장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 7 Oct 2019 05:34:03 +0000 (14:34 +0900)]
Make to support SpaceToBatchND op for acl cl (#7933)
This commit make to support SpaceToBatchND op for acl cl.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 7 Oct 2019 03:53:41 +0000 (12:53 +0900)]
Pad Operation in tflite_loader (#7932)
Pad operaions is now supported by tflite_loader
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
Fix validate check in Conv2d (#7937)
Do not accept conv2d operation with non one dilations
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 7 Oct 2019 01:53:56 +0000 (10:53 +0900)]
[exo-tflite] remove unused header (#7923)
This removes unused header in `TFLShapeInferenceRule.cpp`.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 7 Oct 2019 01:51:43 +0000 (10:51 +0900)]
[res] make explain.sh excutable (#7917)
exeplain.sh now can be run (by `chmod +x explain.sh`)
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 7 Oct 2019 00:12:09 +0000 (09:12 +0900)]
[moco] All IRs (#7908)
* [moco] All IRs
This will add rest of IRs of moco for TFDialect
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix def
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 6 Oct 2019 23:54:16 +0000 (08:54 +0900)]
[exo-tflite] Introducing Pass dir and Passes.h (#7909)
This introduces Pass dir, which is for all optimization pass for TFL nodes, and Passes.h, which is a aggregation of passes in Pass dir.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 6 Oct 2019 23:53:04 +0000 (08:53 +0900)]
[exo-tflite] Remove body of CanonicalNodeConverter.cpp (#7921)
`Run` is now included inside `*.h` so removed from `*.cpp` file.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 6 Oct 2019 23:49:57 +0000 (08:49 +0900)]
[exo-tflite] Code to export TFLConv2D (#7926)
Now OperationExporter has code to export TFLConv2D.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 6 Oct 2019 23:46:17 +0000 (08:46 +0900)]
[exo-tflite] Complete node summary for TFLAvergePool2D & TFLMaxPool2D (#7928)
Complete node summary for TFLAvergePool2D & TFLMaxPool2D was added.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 6 Oct 2019 23:41:49 +0000 (08:41 +0900)]
[exo-tflite] adding an assert to check rank of ifm in TFLShapeInferenceRule (#7922)
This adds an `assert` to check rank of ifm in TFLShapeInferenceRule.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
[mir_tflite] Use object-based API for subgraphs and tensors (#7936)
Object-based API is more convenient.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Use object-based API for operators (#7934)
Object-based API is more convenient.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 4 Oct 2019 08:30:43 +0000 (17:30 +0900)]
[res] Adding manifest for NET_0008 and NET_0009 (#7916)
Summary for NET_0008 and NET_0009 was added.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 4 Oct 2019 08:30:02 +0000 (17:30 +0900)]
[exo-tflite] Remove "// TODO TFLNop" (#7925)
Since we don't have `TFLNop`, related comments were removed.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 4 Oct 2019 08:25:50 +0000 (17:25 +0900)]
[res] Add simple Pad test case (#7893)
* [res] Add simple Pad test case
This commit adds simple pad test case.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* make manifest.
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 4 Oct 2019 08:20:13 +0000 (17:20 +0900)]
[logo] simplifying FilterEncode-FilterDecode (#7875)
* [logo] simplifying FilterEncode-FilterDecode to Transpose (or to Forward)
This commit simplifying FilterEncode-FilterDecode to Transpose (or to Forward)
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* fix wrong const size
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 4 Oct 2019 08:03:17 +0000 (17:03 +0900)]
[nnfw-build] Revise generate test setting (#7905)
- Remove GENERATE_NNAPI_TESTS in makefile
- Use cmake option to disable generate test
- Default: enable
- For tizen: disable as default for gbs/obs, enable on tizen cross build script
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
[neurun] Schedule branch by branch instead of node (#6965)
* [neurun] Schedule branch by branch instead of node
Related issue: 6963
Schedule whole branch (that can be seen as a subgraph) recursively
before moving to next node
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
* Fix CI failure
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
* Address offline review
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
* Fix review feedbacks
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
* Address feedbacks: rename scheduleRecursively
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
* Fix documentation typo
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 4 Oct 2019 01:36:08 +0000 (10:36 +0900)]
[nnfw-gbs] Remove outdated code in nnfw.spec (#7906)
Remove pacl related code
Packaging *.so file only and remove useless exclude
Remove install libbackend_acl_common.a
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
[mir-tflite-importer] Hide class TFLiteImporter definition (#7913)
Class moved to cpp in order to simplify interface header.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir-onnx-importer] Hide class OnnxImporterImpl definition (#7912)
Class moved to cpp in order to simplify interface header.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir-caffe2-importer] Hide class Caffe2Importer definition (#7911)
Class moved to cpp in order to simplify interface header.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir-caffe-importer] Hide class CaffeImporter definition (#7910)
In order to simplify interface header, class moved to cpp.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 2 Oct 2019 06:49:35 +0000 (15:49 +0900)]
[nnapi-test] Introduce TestNeuralNetworksWrapper (#7903)
Port TestNeuralNetworksWrapper.h/cpp from upstream android nn runtime's NNAPI test
Fix
- Comment out 'include NeuralNetworksWrapperExtensions.h' and related namespace
- Use boost::optional instead of std::optional
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 2 Oct 2019 05:51:43 +0000 (14:51 +0900)]
[moco] Introduce TensorName and VariadicArityNode (#7899)
This will introduce two helper TensorName and VariadicArityNode used for TFDialect IRs
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 2 Oct 2019 05:35:42 +0000 (14:35 +0900)]
Apply optimized cpu kernel of MaxPoolFloat32 (#7886)
This commit applies optimized cpu kernel of MaxPoolFloat32.
