박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 12 Jun 2019 09:27:19 +0000 (18:27 +0900)]
[loco] Expose verifier and codec through loco.h (#3749)
This commit updates loco.h to include verifier and permuting codec.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 12 Jun 2019 08:51:58 +0000 (17:51 +0900)]
[moco/tf] class storing user-provided compiler arguments (#3734)
* [moco/tf] class storing user-provided compiler arguments
When a user run the compiler with arguments, these arguments are parsed and stored into this class.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* Using default constructor
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 12 Jun 2019 05:58:56 +0000 (14:58 +0900)]
[locomotiv] Conv2D (padding is not yet added) (#3725)
* [locomotiv] Conv2D (padding is not yet added)
This adds Conv2D implementation of locomotiv. Padding is not implemented yet.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* revised per comments
* Fixed type. Added TODO
* int to uint32_t
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 12 Jun 2019 05:33:40 +0000 (14:33 +0900)]
[moco/tf] a test case for Conv2D (#3728)
This adds Conv2D_000 test case for moco/tf.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 12 Jun 2019 04:48:13 +0000 (13:48 +0900)]
[loco] Introduce CanonicalNode interface (#3743)
This commit introduces CanonicalNode interface, and rewrites Forward
node as an example.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 12 Jun 2019 03:45:55 +0000 (12:45 +0900)]
[locomotiv] Add MaxPool2D test case for padding (#3742)
This commit test MaxPool2D execution with padding support.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 12 Jun 2019 03:45:33 +0000 (12:45 +0900)]
[moco/tf] Clean frontend annotations (#3740)
This will clean frontend temporary annotations
- remove test that checks shape information
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 12 Jun 2019 01:54:34 +0000 (10:54 +0900)]
[loco] Introduce CanonicalOpcode enum class (#3741)
This commit introduces CanonicalOpcode enum class which serves as a
unique tag for each CanonicalNode.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 11 Jun 2019 10:38:18 +0000 (19:38 +0900)]
[moco/tf] Test case for Concat axis with -1 (#3721)
* [moco/tf] Test case for Concat axis with -1
This will fill the test code for Cocat axis with -1 value
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* check values
* update comment and formula
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Jun 2019 10:04:06 +0000 (19:04 +0900)]
[loco] Extend Node with dialect method (#3730)
This commit extends Node with dialect method as a step toward
multi-dialect support.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 11 Jun 2019 10:03:51 +0000 (19:03 +0900)]
[moco/tf] Enable concat inference test (#3724)
This will enable full Concat inference test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 11 Jun 2019 10:02:09 +0000 (19:02 +0900)]
[loco] Introduce AvgPool2D (#3720)
* [loco] Introduce AvgPool2D
This will introduce AvgPool2D for average pool operator.
Attributes are same as that of exising MaxPool2D.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add divisor
* rebase
* rebase and add todo
* use full, valid
* uncomment pad
* update note
* use convention
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Jun 2019 07:19:20 +0000 (16:19 +0900)]
[loco] Introduce CanonicalDialect singleton (#3729)
This commit introduces CanonicalDialect singleton which serves as an
in-memory unique identifier.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Jun 2019 04:18:16 +0000 (13:18 +0900)]
[loco] Enable MaxPool2D Pad setter (#3723)
This commit enables (temporarily disabled) MaxPool2D Pad setter, and add
a related test.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 11 Jun 2019 03:06:45 +0000 (12:06 +0900)]
[moco/tf] add include for stringstream (#3722)
This will add include of sstream that was missed in previous commit
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 11 Jun 2019 03:05:06 +0000 (12:05 +0900)]
[locomotiv] MaxPool2D support padding (#3719)
* [locomotiv] MaxPool2D support padding
By this commit, MaxPool2D node execution is able to deal with padding.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Review feedback: local function name
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 11 Jun 2019 02:20:27 +0000 (11:20 +0900)]
[locomotiv] Support FilterEncode execution (#3716)
This commit supports FilterEncode node execution.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 11 Jun 2019 01:00:14 +0000 (10:00 +0900)]
[locomotiv] Combine Session test in one file (#3700)
Previously Session tests was divided into two files, public and internal
test. This commit combine them into one.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Jun 2019 00:56:50 +0000 (09:56 +0900)]
[loco] Introduce replace helper (#3697)
This commit introduce "replace" helper which facilitate graph rewriting.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Jun 2019 00:55:35 +0000 (09:55 +0900)]
[loco] Rewrite FixedArityNode as a mix-in (#3699)
* [loco] Rewrite FixedArityNode as a mix-in
FixedArityNode now serves as a mix-in rather than a concrete
implementation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Inherit Base
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 10 Jun 2019 23:43:47 +0000 (08:43 +0900)]
[moco/tf] Implement fix_shape for TensorConcat (#3694)
* [moco/tf] Implement fix_shape for TensorConcat
This will implement fix_shape in shape inference for TensorConcat node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add assert and comment
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 10 Jun 2019 10:01:33 +0000 (19:01 +0900)]
[moco/tf] const test with shape inference (#3709)
* [moco/tf] const test with shape inference
This will add test of ShapeInferenceData for ConstGen node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* use name shape
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 10 Jun 2019 07:41:01 +0000 (16:41 +0900)]
[locomotiv] Amend runtime error message for executions (#3712)
This commit edits runtime error messages for executions. It unifies
message format and style and correct some wrong infos.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 10 Jun 2019 07:29:11 +0000 (16:29 +0900)]
[moco/tf] Dump ShapeInferenceData for outputs (#3695)
This will dump ShapeInferenceData for output nodes with moco log library
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 10 Jun 2019 01:58:04 +0000 (10:58 +0900)]
[locomotiv] Execution verify and annotate domain info (#3701)
This commit makes use of domain annotation tools in node executions.
