platform/core/ml/nnfw.git
5 years ago[moco/tf] Introduce NodeShape (#3926)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 24 Jun 2019 01:20:58 +0000 (10:20 +0900)]
[moco/tf] Introduce NodeShape (#3926)

* [moco/tf] Introduce NodeShape

This will introduce NodeShape to access shape inference result(shape information) of each loco::Node

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

* apply another comment

5 years ago[moco/tf] revise test for shape inf feature (#3931)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 24 Jun 2019 00:07:11 +0000 (09:07 +0900)]
[moco/tf] revise test for shape inf feature (#3931)

This will revise feature_shape accessors test in shape inference data to remove implementation detail and focus on interface testing

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[pepper-strcast] Use proper target name (#3917)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Sun, 23 Jun 2019 23:56:30 +0000 (08:56 +0900)]
[pepper-strcast] Use proper target name (#3917)

pepper-strcast currently exposes itself as pepper-string.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoExtract moco-onnx from moco (#3919)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Sun, 23 Jun 2019 23:55:18 +0000 (08:55 +0900)]
Extract moco-onnx from moco (#3919)

This commit extracts moco-onnx from moco in order to make it easy to
manage internal dependencies.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] revise test for shape inf bias (#3930)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 23 Jun 2019 23:48:20 +0000 (08:48 +0900)]
[moco/tf] revise test for shape inf bias (#3930)

This will revise bias_shape accessors test in shape inference data

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[mocotest/tf] add avgpool2d_001 (#3928)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 23 Jun 2019 23:46:42 +0000 (08:46 +0900)]
[mocotest/tf] add avgpool2d_001 (#3928)

This will add AvgPool_001 test for VALID padding

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[moco/tf] revise test for shape inf filter (#3920)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 21 Jun 2019 09:36:19 +0000 (18:36 +0900)]
[moco/tf] revise test for shape inf filter (#3920)

This will revise filter_shape accessors test in shape inference data

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[ann-ref] Check required targets (#3923)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 08:42:36 +0000 (17:42 +0900)]
[ann-ref] Check required targets (#3923)

Now, ann-ref build gets stuck with error message if required targets are
missing.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[locomotiv] add method for condition check (#3912)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 21 Jun 2019 07:51:46 +0000 (16:51 +0900)]
[locomotiv] add method for condition check (#3912)

There are many validation check if (...) throw ... . This commit adds a function to do this with one call.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years ago[moco/tf] support bias in ShapeInferenceData (#3913)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 21 Jun 2019 07:41:48 +0000 (16:41 +0900)]
[moco/tf] support bias in ShapeInferenceData (#3913)

This will introduce bias attribute accessor in ShapeInferenceData

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[moco-log] Use Builtin Hermes Console Reporter (#3914)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 06:49:30 +0000 (15:49 +0900)]
[moco-log] Use Builtin Hermes Console Reporter (#3914)

This commit replaces locally-implemented reporter with the one in
hermes-std module.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoExtract moco-log from moco (#3897)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 05:43:51 +0000 (14:43 +0900)]
Extract moco-log from moco (#3897)

Let's extract "moco-log" and manage its internal dependencies.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[tf2tflite] Use TargetRequire_Return (#3910)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 05:32:02 +0000 (14:32 +0900)]
[tf2tflite] Use TargetRequire_Return (#3910)

This commit replaces ensure_required_targets (which is local to
tf2tflite) with TargetRequire_Return.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] introduce domain in ShapeInferenceData (#3901)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 21 Jun 2019 05:13:24 +0000 (14:13 +0900)]
[moco/tf] introduce domain in ShapeInferenceData (#3901)

* [moco/tf] introduce domain in ShapeInferenceData

This will introduce domain property in ShapeInferenceData

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

5 years agoRequire moco from nnkit (#3909)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 04:57:08 +0000 (13:57 +0900)]
Require moco from nnkit (#3909)

nnkit-moco-tf in nnkit needs moco, and thus this dependency should be
explicit in nnkit.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[locomotiv] BiasEncode (#3888)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 21 Jun 2019 04:40:21 +0000 (13:40 +0900)]
[locomotiv] BiasEncode (#3888)