- Introduce optimized cpu kernel of MaxPool for float
- Apply that kernel for cpu backend of neurun
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 2 Oct 2019 05:01:52 +0000 (14:01 +0900)]
[nnfw-api] rename api related files (#7895)
- nnfw_dev.cc is renamed to nnfw_api.cc.
- nnfw_dev.cc looks like the implementation for `nnfw_dev.h`. (i.e. APIs for developers like custom op)
- However, it is a binding from C APIs to C++ implementation for WHOLE APIs.
- nnfw_api.cc and nnfw_api.hpp are C++ implementation.
- nnfw_api.cc is already used for a binding implementation the above.
- Thus, they are renamed to nnfw_api_internal.*.
- nnfw_api.hpp is renamed to nnfw_api_internal.h.
- It was the only file that uses the suffix `*.hpp`.
- wrapper directory is removed to make structure simple.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 2 Oct 2019 04:29:35 +0000 (13:29 +0900)]
[android] Disable STRICT_BUILD (#7900)
Disable STRICT_BUILD to suppress warnings from ARMComputeEx.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 2 Oct 2019 03:38:18 +0000 (12:38 +0900)]
[moco] Introduce Conv2D series IR (#7891)
This will introduce IR for Conv2D, Conv2DBackpropInput and DepthwiseConv2dNative node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 2 Oct 2019 03:38:00 +0000 (12:38 +0900)]
[moco] Introduce IR for Add AvgPool BiasAdd (#7890)
This will introduce IR for Add, AvgPool and BiasAdd node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 2 Oct 2019 03:28:05 +0000 (12:28 +0900)]
[android] Disable building unsupported libraries (#7898)
Disable building libraries that are not supported due to dependency on
Boost library.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
Segregate interface of tflite_loader (#7668)
* Segregate interface of tflite_loader
Split `tflite_loader` component into two parts -- interface and implementation.
Put the loader into `neurun` namespace.
Remove a couple of unused functions that triggered compiler warnings.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 2 Oct 2019 01:01:53 +0000 (10:01 +0900)]
[moco] Introduce TFNodeVisitor (#7887)
This will introduce TFNodeVisitor and revise TFNode to support visitor pattern
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 22:06:58 +0000 (07:06 +0900)]
[exo-tflite] add TensorTransposeConverter into the list of pass (#7877)
This adds TensorTransposeConverter into the list of pass.
Please turns on the knob to convert TensorTranspose to TFLTransport.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
[mir] Fix TensorVariant constructor used in broadcasting (#7889)
* Fix TensorType creation with old shape
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Change all calls to MIR importers in [nnc] (#7879)
According with interface changes, we now use loadModel(...) functions.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 10:36:13 +0000 (19:36 +0900)]
[moco-tf] ShapeInf for Add AvgPool BiasAdd (#7885)
This will enable shape inference for Add AvgPool and BiasAdd node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 10:35:54 +0000 (19:35 +0900)]
[moco-tf] Use TFShapeInferenceHelper fox FixShape (#7884)
This will make FixShapeTransform to use TFShapeInferenceHelper methods
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 1 Oct 2019 10:26:37 +0000 (19:26 +0900)]
[nnfw-cmake] Remove runtime variable (#7881)
Remove unused runtime name variable
Move set LIB_NEURUN variable
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 09:47:32 +0000 (18:47 +0900)]
[moco-tf] Refactor Conv2DCanonicalizer (#7874)
This will update Conv2DCanonicalizer to do shape, pad inference and NOT to use annotations
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 09:47:11 +0000 (18:47 +0900)]
[moco-tf] Refactor AvgPoolCanonicalizer (#7872)
This will update AvgPoolCanonicalizer to do shape, pad inference and NOT to use annotations
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 09:42:21 +0000 (18:42 +0900)]
[moco] Introduce TFNode and related (#7870)
This will introduce TFNode base class and related codes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 09:41:49 +0000 (18:41 +0900)]
[moco] Introduce requires.cmake (#7880)
This will introduce moco requires.cmake file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 1 Oct 2019 09:24:52 +0000 (18:24 +0900)]
[nnfw-cmake] Replace fp16 source package config (#7840)
Move fp16 source package config to common directory
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 09:20:37 +0000 (18:20 +0900)]
[neurun] move api out of frontend (#7873)
- api is now under `neurun`, instead of `neurun/frontend`.
