platform/core/ml/nnfw.git
4 years ago[exo-tflite] functions to build node (#7080)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 09:06:39 +0000 (18:06 +0900)]
[exo-tflite] functions to build node (#7080)

This adds functions to build featureEncode and featureDecode, which are frequently used.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[exo-tflite] Adding knob for AveragePool2D conversion (#7092)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 09:04:59 +0000 (18:04 +0900)]
[exo-tflite] Adding knob for AveragePool2D conversion (#7092)

This adds knob for AveragePool2D conversion. Default is false.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years agoEnable Floor op for ACL neon (#7100)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 2 Sep 2019 08:25:52 +0000 (17:25 +0900)]
Enable Floor op for ACL neon (#7100)

This commit enables to support Floor op for ACL neon.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[exo-tflite] Adding TFLTypeInferenceRule into TypeInference (#7097)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 08:24:26 +0000 (17:24 +0900)]
[exo-tflite] Adding TFLTypeInferenceRule into TypeInference (#7097)

This adds TFLTypeInferenceRule into TypeInference.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[tflite_loader] Add Mul and Sub operator (#7099)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 07:55:58 +0000 (16:55 +0900)]
[tflite_loader] Add Mul and Sub operator (#7099)

It adds mul and sub operator to run ST model.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years agoFix uninitialized field (#7089)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 2 Sep 2019 06:54:24 +0000 (15:54 +0900)]
Fix uninitialized field (#7089)

Fix uninitialized field contructor warning in neurun core and backend

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years agoEnable Exp op for ACL neon (#7093)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 2 Sep 2019 06:14:04 +0000 (15:14 +0900)]
Enable Exp op for ACL neon (#7093)

This commit enables to support Exp op for ACL neon.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[exo-tflite] Change the name of input of TFLRelu (#7081)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 04:16:38 +0000 (13:16 +0900)]
[exo-tflite] Change the name of input of TFLRelu (#7081)

* [exo-tflite] Change the name of input of TFLRelu

Input name follows TensorFlow input naming. (input -> features)

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* modify input -> features

4 years agoApply finding frontend layout of operand (#7065)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 2 Sep 2019 04:08:32 +0000 (13:08 +0900)]
Apply finding frontend layout of operand (#7065)

This commit applies finding frontend layout of operand.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[tflite_loader] implement Relu6 operator (#7068)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 04:08:03 +0000 (13:08 +0900)]
[tflite_loader] implement Relu6 operator (#7068)

It adds `Relu6` for mobilenet v3.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years agoFix null type reference (#7059)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 2 Sep 2019 03:45:24 +0000 (12:45 +0900)]
Fix null type reference (#7059)

Instead of using getOperandSize, use type pointer to find out operand has unspecified shape

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[exo-tflite] Introducing TFLAveragePool2D node (#7054)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 03:44:12 +0000 (12:44 +0900)]
[exo-tflite] Introducing TFLAveragePool2D node (#7054)

* [exo-tflite] Introducing TFLAveragePool2D node

This adds TFLAveragePool2D node, which represelt AVERAGE_POOL_2D of TensorFlow Lite.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* modified per jh1304's review. Filter and Stride were made

4 years agoCoverity issue on scheduler (#7072)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 2 Sep 2019 00:56:33 +0000 (09:56 +0900)]
Coverity issue on scheduler (#7072)

- Unreached default in switch-case
- Unchecked return of library call

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[exo-tflite] Introducing TFLTypeInference (#7015)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 1 Sep 2019 23:03:02 +0000 (08:03 +0900)]
[exo-tflite] Introducing TFLTypeInference (#7015)

This adds TFLTypeInference to infer type for TFL nodes.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[pepper-str] Fix "unused parameter" warning in CI (#7075)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 1 Sep 2019 23:02:26 +0000 (08:02 +0900)]
[pepper-str] Fix "unused parameter" warning in CI (#7075)

This fix "unused parameter" warning in CI.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years agoRemove unnecessary helper function (#7066)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 09:59:01 +0000 (18:59 +0900)]
Remove unnecessary helper function (#7066)