* [locomotiv] BiasEncode

This commit adds BiasEncode and its test cases for locomotiv.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* checking input rank == 1

5 years ago[moco/tf] Setting shape of Pull from user-provided input data (#3889)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 21 Jun 2019 04:40:05 +0000 (13:40 +0900)]
[moco/tf] Setting shape of Pull from user-provided input data (#3889)

This enables shape of Pull to be filled from user-provided input data.
(Assuming the user-provided input data is already stored in CompilerArgs class)

Note that this was originally writte while Conv2D was written to figure out unknown dim from user-provided shape info.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years agoExtract moco tests from moco (#3907)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 04:22:17 +0000 (13:22 +0900)]
Extract moco tests from moco (#3907)

This commit extracts mocotest projects (mocotest-tf and moctest-onnx)
from moco in order to break dependency cycle between moco and nnkit.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[onnxkit] Update README.md (#3900)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 04:19:23 +0000 (13:19 +0900)]
[onnxkit] Update README.md (#3900)

Now, onnxkit's README.md is compatible with Doxygen.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoAdd TargetRequire module (#3895)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 04:07:26 +0000 (13:07 +0900)]
Add TargetRequire module (#3895)

This commit adds TargetRequire module which includes the following
CMake helpers which simplifies required target check:
- TargetRequire_Check
- TargetRequire_Assert
- TargetRequire_Return

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco.tf] Remove load_model unittest (#3905)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 03:05:22 +0000 (12:05 +0900)]
[moco.tf] Remove load_model unittest (#3905)

This commit removes "load_model" test; Now tf2tflite is responsoble for
tests of this kind.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco.tf] Add Conversion.md (#3894)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 01:55:21 +0000 (10:55 +0900)]
[moco.tf] Add Conversion.md (#3894)

This commit adds Conversion.md which describes how to express each
T/F operation on top of loco.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[pepper-strcast] Initial commit (#3896)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 01:44:53 +0000 (10:44 +0900)]
[pepper-strcast] Initial commit (#3896)

This commit introduces pepper-strcast which will hold various
string-to-value casting helpers.

The initial version supports string-to-int casting.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[tfldump] Update README.md (#3899)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 01:33:24 +0000 (10:33 +0900)]
[tfldump] Update README.md (#3899)

Now, tfldump's README.md is compatible with Doxygen.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[hermes-std] Initial commit (#3893)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 21 Jun 2019 00:00:09 +0000 (09:00 +0900)]
[hermes-std] Initial commit (#3893)

This commit introduces hermes-std which includes basic hermes extensions
such as console reporter.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[locomotiv] BiasAdd (#3877)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 20 Jun 2019 23:18:53 +0000 (08:18 +0900)]
[locomotiv] BiasAdd (#3877)

* [locomotiv] BiasAdd

This commit adds BiasAdd and test case for locomotiv.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* checking loco::Domain::Tensor

* msg

* setting the domain of input[1] to loco::Domain::Bias

* fix message

* more check

5 years ago[loco exporter] Naming multiple graph I/O from loco (#3880)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 20 Jun 2019 22:27:31 +0000 (07:27 +0900)]
[loco exporter] Naming multiple graph I/O from loco (#3880)

* [loco exporter] Naming multiple graph I/O from loco

Previously loco exporter only support single graph input and single
graph output. With this commit, it now can support multiple inputs and
outputs with I/O tensor name copied from loco.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Review feedback: better comment look

5 years ago[locop] Introduce NodeDesc class (#3891)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Jun 2019 10:20:11 +0000 (19:20 +0900)]
[locop] Introduce NodeDesc class (#3891)

* [locop] Introduce NodeDesc class

This commit introduces NodeDesc class and refactors the internal implementation of
LinearV1 formatter using this class.