- add dependency for nnfw-header in custom op kernels and apps.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 09:12:25 +0000 (18:12 +0900)]
[moco-tf] broadcast_shape to helper (#7844)
* [moco-tf] broadcast_shape to helper
This will copy broadcast_shape method and related codes to helper file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add todo comment
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 08:18:49 +0000 (17:18 +0900)]
[moco-tf] Introduce ShapeInferenceAlgorithm (#7871)
This will introduce ShapeInferenceAlgorithm to provide shape inferece by type of TFNode
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 1 Oct 2019 07:35:56 +0000 (16:35 +0900)]
Apply optimized cpu kernel for AvgPoolFloat32 (#7834)
This commit applies optimized cpu kernel for AvgPoolFloat32.
- Introduce introduce optimized cpu kernel of AvgPool2D op
- Apply that kernel for AvgPoolFloat32
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 1 Oct 2019 07:14:06 +0000 (16:14 +0900)]
[res] Summary for NET_0025 (#7867)
This commit adds summary for NET_0025, CBR network test case.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 1 Oct 2019 07:13:34 +0000 (16:13 +0900)]
[tf2tflite] Test NET_0025 (#7868)
This commit registers NET_0025 unit test, CBR network, to tf2tflite
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 07:10:42 +0000 (16:10 +0900)]
[moco-tf] PlaneShape for shape inference (#7866)
This will introduce PlaneShape, PlaneInference and related codes for plane shape inference for Pool and Conv2D series nodes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 07:10:18 +0000 (16:10 +0900)]
[moco-tf] window_of for Conv2D (#7864)
This will introduce window_of method used for Conv2D type nodes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 07:09:59 +0000 (16:09 +0900)]
[logo] traversing using active_nodes instead of all_nodes (#7865)
Using all_nodes makes simplifying orphant subgraph and cause error.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 07:08:44 +0000 (16:08 +0900)]
[moco] Introduce lang sub project and TFDialect (#7863)
This will introduce moco lang sub project with TFDialect class
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 1 Oct 2019 03:06:11 +0000 (12:06 +0900)]
[pacl] Additional NNAPI implementation for update NNAPI (#7860)
- PACL's NNAPI implementation for updated NNAPI generated test
- Update skiplist for updated validation check
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 1 Oct 2019 02:01:31 +0000 (11:01 +0900)]
[nnfw-cmake] Rename NNFW_OVERLAY_DIR (#7848)
Rename NNFW_OVERLAY_DIR to NNAS_OVERLAY_DIR to share cmake package config with nnfw
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 1 Oct 2019 01:56:38 +0000 (10:56 +0900)]
[nnfw-cmake] Replace nonius package config (#7839)
Move nonius and source package config to common directory
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 01:45:05 +0000 (10:45 +0900)]
[exo-tflite] Make S32 tensor to be exported (#7827)
* [exo-exporter] Make S32 tensor to be exported
Previously only FLOAT32 tensor could be exported. This commit enables S32 tensor to be exported.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* throw exception when not-supported dtype is found
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 1 Oct 2019 01:17:07 +0000 (10:17 +0900)]
[moco] Initial readme (#7813)
* [moco] Initial readme
This will introduce readme for moco project and moco-lang sub project
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* change folder to lang
* update moco
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 1 Oct 2019 00:53:36 +0000 (09:53 +0900)]
[nncc-cmake] Introduce NNAS_OVERLAY_DIR (#7846)
Introduce NNAS_OVERLAY_DIR to share cmake package config with nnfw
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 23:21:59 +0000 (08:21 +0900)]
[exo-tflite] code to export TFLTranspose to tflite file (#7806)
Code to export TFLTranspose to tflite file was added into OperationExporter.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 23:21:46 +0000 (08:21 +0900)]
[exo-tflite] shape & type inference for TFLConv2D (#7835)
This adds shape inference and type inference for TFLConv2D.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 23:21:33 +0000 (08:21 +0900)]
[exo-tfltie] converting loco::Conv2D to locoex::TFLConv2D (#7845)
This adds a Conv2DConverter that converts loco::Conv2D to locoex::TFLConv2D.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 22:21:32 +0000 (07:21 +0900)]
[moco-tf] Revose ResolveReshapeWildcardDim (#7843)