Now node executions check appropriate domain info preparation, and
annotate appropriate domain info on execution run.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 5 Jun 2019 06:39:10 +0000 (15:39 +0900)]
[locomotiv] Node domain annotation for Session (#3682)
Session now annotate node domain on input setting, and delete annotated
domain information on destruction.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 5 Jun 2019 04:32:56 +0000 (13:32 +0900)]
[moco/tf] Implement fix_shape for ConstGen (#3692)
This will implement fix_shape in shape inference for ConstGen node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 5 Jun 2019 03:54:47 +0000 (12:54 +0900)]
[moco/tf] Implement fix_shape for Pull (#3693)
This will implement fix_shape in shape inference for Pull node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Jun 2019 03:37:48 +0000 (12:37 +0900)]
[loco] Add Conv2D_Float_000 testcase (#3691)
* [loco] Add Conv2D_Float_000 testcase
This commit adds TensorFlowTest.Conv2D_Float_000 testcase which
checks whether loco is able to encode a simple TensorFlow conv2d
network.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Update per feedback
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 5 Jun 2019 01:54:49 +0000 (10:54 +0900)]
[tfkit] Fix for already packed or unpacked (#3688)
This will fix tfkit to run pack or unpack for data are already packed or unpakced
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 5 Jun 2019 01:53:38 +0000 (10:53 +0900)]
[tfkit] support pack,unpack for int32 type (#3690)
This will make pack, unpack to support int32 data type
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 5 Jun 2019 01:17:36 +0000 (10:17 +0900)]
[moco/tf] Implement fix_shape for copy (#3685)
This will implement fix_shape() methods for nodes that just will do with copy input shape to output
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Jun 2019 00:29:17 +0000 (09:29 +0900)]
[loco] Support Padding over Conv2D (#3686)
This commit extends Conv2D nodes with pad field and its getter.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 5 Jun 2019 00:28:50 +0000 (09:28 +0900)]
[loco] Introduce Filter Permuting Encoder (#3684)
This commit introduces a permuting encoder for filter values.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 5 Jun 2019 00:28:41 +0000 (09:28 +0900)]
[moco/tf] Change calling transform run (#3687)
This will change calling transform run by always call and update changed bool value
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 5 Jun 2019 00:27:54 +0000 (09:27 +0900)]
[moco/tf] Register two transforms (#3683)
This will register and run (currently dummy) two transforms after loading the graph
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Jun 2019 23:40:45 +0000 (08:40 +0900)]
[loco] Introduce Pad field and its getter on MaxPool2D (#3679)
This commit extends MaxPool2D node with a padding field and its getter.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Jun 2019 09:30:51 +0000 (18:30 +0900)]
[loco] Implement FilterAxis Permutation (#3675)
* [loco] Implement FilterAxis Permutation
This commit implements Permutation over FilterAxis similarly as that
over FeatureAxis.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Return const reference
* Fix a typo
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 4 Jun 2019 08:22:00 +0000 (17:22 +0900)]
[moco/tf] introduce FixShapeTransform (#3673)
* [moco/tf] introduce FixShapeTransform
This will introduce FixShapeTransform class to perform shape inference from known nodes and place holders for each node types.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* reduce line
* sort
* use ||
* fix call call condition
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 4 Jun 2019 08:16:44 +0000 (17:16 +0900)]
[loco] Introduce Dialect interface (#3676)
This commit introduces Dialect interface class.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 4 Jun 2019 08:11:21 +0000 (17:11 +0900)]
[moco/tf] Add Concat node converter (#3671)
* [moco/tf] Add Concat node converter
This will add Concat node converter for TF loading
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* rename
* update comments
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 4 Jun 2019 04:53:07 +0000 (13:53 +0900)]
[locomotiv] Fix ASSERT_EQ for integer test of ConstGen (#3678)
It seems good to use ASSERT_EQ for integer test, ASSERT_FLOAT_EQ for
float test.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 4 Jun 2019 02:28:30 +0000 (11:28 +0900)]
[moco/tf] Introduce ClearAnnotTransform (#3672)
This will introduce ClearAnnotTransform class as a place holder to remove temporary annotation while loading TF model
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Jun 2019 23:53:33 +0000 (08:53 +0900)]
[loco] Introduce FilterAxis enum class (#3669)
This commit introduces FilterAxis enum class which denotes the name of
each axis of any convolutional filter data.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 3 Jun 2019 23:53:22 +0000 (08:53 +0900)]
[locomotiv] Introduce node domain annotation tools (#3665)
* [locomotiv] Introduce node domain annotation tools
This commit introduces project-wise private (i.e. internal use in
locomotiv only) node domain annotation tools.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Build fix: remove const return type qualifier
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 23:51:47 +0000 (08:51 +0900)]
[moco/tf] Add graph transformation step (#3674)
This will add graph transformation step after loading has finished
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 3 Jun 2019 23:51:19 +0000 (08:51 +0900)]
[moco/ONNX] Introduce onnxutil (#3633)
* [moco/ONNX] Introduce onnxutil
Until now, some functions only for ONNX is in the `Frontend.cpp` file.