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

5 years ago[tftestinfo] Remove T/F dependencies (#3892)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Jun 2019 09:09:40 +0000 (18:09 +0900)]
[tftestinfo] Remove T/F dependencies (#3892)

tftestinfo now does not depend on TensorFlow.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[stdex] Update README.md (#3886)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Jun 2019 06:13:43 +0000 (15:13 +0900)]
[stdex] Update README.md (#3886)

This commit updates stdex's README.md to be compatible with Doxygen.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[tfkit] Support conversion from pb (#3883)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Jun 2019 01:39:05 +0000 (10:39 +0900)]
[tfkit] Support conversion from pb (#3883)

tfkit convert command now supports pb-to-JSON conversion.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[enco.caffe] Remove local tests (#3884)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Jun 2019 01:38:57 +0000 (10:38 +0900)]
[enco.caffe] Remove local tests (#3884)

enco caffe test framework no longer uses these local tests.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] arrange concat validate codes (#3881)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 19 Jun 2019 22:54:20 +0000 (07:54 +0900)]
[moco/tf] arrange concat validate codes (#3881)

This will move(arrange) codes in build to validate for ConcatV2

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[mirunner] Update README.md (#3857)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 19 Jun 2019 17:49:10 +0000 (02:49 +0900)]
[mirunner] Update README.md (#3857)

This commit updates mirunner's README.md to be compatible with Doxygen.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[enco.caffe] Use shared test suite (#3882)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 19 Jun 2019 10:55:41 +0000 (19:55 +0900)]
[enco.caffe] Use shared test suite (#3882)

This commit updates enco caffe test frameworks to use the shared
test suite introduced recently.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[tf2tflite] Add BiasAdd 000 testcase (#3876)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 19 Jun 2019 07:11:56 +0000 (16:11 +0900)]
[tf2tflite] Add BiasAdd 000 testcase (#3876)

This commit adds BiasAdd 000 testcase which includes a simple T/F network
that performs BiasAdd.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco exporter] Support BiasAdd<Tensor> (#3875)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 19 Jun 2019 05:24:42 +0000 (14:24 +0900)]
[loco exporter] Support BiasAdd<Tensor> (#3875)

This commit supports BiasAdd loco node of Tensor domain for loco
exporter.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[moco/tf] fix style for filter_shape (#3866)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 19 Jun 2019 05:22:45 +0000 (14:22 +0900)]
[moco/tf] fix style for filter_shape (#3866)

* [moco/tf] fix style for filter_shape

This will fix style of filter_shape() like existing feature_shape()

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

* throw

* fix typo

5 years ago[cli] Update README.md (#3867)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 19 Jun 2019 04:43:11 +0000 (13:43 +0900)]
[cli] Update README.md (#3867)

This commit updates cli's README.md to be compatible with Doxygen.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco exporter] Support BiasEncode (#3872)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 19 Jun 2019 04:40:38 +0000 (13:40 +0900)]
[loco exporter] Support BiasEncode (#3872)

This commit supports BiasEncode loco node for loco exporter

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[moco/tf] throw instead of assert (#3874)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 19 Jun 2019 04:40:13 +0000 (13:40 +0900)]
[moco/tf] throw instead of assert (#3874)

This will use throw runtime_error if rank mismatches for ShareInferenceData

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[moco/tf] FixPaddingTransform for Conv2D (#3863)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 19 Jun 2019 03:53:45 +0000 (12:53 +0900)]
[moco/tf] FixPaddingTransform for Conv2D (#3863)

* [moco/tf] FixPaddingTransform for Conv2D

This commit adds FixPaddingTransform implementation and test cases for Conv2D.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* comment, win_-> ker

5 years agoAdd BVLCCaffeTest resource (#3868)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 19 Jun 2019 03:45:58 +0000 (12:45 +0900)]
Add BVLCCaffeTest resource (#3868)

This commit adds BVLCCaffeTest resource which includes various caffe
prototxt for testing.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] FixShapeTransform for Conv2D (#3858)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 11:49:54 +0000 (20:49 +0900)]
[moco/tf] FixShapeTransform for Conv2D (#3858)

This commit adds FixShapeTransform for Conv2D and two test cases extracted from Inception_v3.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years ago[loco exporter] Support TensorConcat (#3861)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 18 Jun 2019 11:49:16 +0000 (20:49 +0900)]
[loco exporter] Support TensorConcat (#3861)

This commit supports TensorConcat loco node for loco exporter.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[tf2tflite] Add TF_IV3_Conv2D_000 (#3859)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 11:42:12 +0000 (20:42 +0900)]
[tf2tflite] Add TF_IV3_Conv2D_000 (#3859)