This will revise ResolveReshapeWildcardDim to use NodeShape instead of ShapeInferenceData
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 22:21:06 +0000 (07:21 +0900)]
[moco-tf] Revise ResolveConstantShape (#7842)
This will revise ResolveConstantShape to use NodeShape instead of ShapeInferenceData
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 22:14:55 +0000 (07:14 +0900)]
[moco-tf] Revise FuseBinaryIntoPreceding (#7841)
This will revise FuseBinaryIntoPreceding to use NodeShape instead of ShapeInferenceData
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 30 Sep 2019 15:34:17 +0000 (18:34 +0300)]
[mir2loco] Support Broadcast on Elementwise operations (#7665)
* Supported new elemetwise operations
* Implemented TensorBroadcast creation
* Fixed all functions for broadcasting
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Expand [mir-caffe-importer] interface (#7850)
Added new interface function loadModel in caffe importer
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
Expand [mir-caffe2-importer] interface (#7855)
A new function loadModel was added.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
Expand [mir-onnx-importer] interface (#7856)
A new function loadModel was added.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
Importer interface was expanded. (#7857)
A new function loadModel was added.
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir] Introduce TensorType (#7854)
* Add `TensorType` class which combines tensor element type and shape.
* Use it in `TensorVariant` and `Operation::Output`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 30 Sep 2019 11:04:00 +0000 (20:04 +0900)]
[nnapi] Update NeuralNetworks.Wrapper.h (#7829)
Use NeuralNetworks.Wrapper.h in android-10 nn runtime
Fix to use boost::optional instead of std::optional (c++17 feature)
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 10:00:24 +0000 (19:00 +0900)]
[moco-tf] TFShapeInferenceRule V2 (#7825)
This will revise TFShapeInferenceRule to support V2 interface
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 09:36:20 +0000 (18:36 +0900)]
[moco-tf] Fix build error for TFShapeInferenceHelper path (#7837)
This will fix build error for recent TFShapeInferenceHelper path change
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 09:07:15 +0000 (18:07 +0900)]
[exo-tflite] converting loco::TensorTranspose to locoex::TFLTranspose (#7824)
* [exo-tflite] converter to convert loco::TensorTranspose to locoex::TFLTranspose
A converter to convert loco::TensorTranspose to locoex::TFLTranspose is introduced.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* adding more validation check + using std::is_permutation(..)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 09:02:35 +0000 (18:02 +0900)]
[moco-tf] Revise TFNodeSummaryBuilder for TFConst (#7826)
This will remove shape information for TFConst as shape is shown in loco
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 08:59:48 +0000 (17:59 +0900)]
[moco-tf] Convert TF strides and ksize (#7812)
* [moco-tf] Convert TF strides and ksize
This will introduce two methods to convert TensorFlow Strides and KSize vector to loco Stride and Window in TFShapeInferenceHelper
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* change folder to src
* recover changes
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 30 Sep 2019 08:33:24 +0000 (17:33 +0900)]
[nnfw-cmake] Replace NNPACK and related package config (#7798)
Move NNPACK and related source package config to common directory
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 30 Sep 2019 08:23:17 +0000 (17:23 +0900)]
[lib-tflite] Remove tflite version definition depdency code (#7807)
- Remove TFLITE_MAJOR_VER and TFLITE_MINOR_VER setting in nnfw.spec and cmake script
- Remove TFLITE_MAJOR_VER and TFLITE_MINOR_VER dependency code in tflite extension library
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 08:07:00 +0000 (17:07 +0900)]
[exo-tflite] helper funtion to create filter (#7828)
* [exo-tflite] helper fultion to create filter
This adds helper functions to easily create FilterEncode and FilterDecode of two filter layout.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remove blank
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 30 Sep 2019 08:06:11 +0000 (17:06 +0900)]
[exo-tflite] Unit test getOpPadding (#7802)
This commit adds unit test of getOpPadding() for valid, same
and custom padding cases.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 30 Sep 2019 06:58:48 +0000 (15:58 +0900)]
Make to support Gather op for acl neon (#7746)
This commit makes to support Gather op for acl neon.