This commit removes unnecessary helper function.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years agoMake ConcatLayers support NCHW frontend layout (#7063)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 09:41:08 +0000 (18:41 +0900)]
Make ConcatLayers support NCHW frontend layout (#7063)

This commit makes ConcatLayers support NCHW frontend layout.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[neurun] Use LIB_PTHREAD variable in CMake (#7069)
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 09:25:38 +0000 (18:25 +0900)]
[neurun] Use LIB_PTHREAD variable in CMake (#7069)

Use variable `${LIB_PTHREAD}` rather than hardcoded `pthread`. This is
useful for Android build which does not have pthread lib. Android
contains pthread in libc.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
4 years agoRevert commits related to mutex in acl_cl::Object (#7062)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 08:37:25 +0000 (17:37 +0900)]
Revert commits related to mutex in acl_cl::Object (#7062)

- Revert "Fix deadlock when access two acl_cl at once (#6500)"
- Revert "[neurun] Change acl_cl::Object::access to multithread safe (#5636)"

This reverts commit 51671b098692a133d86624afc5455c6e01ef9302
This reverts commit 6097ce0e7d59be4342db40e1bfc104d5ec88c5fa

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[mir_caffe] Switch to AvgPool2D and MaxPool2D ops (#7029)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 08:11:21 +0000 (17:11 +0900)]
[mir_caffe] Switch to AvgPool2D and MaxPool2D ops (#7029)

Switch from `PoolOp` to `AvgPool2DOp` and `MaxPool2DOp`. The former ones are deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years agoCheck dladdr return value (#7061)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Aug 2019 07:32:17 +0000 (16:32 +0900)]
Check dladdr return value (#7061)

Check dladdr return value and log if fail to load

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years agoFix unused return value (#7060)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Aug 2019 07:17:14 +0000 (16:17 +0900)]
Fix unused return value (#7060)

Fix unused return value of call for dimension valid check

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[mir_onnx] Switch GlobalAveragePool converter to AvgPool2DOp (#7049)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 07:14:22 +0000 (16:14 +0900)]
[mir_onnx] Switch GlobalAveragePool converter to AvgPool2DOp (#7049)

Switch from `PoolOp` to `AvgPool2DOp` in `GlobalAveragePool` converter. The former one is deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[exo-tflite] Make "Check.h" to use pepper instead of pp (#7038)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 30 Aug 2019 07:07:32 +0000 (16:07 +0900)]
[exo-tflite] Make "Check.h" to use pepper instead of pp (#7038)

* [exo-tflite] added pp into cmake scripts

`pp` is added into cmake scripts to use "Check.h", which includes a header in pp.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* pp to lightweight pepper::str

4 years ago[mir] Remove operation names (#7016)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 07:06:58 +0000 (16:06 +0900)]
[mir] Remove operation names (#7016)

Names on operations were difficult to maintain.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years agoFix uncatched exception (#7058)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Aug 2019 05:49:30 +0000 (14:49 +0900)]
Fix uncatched exception (#7058)

Operand::operandSize() can throw exeception because sizeOfDataType() in DataType.h can throw runtime exception

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[neurun] Resolve Division by zero in Softmax layer (#7055)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 05:02:07 +0000 (14:02 +0900)]
[neurun] Resolve Division by zero in Softmax layer (#7055)

This commit will resolve division by zero in Softmax layer

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[pepper-str] make a function in header inline (#7043)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 30 Aug 2019 02:41:38 +0000 (11:41 +0900)]
[pepper-str] make a function in header inline (#7043)

* [pepper-str] make a function in header inline

This adds `inline` keyword to `str_impl(...)` function in header.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* added inline to all str_impl

4 years ago[neurun] Implemented scheduler test with branched graph (#6926)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 02:17:48 +0000 (11:17 +0900)]
[neurun] Implemented scheduler test with branched graph (#6926)

* [neurun] Implemented scheduler test with branched graph

* Implemented scheduler test with branched graph and known execution time
* Added set time methods to ExecTime
* Refactored existing scheduler test a little bit

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* 'set' methods from ExecutionTime replaced with helper functions

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* remove profile data before test