This commit adds TF_IV3_Conv2D_000 test which simulates
"InceptionV3/InceptionV3/Conv2d_1a_3x3/Conv2D" node in inception v3
model.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco exporter] Support Conv2D (#3849)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 18 Jun 2019 10:44:13 +0000 (19:44 +0900)]
[loco exporter] Support Conv2D (#3849)

This commit supports Conv2D node for loco exporter

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[moco/tf] Methods to handle feature in ShapeInferenceData (#3855)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 10:11:40 +0000 (19:11 +0900)]
[moco/tf] Methods to handle feature in ShapeInferenceData (#3855)

* [moco/tf] Methods to handle feature in ShapeInferenceData

This commit adds getter and setter for feature into/from ShapeInferenceData.

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

5 years ago[enco] Cleanup caffe test framework (#3856)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 09:59:44 +0000 (18:59 +0900)]
[enco] Cleanup caffe test framework (#3856)

This commit introduce TESTCASE_BASE_DIR variable which indicates where
testcases are located.

This is a preliminary work for shared caffe testcases.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[nnkit.support.tf] Remove dtype calls (#3854)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 09:56:52 +0000 (18:56 +0900)]
[nnkit.support.tf] Remove dtype calls (#3854)

As a step to decouple tftestinfo from TensorFlow, this commit removes
dtype method calls from nnkit.support.tf.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] Addding padding data annotation into Conv2D (#3853)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 09:41:28 +0000 (18:41 +0900)]
[moco/tf] Addding padding data annotation into Conv2D (#3853)

This commit adds padding data annotation into Conv2D, which will be used by transforms after graph building.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years ago[tfkit] Introduce convert command (#3852)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 09:35:33 +0000 (18:35 +0900)]
[tfkit] Introduce convert command (#3852)

This commit extends tfkit with convert command. The current
implementation supports only conversion from pbtxt into json.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[tf2tflit] Add TF_IV3_AvgPool_GlobalPooling test (#3851)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 07:34:34 +0000 (16:34 +0900)]
[tf2tflit] Add TF_IV3_AvgPool_GlobalPooling test (#3851)

This test corresponds to the last AvgPool node in inception v3 that
performs global average pooling.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[tf2tflite] Add TF_IV3_AvgPool_Module test (#3850)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 07:27:13 +0000 (16:27 +0900)]
[tf2tflite] Add TF_IV3_AvgPool_Module test (#3850)

This commit adds TF_IV3_AvgPool_Modeul test which covers all the AvgPool
nodes in IV3 except the last one.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[tf2tflite] Add TF_IV3_MaxPool test (#3847)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 07:26:55 +0000 (16:26 +0900)]
[tf2tflite] Add TF_IV3_MaxPool test (#3847)

This commit adds TF_IV3_MaxPool test.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] fix shape for feature decode (#3842)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 07:21:39 +0000 (16:21 +0900)]
[moco/tf] fix shape for feature decode (#3842)

* [moco/tf] fix shape for feature decode

This will correct fix shape for feature decode, output as tensor from feature input

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

5 years ago[moco/tf] fix shape for filter encode (#3844)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 07:10:56 +0000 (16:10 +0900)]
[moco/tf] fix shape for filter encode (#3844)

* [moco/tf] fix shape for filter encode

This will implement fix shape for filter encode, output as filter from tensor input

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

5 years ago[moco/tf] fix shape for feature encode (#3843)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 06:55:21 +0000 (15:55 +0900)]
[moco/tf] fix shape for feature encode (#3843)

This will correct fix shape for feature encode, output as feature from tensor input

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[tf2tflite] Sync .pbtxt and .info on change (#3838)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 06:48:17 +0000 (15:48 +0900)]
[tf2tflite] Sync .pbtxt and .info on change (#3838)

The current implementation does not reflect the changes on .pbtxt and
.info.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoIntroduce nncc_find_resource (#3823)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 06:47:34 +0000 (15:47 +0900)]
Introduce nncc_find_resource (#3823)

* Introduce nncc_find_resource

This commit introduces nncc_find_resource which allows us to share the
common resource files across various modules.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Use NAME instead of PREFIX