- Introduce NEGatherEx and NEGatherKernelEx
- Apply NEGatherEx layer for neurun
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 30 Sep 2019 05:20:35 +0000 (14:20 +0900)]
[cmd] Move doxygen command (#7821)
Move doxygen command from nnfw to nnas
Use user-setting workspace for docygen output
Add document for help
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 30 Sep 2019 04:18:15 +0000 (13:18 +0900)]
[exo-tflite] Fix getOpPadding for SAME padding case (#7787)
* [exo-tflite] Fix getOpPadding for SAME padding case
Previously getOpPadding() checks only necessary condition for SAME
padding case. This commit checks fully equivalent logic for this.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Use explicit cast
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 03:09:33 +0000 (12:09 +0900)]
[moco-tf] Remove ShapeInferenceData in Canonicalizers (#7810)
This will revise Canonicalizers not to use ShapeInferenceData and use node_shape instead
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 30 Sep 2019 03:05:40 +0000 (12:05 +0900)]
[moco-tf] Remove dump shape after import (#7811)
This is to remove usage of ShapeInferenceData.
As loco can display shape information of the nodes, we do not need to dump the shape information after import.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
Rename cpu backend Shape (#5534)
Rename cpu backend Shape class into TensorDescriptor
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
이성재/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 27 Sep 2019 08:43:49 +0000 (17:43 +0900)]
Roll-back and fix typo in CONTRIBUTORS (#7809)
- Roll-back CONTRIBUTUTORS file from mis committed.
- Fix typo in filename CONTRIBUTUTORS to CONTRIBUTORS.
Signed-off-by: Sung-Jae Lee <sj925.lee@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 27 Sep 2019 08:28:22 +0000 (17:28 +0900)]
[exo-tflite] shape / type inference for TFLTranspose (#7803)
* [exo-tflite] shape / type inference for TFLTranspose
This adds shape and type inference for TFLTranspose and a test case.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* Fix wrong test case. Previously it is testing loco::Transpose, now it tests locoex::TFLTranspose
* remove method needed for loco::TensorTranspose
* typo
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 27 Sep 2019 08:22:28 +0000 (17:22 +0900)]
[loco] Introducing PermutingDecoder for filter (#7801)
* [loco] Introducing PermutingDecoder for filter
This adds PermutingDecoder for filter and related test case.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* move PermutingDecoder from DepthwiseFilter area to filter area
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 27 Sep 2019 08:22:14 +0000 (17:22 +0900)]
Make to support Cast op for acl neon (#7800)
This commit make to support Cast op for acl neon.
- Add NECast layer and NECastKernel
- Apply NECast layer for neurun
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 27 Sep 2019 08:20:46 +0000 (17:20 +0900)]
Enable some nnapi tests on ACL neon (#7756)
This commit enables some nnapi tests on ACL neon.
- dequantize*
- TrivialTest.BroadcastMulTwo
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 27 Sep 2019 07:50:52 +0000 (16:50 +0900)]
[loco] Type and Shape inference for FilterDecode (#7804)
This adds Type and Shape inference for FilterDecode.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 27 Sep 2019 07:31:24 +0000 (16:31 +0900)]
[nnfw-gbs] Use pre-generated test code (#7805)
Update nnfw.spec to use pre-generated nnapi test code
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 27 Sep 2019 06:52:58 +0000 (15:52 +0900)]
[cmd] Fix build docker image command help (#7742)
Remove deprecated option: tizen build option was removed
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 27 Sep 2019 06:39:32 +0000 (15:39 +0900)]
[nnfw-cmake] Revise tflite version setting (#7793)
Define option for tflite external code version
Replace ported tflite files to support two or more version
Prepare to remove TFLITE_MAJOR_VER and TFLITE_MINOR_VER setting
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 27 Sep 2019 06:02:17 +0000 (15:02 +0900)]
[ARMCompute] Fix for Android build (#7791)
- Do not build ARMCompute by default
- Fix `CMAKE_FIND_ROOT_PATH_MODE_LIBRARY` to search in the host dirs
For now, using pre-built library is recommended and building ARMCompute
is not enabled. It can be used by specifying `EXT_ACL_FOLDER` in
Makefile or pass `ARMCompute_EXTDIR` to CMake.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 27 Sep 2019 06:01:59 +0000 (15:01 +0900)]
[android_tflite] Remove finding NDK_DIR (#7799)
Remove automatic finding from CMake. Users must specify NDK_DIR from now
on.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>