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Review fixes

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Increased execution time for GPU in last test

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Set correct large exec time for gpu

Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
4 years ago[neurun] Prettified HE scheduler a little bit (#6982)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 01:43:27 +0000 (10:43 +0900)]
[neurun] Prettified HE scheduler a little bit (#6982)

* [neurun] Prettified HE scheduler a little bit

* Removed backend transfer time from _run_cache
* _run_cache replaced with _preferred_operations
* Profiling information existence checks added

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Review fixes

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
4 years ago[neurun] Made scheduler to shuffle backends after all nodes are profiled (#7010)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 01:39:28 +0000 (10:39 +0900)]
[neurun] Made scheduler to shuffle backends after all nodes are profiled (#7010)

[neurun] Made scheduler to shuffle backends after all nodes are already profiled

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
4 years ago[neurun] Introduce ITensorManager to be used as MemoryManager (#7048)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 00:59:05 +0000 (09:59 +0900)]
[neurun] Introduce ITensorManager to be used as MemoryManager (#7048)

Introduce ITensorManager to be used as MemoryManager instead of existing
MemoryManager in the future.

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[moco-tf] Delete FixPaddingTransform (#7042)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 30 Aug 2019 00:44:59 +0000 (09:44 +0900)]
[moco-tf] Delete FixPaddingTransform (#7042)

This will delete unused FixPaddingTransform

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[tf2tflite] Enable moco logs via TF2TFLITE_Log_Frontend (#7040)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Aug 2019 00:04:32 +0000 (09:04 +0900)]
[tf2tflite] Enable moco logs via TF2TFLITE_Log_Frontend (#7040)

Let's use TF2TFLITE_Log_Frontend instead of MOCO_LOG.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[res] Introduce UNIT_Squeeze_003 test (#7039)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 00:04:20 +0000 (09:04 +0900)]
[res] Introduce UNIT_Squeeze_003 test (#7039)

This test is for checking that `Squeeze` operation handle multiple negative
squeeze_dims or not

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[mir_tflite] Switch to AvgPool2D and MaxPool2D ops (#7024)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:59:11 +0000 (06:59 +0900)]
[mir_tflite] Switch to AvgPool2D and MaxPool2D ops (#7024)

Switch from `PoolOp` to `AvgPool2DOp` and `MaxPool2DOp`. The former ones are deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe2] Switch to AvgPool2D and MaxPool2D ops (#7032)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:52:24 +0000 (06:52 +0900)]
[mir_caffe2] Switch to AvgPool2D and MaxPool2D ops (#7032)

Switch from `PoolOp` to `AvgPool2DOp` and `MaxPool2DOp`. The former ones are deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Switch to AvgPool2D and MaxPool2D ops (#7023)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:34:27 +0000 (06:34 +0900)]
[mir_onnx] Switch to AvgPool2D and MaxPool2D ops (#7023)

Switch from `PoolOp` to `AvgPool2DOp` and `MaxPool2DOp`. The former ones are deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir2loco] Add support for AvgPool2D and MaxPool2D (#7022)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:33:27 +0000 (06:33 +0900)]
[mir2loco] Add support for AvgPool2D and MaxPool2D (#7022)

These operations are the future replacement of the `Pool` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_tflite] Switch to ReduceMean op (#7004)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:30:21 +0000 (06:30 +0900)]
[mir_tflite] Switch to ReduceMean op (#7004)

Switch from `ReduceOp` to `ReduceMeanOp`. The former one is deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Switch to ReduceMean op (#7003)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:28:37 +0000 (06:28 +0900)]
[mir_onnx] Switch to ReduceMean op (#7003)

Switch from `ReduceOp` to `ReduceMeanOp`. The former one is deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Implemented Data Format Switcher (#6932)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 19:02:44 +0000 (22:02 +0300)]
[nnc] Implemented Data Format Switcher (#6932)

* Implemented PoolOp visitor in switcher

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[neurun] Introduce AclInternalBufferManager class (#6983)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 29 Aug 2019 10:00:48 +0000 (19:00 +0900)]
[neurun] Introduce AclInternalBufferManager class (#6983)