5 years ago[i5diff] Add missing license (#3839)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 06:01:18 +0000 (15:01 +0900)]
[i5diff] Add missing license (#3839)

This commit adds missing license notice.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco exporter] Support FilterEncode (#3845)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 18 Jun 2019 06:00:26 +0000 (15:00 +0900)]
[loco exporter] Support FilterEncode (#3845)

This commit supports FilterEncode node for loco exporter

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[tf2tflite] Add MaxPool 000 testcase (#3827)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 05:57:34 +0000 (14:57 +0900)]
[tf2tflite] Add MaxPool 000 testcase (#3827)

* [tf2tflite] Add MaxPool 000 testcase

This commit adds MaxPool 000 testcase which checks whether tf2tflite is
able to convert a simple tf model only with one MaxPool operation.

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

5 years ago[moco/tf] tensor and filter for ShapeInferenceData (#3837)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 05:11:55 +0000 (14:11 +0900)]
[moco/tf] tensor and filter for ShapeInferenceData (#3837)

This will add getter of tensor and setter of filter for ShapeInferenceData

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[tf2tflite] Use i5diff to detect shape mismatch (#3836)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 04:08:01 +0000 (13:08 +0900)]
[tf2tflite] Use i5diff to detect shape mismatch (#3836)

It turns out that h5diff exited with zero even in the presence of
shape mismatch.

This commit updates tf2tflite test framework to use i5diff (instead of
h5diff) to detect such shape mismatch cases.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco exporter] Refactor export Transpose (#3835)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 18 Jun 2019 03:50:17 +0000 (12:50 +0900)]
[loco exporter] Refactor export Transpose (#3835)

FeatureEncode, FeatureDecode are now exported as TRANSPOSE in tflite
when they are not identity(NHWC). In future, FilterEncode will be as
well. This commit refactors exporting TRANSPOSE in a form reusable
by FilterEncode.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[locomotiv] Session setting input may throw error (#3714)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 18 Jun 2019 03:45:15 +0000 (12:45 +0900)]
[locomotiv] Session setting input may throw error (#3714)

* [locomotiv] Session setting input may throw error

Previously Session::set_input() returns false on undesired cases. With
this commit, set_input() throws runtime error on such cases.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Review feedback: amend comment

5 years agoIntroduce i5diff (#3832)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 03:20:47 +0000 (12:20 +0900)]
Introduce i5diff (#3832)

* Introduce i5diff

This commit introduces i5diff which takes two HDF5 files (that
nnkit HDF5 exports generates) and compares them.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Enable format check

* Fix typos

5 years ago[moco/tf] remove unnecessary call to toupper (#3834)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 03:03:18 +0000 (12:03 +0900)]
[moco/tf] remove unnecessary call to toupper (#3834)

This will remove unnecessary call to toupper of pad type string as it is already uppercase when created

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[loco] Enable Conv2D pad setter (#3833)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Jun 2019 03:00:28 +0000 (12:00 +0900)]
[loco] Enable Conv2D pad setter (#3833)

This commit enable (temporarily disabled) Conv2D pad setter.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] add log for fix padding avgpool2d (#3829)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 02:25:35 +0000 (11:25 +0900)]
[moco/tf] add log for fix padding avgpool2d (#3829)

* [moco/tf] add log for fix padding avgpool2d

This will add result pad values of fix padding of AvgPool2D node

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* move LOGGER to top of function

5 years ago[moco/tf] Adding BiasAdd (#3815)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 02:23:31 +0000 (11:23 +0900)]
[moco/tf] Adding BiasAdd (#3815)

[moco/tf] Adding BiasAdd

This comits adds BiasAdd for moco/tf.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
Signed-off-by: Pavel Iliutchenko p.iliutchenk@samsung.com
5 years ago[moco/tf] provided helper for validate methods (#3804)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 18 Jun 2019 01:23:09 +0000 (04:23 +0300)]
[moco/tf] provided helper for validate methods (#3804)

* [moco/tf] provided helper for frontend validate method

provided helper for frontend validate method

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

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
5 years ago[moco/tf] Fix padding for MaxPool2D (#3805)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 01:17:49 +0000 (10:17 +0900)]
[moco/tf] Fix padding for MaxPool2D (#3805)

