizer is to canonicalize TF-dialect TFSqueeze into
canonical FixedReshape.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
4 years ago[exo-tflite] Convert FeatureShape to ShapeDescription (#6254)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 01:45:47 +0000 (10:45 +0900)]
[exo-tflite] Convert FeatureShape to ShapeDescription (#6254)

This commit introduces "to_shape_description" helper which constructs
ShapeDescription (which exo-tflite internally uses) from FeatureShape.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years agoUpgrade Arm Compute Lib to 19.05 (#5611)
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 00:36:11 +0000 (09:36 +0900)]
Upgrade Arm Compute Lib to 19.05 (#5611)

- upgrade Arm Compute Library to v19.05

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
4 years ago[moco-tf] Use loco::link helper (#6228)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Aug 2019 00:16:58 +0000 (09:16 +0900)]
[moco-tf] Use loco::link helper (#6228)

Let's use loco::link helper instead of deprecated node method!

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Fix pad for TFAvgPool in fix shape (#6225)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 5 Aug 2019 23:25:10 +0000 (08:25 +0900)]
[moco-tf] Fix pad for TFAvgPool in fix shape (#6225)

This will merge fix pad for TFAvgPool node in fix shape transform

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Introduce FuseType and divide functions using it (#6227)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 5 Aug 2019 23:23:19 +0000 (08:23 +0900)]
[moco-tf] Introduce FuseType and divide functions using it (#6227)

This commit will introduce `FuseType` and divide functions using `FuseType`
for each case

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[moco-tf] Fix pad for MaxPool2D in fix shape (#6223)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 5 Aug 2019 23:22:18 +0000 (08:22 +0900)]
[moco-tf] Fix pad for MaxPool2D in fix shape (#6223)

This will merge fix pad for MaxPool2D node in fix shape transform

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[loco] EltwiseDiv IR (#6229)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 5 Aug 2019 23:21:59 +0000 (08:21 +0900)]
[loco] EltwiseDiv IR (#6229)

This will introduce canonical EltwiseDiv IR

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Registering custom op before exporting op code table (#6235)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 5 Aug 2019 23:21:46 +0000 (08:21 +0900)]
[exo-tflite] Registering custom op before exporting op code table (#6235)

This adds custom op before exporting op code table.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[res] RealDiv_000 (#6233)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 5 Aug 2019 23:17:51 +0000 (08:17 +0900)]
[res] RealDiv_000 (#6233)

This will introduce TensorFlow RealDiv_000 test model with one RealDiv node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[res] TF Sub_000 (#6231)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 5 Aug 2019 23:17:11 +0000 (08:17 +0900)]
[res] TF Sub_000 (#6231)

This will introduce Sub_000 TensorFlow test model with one Sub node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[mir] Remove deserializer header (#6249)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 19:29:23 +0000 (22:29 +0300)]
[mir] Remove deserializer header (#6249)

This is a leftover after removing stale serialization support.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years agoSelecting all helper functions in a separate file (#6237)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 18:12:18 +0000 (21:12 +0300)]
Selecting all helper functions in a separate file (#6237)

* Move all helper functions in one file
* Fix other code

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[mir2loco] Rename DTYPE to DataType (#6247)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 18:06:11 +0000 (21:06 +0300)]
[mir2loco] Rename DTYPE to DataType (#6247)

Replace deprecated `DTYPE` with `DataType`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Rename DTYPE to DataType (#6248)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 17:40:16 +0000 (20:40 +0300)]
[nnc] Rename DTYPE to DataType (#6248)

Replace deprecated `DTYPE` with `DataType`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_tflite] Rename DTYPE to DataType (#6246)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 17:39:16 +0000 (20:39 +0300)]
[mir_tflite] Rename DTYPE to DataType (#6246)

Replace deprecated `DTYPE` with `DataType`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe2] Rename DTYPE to DataType (#6245)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 17:38:52 +0000 (20:38 +0300)]
[mir_caffe2] Rename DTYPE to DataType (#6245)

Replace deprecated `DTYPE` with `DataType`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe] Rename DTYPE to DataType (#6244)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 17:38:27 +0000 (20:38 +0300)]
[mir_caffe] Rename DTYPE to DataType (#6244)

Replace deprecated `DTYPE` with `DataType`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_tflite] Rename namespace nnc to mir_tflite in TFLite importer (#6240)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 16:45:25 +0000 (19:45 +0300)]
[mir_tflite] Rename namespace nnc to mir_tflite in TFLite importer (#6240)

* Rename namespace and include guards in TFLite importer
* Fix usages of the namespace in `nnc`

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe] Rename namespace nnc to mir_caffe in Caffe importer (#6239)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 16:45:07 +0000 (19:45 +0300)]
[mir_caffe] Rename namespace nnc to mir_caffe in Caffe importer (#6239)

* Rename namespace and include guards in Caffe importer
* Fix usages of the namespace in `nnc`

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe2] Rename namespace nnc to mir_caffe2 in Caffe2 importer (#6238)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 16:43:06 +0000 (19:43 +0300)]
[mir_caffe2] Rename namespace nnc to mir_caffe2 in Caffe2 importer (#6238)

* Rename namespace and include guards in Caffe2 importer
* Fix usages of the namespace in `nnc`

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir] Rename DTYPE to DataType (#6243)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 16:35:39 +0000 (19:35 +0300)]
[mir] Rename DTYPE to DataType (#6243)

Rename enum class `DTYPE` to `DataType` to conform to the naming rules.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years agoRename ncc namespace into mir_onnx in ONNX importer (#6236)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 15:39:48 +0000 (18:39 +0300)]
Rename ncc namespace into mir_onnx in ONNX importer (#6236)

* Rename namespace in importer
* Fix onnx_frontend in NNC

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years agoACL NEON Strided Slice (#5946)
Nikita Sizov/AI Tools Lab /SRR/Professional/삼성전자 [Mon, 5 Aug 2019 13:51:36 +0000 (16:51 +0300)]
ACL NEON Strided Slice (#5946)

Add support of Strided Slice in ACL NEON

Signed-off-by: Sizov Nikita <n.sizov@samsung.com>
4 years ago[mir2loco] Support Conv2D operation (#5899)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 5 Aug 2019 13:49:31 +0000 (16:49 +0300)]
[mir2loco] Support Conv2D operation (#5899)

* Implemented `mir::Conv2DOp` transformation to `loco::Conv2D`
* Added test for this

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years agoAdd layout as a condition for merging subgraphs (#6216)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 5 Aug 2019 11:12:18 +0000 (20:12 +0900)]
Add layout as a condition for merging subgraphs (#6216)

This commit adds layout as a condition for merging subgraph.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>