Introduce AclInternalBufferManager class which will be used by acl's
layers

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[neurun] Fix nnfw_output_tensorinfo (#7035)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 09:48:23 +0000 (18:48 +0900)]
[neurun] Fix nnfw_output_tensorinfo (#7035)

nnfw_session::output_tensoninfo should uses output size, instead of input size.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[moco-tf] Use logo Pass (#7030)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 09:35:02 +0000 (18:35 +0900)]
[moco-tf] Use logo Pass (#7030)

* [moco-tf] Use logo Pass

This will update to use logo Pass as transformations for two Optimiziers

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

4 years ago[moco-tf] Use loco::NodeShape for inputs (#7008)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 09:20:58 +0000 (18:20 +0900)]
[moco-tf] Use loco::NodeShape for inputs (#7008)

* [moco-tf] Use loco::NodeShape for inputs

This will change fix_shape() to use loco::NodeShape for input's shape information

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

4 years ago[nnc] Add support for ReduceMean (#7002)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 08:52:38 +0000 (17:52 +0900)]
[nnc] Add support for ReduceMean (#7002)

This operation is the future replacement of the `Reduce` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Add support for AvgPool2D and MaxPool2D (#7011)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 08:52:13 +0000 (17:52 +0900)]
[nnc] Add support for AvgPool2D and MaxPool2D (#7011)

These operations are the future replacement of the `Pool` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[exo-tflite] Placeholders for TFL nodes (#7021)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 08:27:01 +0000 (17:27 +0900)]
[exo-tflite] Placeholders for TFL nodes (#7021)

* [exo-tflite] Placeholders for TFL nodes

This will add TODO comment as placeholders for TFL nodes to come

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

4 years ago[exo-tflite] Introducing TFLShapeInference (#6991)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 08:19:11 +0000 (17:19 +0900)]
[exo-tflite] Introducing TFLShapeInference (#6991)

* [exo-tflite] Introducing TFLShapeInference

This adds TFLShapeInference that infer the shape of TFL nodes and TFLShapeAnnot that passes shape from canonical node.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* adding missing graph input

* fix typo

* remove Forward word from internal class naming

4 years ago[neurun] Add iterate() to FunctionSequence (#6977)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 29 Aug 2019 07:25:31 +0000 (16:25 +0900)]
[neurun] Add iterate() to FunctionSequence (#6977)

Add iterate() to FunctionSequence for #6156

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[nnpkg_tool] Revise nnpkg_test and model2nnpkg for readable log (#7028)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 07:05:30 +0000 (16:05 +0900)]
[nnpkg_tool] Revise nnpkg_test and model2nnpkg for readable log (#7028)

`nnpkg_test`
- distinguish the run and compare result.
- shows the errors after a blank line.
- does not use `set -e` to continue after error for pretty printing.

`model2nnpkg`
- It becmome less noisy.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[nnpkg_tool] Introduce nncc-tc-to-nnpkg-tc (#7005)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 07:02:38 +0000 (16:02 +0900)]
[nnpkg_tool] Introduce nncc-tc-to-nnpkg-tc (#7005)

Introduce tool for converting nncc testcase to nnpkg testcase.
Please read README.md for usage.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[mir] Add AvgPool2D and MaxPool2D operations (#6996)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 05:55:26 +0000 (14:55 +0900)]
[mir] Add AvgPool2D and MaxPool2D operations (#6996)

These are the future replacement of the `Pool` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir] Add ReduceMean operation (#6994)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 05:55:13 +0000 (14:55 +0900)]
[mir] Add ReduceMean operation (#6994)

This is a future replacement of `Reduce` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnpkg_tool] Introduce nnpkg_test.sh (#7020)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 05:39:06 +0000 (14:39 +0900)]
[nnpkg_tool] Introduce nnpkg_test.sh (#7020)

Introduce a tool for running an nnpackage testcase.
It will run nnpackage with nnpackage_run, and compare the result.
For usage, find README.md.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[neurun] Apply InternalBufferManager to RNN on acl_cl (#6978)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 29 Aug 2019 05:35:18 +0000 (14:35 +0900)]
[neurun] Apply InternalBufferManager to RNN on acl_cl (#6978)