* [moco/tf] Fix padding for MaxPool2D

This will fix padding for MaxPool2D: same as AvgPool2D

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

* fix pad formula

* fix typo

5 years ago[moco/tf] test of shape inference for avgpool2d (#3825)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Jun 2019 01:09:01 +0000 (10:09 +0900)]
[moco/tf] test of shape inference for avgpool2d (#3825)

This wll add test of TestShapeTransform AvgPool2D for SAME and VALID padding type

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[loco exporter] Support AvgPool2D (#3820)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 17 Jun 2019 23:23:18 +0000 (08:23 +0900)]
[loco exporter] Support AvgPool2D (#3820)

This commit supports AvgPool2D loco node.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[angkor] Introduce README.md (#3331)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 17 Jun 2019 22:32:53 +0000 (07:32 +0900)]
[angkor] Introduce README.md (#3331)

* [angkor] Introduce README.md

This commit will add README file for `angkor`

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

* Add words

* Fix headlines

5 years ago[tf2tflite] Ignore name mismatch on testing (#3826)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Jun 2019 11:20:01 +0000 (20:20 +0900)]
[tf2tflite] Ignore name mismatch on testing (#3826)

tfttflite now does not count tensor name mismatch as a test failure.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] Test pbtxt extracted from inception_v3 (#3824)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 17 Jun 2019 11:16:35 +0000 (20:16 +0900)]
[moco/tf] Test pbtxt extracted from inception_v3 (#3824)

These test pbtxt files are extracted from inception_v3, containing 4, 7, 10 nodes respectively.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years ago[moco/tf] remove unnecessary comment (#3822)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 17 Jun 2019 10:44:28 +0000 (19:44 +0900)]
[moco/tf] remove unnecessary comment (#3822)

This will remove unnecessary comment about padding

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[nnkit-HDF5] Use index instead of name (#3821)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Jun 2019 10:42:30 +0000 (19:42 +0900)]
[nnkit-HDF5] Use index instead of name (#3821)

Previously, nnkit HDF5 export uses a tensor name when it create a
dataset. With this commit, nnkit HDF5 export uses a tensor index
instead.

This commit also updates nnkit HDF5 import action accordingly.

To maintain backward compatibility, HDF5 export stores the name of
each tensor as an independent attribute. This additional attribute
allows users to detect name mismatch same as before.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[moco/tf] store padding case insensitive (#3819)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 17 Jun 2019 10:26:10 +0000 (19:26 +0900)]
[moco/tf] store padding case insensitive (#3819)

This will change to store padding string as case insensitive as it will be stored once and used many

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[moco/tf] fix padding for avgpool2d (#3816)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 17 Jun 2019 10:23:23 +0000 (19:23 +0900)]
[moco/tf] fix padding for avgpool2d (#3816)

* [moco/tf] fix padding for avgpool2d

This will fox padding calculation formula for AvgPool2D

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* with dilation and log

5 years ago[loco exporter] Refactor Feature Codec export (#3818)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 17 Jun 2019 10:02:41 +0000 (19:02 +0900)]
[loco exporter] Refactor Feature Codec export (#3818)

* [loco exporter] Refactor Feature Codec export

This commit amends detail structure to export FeatureEncode and
FeatureDecode nodes. Mainly, it redefine 'isIdentity()' utility function
and rename 'exportPermutation' into 'exportFeatureTranspose'

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Review fix: rename and notice

5 years ago[nnkit-intf] Update README.md (#3817)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Jun 2019 09:26:16 +0000 (18:26 +0900)]
[nnkit-intf] Update README.md (#3817)

This commit updates nnkit-intf's README.md to be compatible with
Doxygen.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco exporter] General use of checking padding (#3811)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 17 Jun 2019 09:13:06 +0000 (18:13 +0900)]
[loco exporter] General use of checking padding (#3811)

* [loco exporter] General use of checking padding

This commit fixes getOpPadding function. It now supports SAME padding.
Also function signature is generalized to deal with any padding, not just
for MaxPool2d node.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Review fix: careful about unsigned variable

5 years ago[moco/tf] Fix shape transformation for AvgPool2D (#3812)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 17 Jun 2019 07:23:50 +0000 (16:23 +0900)]
[moco/tf] Fix shape transformation for AvgPool2D (#3812)