Apply InternalBufferManager to RNN on acl_cl

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[moco-tf] Introduce ProgressReporter (#7013)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 05:26:09 +0000 (14:26 +0900)]
[moco-tf] Introduce ProgressReporter (#7013)

* [moco-tf] Introduce PhaseEventListener

This will introduce PhaseEventListener that implements logo::PhaseEventListener that dumps Phase event logs

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

4 years agoIntroduce model2nnpackage (#6976)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 04:52:16 +0000 (13:52 +0900)]
Introduce model2nnpackage (#6976)

This patch introduces model2nnpackage.
It will take model file (either circle or tflite) and generate
containing nnpackage.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[exo-tflite] Placeholders for TFLNodes.lst (#7019)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 04:41:13 +0000 (13:41 +0900)]
[exo-tflite] Placeholders for TFLNodes.lst (#7019)

This will add TODO comments in TFLNodes.lst as placeholders for new TFL nodes to come

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Use throw instead of assert (#7006)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 29 Aug 2019 03:48:56 +0000 (12:48 +0900)]
[exo-tflite] Use throw instead of assert (#7006)

The current implementation of translateLocoTypeToTFLite may return an
invalid value if the code is built with release configuration.

This commit replaces assert with throw to prevent undefined behavior.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-log] Extract LoggingContext class (#6999)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 29 Aug 2019 03:48:35 +0000 (12:48 +0900)]
[moco-log] Extract LoggingContext class (#6999)

LoggingContext class is currently declared in Log.h, and thus it is
impossible to access this class declaration without including macros
defined in Log.h, which leads to macro name conflicts in some case.

This commit introduce a dedicated file for LoggingContext class to
allow users to access LoggingContext class without the risk of macro
name conflicts.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[nnkit] Remove empty directories (#6967)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 29 Aug 2019 01:09:26 +0000 (10:09 +0900)]
[nnkit] Remove empty directories (#6967)

All the components are now at the top-level.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Use make_shape_inference_data in fix_shape (#6998)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 00:38:47 +0000 (09:38 +0900)]
[moco-tf] Use make_shape_inference_data in fix_shape (#6998)

This will use make_shape_inference_data() for patterns of make_unique() + copy_shape_values() with ShapeInferenceData

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Enabling OperationExporter to handle TFLNode (#7001)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 00:30:55 +0000 (09:30 +0900)]
[exo-tflite] Enabling OperationExporter to handle TFLNode (#7001)

This enables OperationExporter to handle TFLNode

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Use logo::Pass for Transform (#7000)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 00:30:02 +0000 (09:30 +0900)]
[moco-tf] Use logo::Pass for Transform (#7000)

This will make moco::tf to use logo::Pass for Transform class as for first step of migration

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[nnc] Do not set / check names of operations (#6981)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 28 Aug 2019 12:47:57 +0000 (21:47 +0900)]
[nnc] Do not set / check names of operations (#6981)

Operation names are going to be removed.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir2loco] Switch to tensor names (#6974)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 28 Aug 2019 12:44:22 +0000 (21:44 +0900)]
[mir2loco] Switch to tensor names (#6974)

Do not set operation names; set tensor names instead.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Do not set names of operations (#6956)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 28 Aug 2019 12:43:14 +0000 (21:43 +0900)]
[mir_onnx] Do not set names of operations (#6956)

Remove useless setting of operation names.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[exo-tflite] Macros to wrap assert and std::runtime_error (#6919)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 10:56:13 +0000 (19:56 +0900)]
[exo-tflite] Macros to wrap assert and std::runtime_error (#6919)

* [exo-tflite] Macros to wrap assert and std::runtime_error

Two macros were added that wrap assert and std::runtime_error

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

4 years ago[neurun] Recover prepare of IFunction (#6975)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 28 Aug 2019 08:21:09 +0000 (17:21 +0900)]
[neurun] Recover prepare of IFunction (#6975)

Recover prepare of IFunction for #6156

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[mir_tflite] Do not set names of operations (#6955)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 28 Aug 2019 07:55:17 +0000 (16:55 +0900)]
[mir_tflite] Do not set names of operations (#6955)

Remove useless setting of operation names.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe] Do not set names of operations (#6953)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 28 Aug 2019 07:54:54 +0000 (16:54 +0900)]
[mir_caffe] Do not set names of operations (#6953)

Remove useless setting of operation names.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Register Transpose operator converter (#6947)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 28 Aug 2019 07:54:25 +0000 (16:54 +0900)]
[mir_onnx] Register Transpose operator converter (#6947)

It was lost not long ago after improper resolving of a merge conflict.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Add support for auto_pad attribute (#6943)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 28 Aug 2019 07:53:49 +0000 (16:53 +0900)]
[mir_onnx] Add support for auto_pad attribute (#6943)

Add support for `auto_pad` attribute to `Conv`, `AveragePool`, `MaxPool` operator converters.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe2] Do not set names of operations (#6812)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 28 Aug 2019 07:53:09 +0000 (16:53 +0900)]
[mir_caffe2] Do not set names of operations (#6812)

Remove useless setting of operation names.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[exo-tflite] ShapeInference support for Custom Op (#6622)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 07:32:51 +0000 (16:32 +0900)]
[exo-tflite] ShapeInference support for Custom Op (#6622)

* [exo-tflite] ShapeInference support for Custom Op

With this commit, ShapeInference can infer the shape of custom op.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* adds an empty line; remove visit()

4 years ago[mogo-tf] use update_stride_data and update_window_data (#6987)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 07:25:29 +0000 (16:25 +0900)]
[mogo-tf] use update_stride_data and update_window_data (#6987)

This will update to use update_stride_data() and update_window_data() in fix_shape() functions

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] make_shape_inference_data from T (#6980)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 07:17:06 +0000 (16:17 +0900)]
[moco-tf] make_shape_inference_data from T (#6980)

This will introduce template make_shape_inference_data() that creates a copy of ShapeInferenceData from src

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Adding visit(locoex::TFLRelu) into OperationExporter (#6988)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 07:12:41 +0000 (16:12 +0900)]
[exo-tflite] Adding visit(locoex::TFLRelu) into OperationExporter  (#6988)

* [exo-tflite] Making OperationExporter handle locoex::TFLRelu

This enables OperationExporter to export locoex::TFLRelu into tflite file.

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

4 years ago[exo-tflite] introducing TFLConverter class (#6986)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 06:54:14 +0000 (15:54 +0900)]
[exo-tflite] introducing TFLConverter class (#6986)

* [exo-tflite] introducing TFLConverter class

Children of this class will convert a loco node to TFL node. This class is a parent of those children.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remove graph param from

4 years ago[moco-tf] Use loco::NodeShape in copy_shapedata (#6984)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 06:53:36 +0000 (15:53 +0900)]
[moco-tf] Use loco::NodeShape in copy_shapedata (#6984)

This will change to use loco::NodeShape if exist as shape information in copy_shapedata()

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] Introduce as_feature_shape in FixShapeTransform (#6989)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 06:53:03 +0000 (15:53 +0900)]
[moco-tf] Introduce as_feature_shape in FixShapeTransform (#6989)

This will introduce as_feature_shape() that returns FeatureShape from loco::NodeShape with TFDataLayout

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[logo] Inherit PhaseRunnerMixinObservable (#6985)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 06:52:13 +0000 (15:52 +0900)]
[logo] Inherit PhaseRunnerMixinObservable (#6985)

This will update PhaseRunner to inherit PhaseRunnerMixinObservable for notification
and add call methods to send notifications

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] comment for ending namespace (#6979)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 03:51:30 +0000 (12:51 +0900)]
[exo-tflite] comment for ending namespace (#6979)

This adds comment for ending namespace

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Fix to use plier::tf::as_data_layout (#6968)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 03:50:54 +0000 (12:50 +0900)]
[moco-tf] Fix to use plier::tf::as_data_layout (#6968)

This will fix to use plier::tf::as_data_layout() from previous as_DataLayout()
and use explicit plier::tf namespace