This will fix shape transformation formula for AvgPool2D with padding type

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[moco/tf] fix maxpool2d shape calculation (#3801)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 17 Jun 2019 07:04:53 +0000 (16:04 +0900)]
[moco/tf] fix maxpool2d shape calculation (#3801)

* [moco/tf] fix maxpool2d shape calculation

This will fix maxpool2d shape calculation as like avgpool2d
- fix also op test model
- add PaddingData annotation

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

* fix typo

* rename

5 years ago[tf2tflite] Introduce test infrastructure (#3809)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Jun 2019 06:59:07 +0000 (15:59 +0900)]
[tf2tflite] Introduce test infrastructure (#3809)

* [tf2tflite] Introduce test infrastructure

This commit implements very basic test infrastructure for tf2tflite.

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

* Update testall

5 years ago[moco/tf] Add comma to logging (#3813)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 17 Jun 2019 05:10:20 +0000 (14:10 +0900)]
[moco/tf] Add comma to logging (#3813)

This will add comma in log string of ShapeTransform of AvgPool2D

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[tftestinfo] isFloatTensor as a const method (#3798)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Jun 2019 03:14:05 +0000 (12:14 +0900)]
[tftestinfo] isFloatTensor as a const method (#3798)

isFloatTensor does not update the content of ParsedTensor.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco exporter] Parse and export graph I/O name (#3803)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 17 Jun 2019 02:02:30 +0000 (11:02 +0900)]
[loco exporter] Parse and export graph I/O name (#3803)

* [loco exporter] Parse and export graph I/O name

Graph input and output names are parsed from loco graph's information
and then exported as name of input and output tensors.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Fix typo

5 years ago[locop] Introduce SymbolTable alias (#3794)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Jun 2019 00:08:47 +0000 (09:08 +0900)]
[locop] Introduce SymbolTable alias (#3794)

This commit introduces SymbolTable alias. This alias make it easy to
refactor code layout.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco] File-level comments for tensorflow.test.cpp (#3799)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 14 Jun 2019 09:53:19 +0000 (18:53 +0900)]
[loco] File-level comments for tensorflow.test.cpp (#3799)

This commit adds file-level comments at the top of tensorflow.test.cpp.
These file-level comments are valid for all the tests in this file.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco] Introduce TensorBiasAdd node (#3783)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 14 Jun 2019 09:14:05 +0000 (18:14 +0900)]
[loco] Introduce TensorBiasAdd node (#3783)

This commit introduces TensorBiasAdd node.

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[loco exporter] FeatureCodec identity export (#3795)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 14 Jun 2019 09:09:05 +0000 (18:09 +0900)]
[loco exporter] FeatureCodec identity export (#3795)

Previously FeatureCodec nodes tried to be deleted when they are
identity, but that was not successful. This commit export those as
identity, i.e. CONCATENTATION with one input.

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[moco/tf] simplify adding annotation cleaning (#3796)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 14 Jun 2019 08:26:33 +0000 (17:26 +0900)]
[moco/tf] simplify adding annotation cleaning (#3796)

This will rewrite ClearAnnotTransform so that adding cleaning will be bit simple

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[moco/tf] use auto for types in FixShapeTransform (#3793)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 14 Jun 2019 08:18:21 +0000 (17:18 +0900)]
[moco/tf] use auto for types in FixShapeTransform (#3793)

This will fix to use auto for types in FixShapeTransform methods

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[moco/tf] Implement pad fixing for AvgPool2D (#3790)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 14 Jun 2019 08:09:28 +0000 (17:09 +0900)]
[moco/tf] Implement pad fixing for AvgPool2D (#3790)

This will implement pad fixing for AvgPool2D

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[moco/tf] Conv2D test for the 1st Conv2D in inception v3 (#3787)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 14 Jun 2019 07:38:02 +0000 (16:38 +0900)]
[moco/tf] Conv2D test for the 1st Conv2D in inception v3 (#3787)

This adds Conv2D test for the 1st Conv2D in inception v3.
This test failed because the input name is a form of "input:0", which was not correctly processed by moco before.

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