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Function to convert canonical nodes to TFL nodes (#6939)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 03:37:08 +0000 (12:37 +0900)]
[exo-tflite] Function to convert canonical nodes to TFL nodes (#6939)

* [exo-tflite] Function to convert canonical nodes to TFL nodes

This adds a skeleton level implementation of a function that will convert canonical nodes to TFL nodes

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* copyright. fix log for knob checking

4 years ago[logo] Introduce PhaseRunnerMixinObservable (#6971)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 03:31:50 +0000 (12:31 +0900)]
[logo] Introduce PhaseRunnerMixinObservable (#6971)

This will introduce PhaseRunnerMixinObservable for Phase/Pass run stage notification

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years agoIntroduce new NNAPI test generator (#6924)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 28 Aug 2019 02:22:55 +0000 (11:22 +0900)]
Introduce new NNAPI test generator (#6924)

Move test generator into tests/nnapi/nnapi_test_generator/android-p
Introduce test generator into tests/nnapi/nnapi_test_generator/android-q-beta from current android master (not used yet)
Update README.md for introduced test generator

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[loco] Clean up deprecated FixedArityNode class (#6970)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 28 Aug 2019 02:16:12 +0000 (11:16 +0900)]
[loco] Clean up deprecated FixedArityNode class (#6970)

Let's clean up deprecated FixedArityNode class.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] update stride and window data (#6969)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 01:25:17 +0000 (10:25 +0900)]
[moco-tf] update stride and window data (#6969)

This will introduce update_stride_data() and update_window_data() common function in FixShapeTransform

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] introduce node_shape method (#6962)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 28 Aug 2019 01:08:56 +0000 (10:08 +0900)]
[moco-tf] introduce node_shape method (#6962)

* [moco-tf] introduce node_shape method

This will introduce node_shape() method in FixShapeTransform that returns NodeShape from Node as a common shape information for dialect independent

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* header for shape_known

4 years ago[neurun] Fix indentation in DataflowExecutor.cc (#6840)
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 28 Aug 2019 00:59:21 +0000 (09:59 +0900)]
[neurun] Fix indentation in DataflowExecutor.cc (#6840)

Fix indentation in DataflowExecutor.cc, remove TODO comment.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
4 years ago[mir] Add Graph::create() overload without 'name' parameter (#6951)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 27 Aug 2019 10:28:59 +0000 (19:28 +0900)]
[mir] Add Graph::create() overload without 'name' parameter (#6951)

This is a first step to remove names from operations.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnkit] Clean up redundant requires (#6946)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 27 Aug 2019 08:23:06 +0000 (17:23 +0900)]
[nnkit] Clean up redundant requires (#6946)

nnkit no longer requires moco and tfinfo module.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[exo-tflite] TFLRelu uses exo::FixedArityNode (#6952)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 27 Aug 2019 08:17:53 +0000 (17:17 +0900)]
[exo-tflite] TFLRelu uses exo::FixedArityNode (#6952)

Since loco::FixedArityNode is being deprecated, TFLRelu now uses exo::FixedArityNode.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[logo] Introduce PhaseEventListener and enums (#6922)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 27 Aug 2019 08:14:46 +0000 (17:14 +0900)]
[logo] Introduce PhaseEventListener and enums (#6922)

This will introduce PhaseEventListener as interface for event listener while running the Phase, Pass

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[logo] Fix to make same pattern (#6954)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 27 Aug 2019 08:14:24 +0000 (17:14 +0900)]
[logo] Fix to make same pattern (#6954)

This will fix Restart PhaseRunner to follow Saturate of run() return value pattern

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] introduce make_shape_inference_data (#6960)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 27 Aug 2019 08:13:57 +0000 (17:13 +0900)]
[moco-tf] introduce make_shape_inference_data (#6960)

This will introduce make_shape_inference_data() that makes ShapeInferenceData from NodeShape shape information

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[moco-tf] DepthwiseFilter in ShapeInferenceData (#6957)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 27 Aug 2019 07:43:47 +0000 (16:43 +0900)]
[moco-tf] DepthwiseFilter in ShapeInferenceData (#6957)

This will update to support DepthwiseFilter in ShapeInferenceData

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