This commit will make those functions as separate file, `Onnxutil.h`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* Modify parameter type
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 08:38:42 +0000 (17:38 +0900)]
[moco/tf] Guard of unknown dim for Const (#3668)
This will add guard code for unknown dim size for Const
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 08:37:02 +0000 (17:37 +0900)]
[moco/tf] introduce ShapeInferenceData (#3642)
* [moco/tf] introduce ShapeInfData
This will introduce ShapeInfData used for annotation while shape inference of nodes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove valid
* fix
* rename
* fix typo
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 08:17:45 +0000 (17:17 +0900)]
[locomotiv] Support TensorConcat (#3655)
* [locomotiv] Support TensorConcat
This will enable TensorConcat node in locomotiv
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix comment
* shorten to one line
* use iterator only from output
* update comment
* add more test
* check for dim size
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Jun 2019 07:18:48 +0000 (16:18 +0900)]
[loco] Use stdex::make_unique in test (#3667)
This commit replaces all the internal make_unique implemetnations with
stdex::make_unique.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Jun 2019 07:15:05 +0000 (16:15 +0900)]
[loco] Introduce DataType mixin (#3666)
This commit extracts DataType mixin from ConstGen and Pull node.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Jun 2019 07:14:50 +0000 (16:14 +0900)]
[loco] Introduce Pad<2> class (#3659)
This commit introduces Pad<2> which denotes 2D spatial padding
configuration.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 07:08:03 +0000 (16:08 +0900)]
[moco/tf] Introduce transform base class (#3645)
* [moco/tf] Introduce transform base class
This will introduce Base class of transformation used for TensorFlow loading
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* extract
* rename class
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 05:33:19 +0000 (14:33 +0900)]
[moco/tf] Enabling MaxPool2D_000 test (#3663)
This will enables MAxPool2D_000 test in moco/tf.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 05:31:21 +0000 (14:31 +0900)]
[moco/tf] Support Const int32 type (#3657)
* [moco/tf] Support Const int32 type
This will add support for int32 type for Const node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix type
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 04:13:32 +0000 (13:13 +0900)]
[locomotiv] Support S32 type for ConstGen (#3656)
* [locomotiv] Support S32 type for ConstGen
This will enable S32 type for ConstGen node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix format
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 04:12:30 +0000 (13:12 +0900)]
[moco_tf] Fix test.info file for Concat_000 (#3658)
This will fix Concat_000 test.info file that had no output information
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 03:10:53 +0000 (12:10 +0900)]
[moco/tf] Add graph validation (#3653)
* [moco/tf] Add graph validation
This will add graph validation after converting the graph from TensorFlow to loco.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove nullptr
* add assert
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 3 Jun 2019 02:26:46 +0000 (11:26 +0900)]
[moco/tf] Simplify implementation of Const op (#3651)
This commit will simplify the implementation of Const op in moco tf frontend.
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Jun 2019 02:13:05 +0000 (11:13 +0900)]
[pp] Update README.md (#3654)
This commit updates README.md to be compatible with Doxygen.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 02:10:13 +0000 (11:10 +0900)]
[moco/tf] Add Concat test material with -1 axis (#3648)
* [moco/tf] Add Concat test material with -1 axis
This will add Concat_002 test material that has axis value of -1
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix input name
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 3 Jun 2019 02:07:43 +0000 (11:07 +0900)]
[loco] Introduce Conv2D (#3650)
This commit extends loco IR with Conv2D node.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 02:07:20 +0000 (11:07 +0900)]
[moco/tf] Add test material for Concat (#3646)
* [moco/tf] Add test materials for Concat
This will add Concat_000 test material
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* use float val
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 02:06:20 +0000 (11:06 +0900)]
[moco/tf] Add Concat test material with 3 inputs (#3647)
* [moco/tf] Add Concat test material with 3 inputs
This will add Concat_001 test material that has 3 input tensors and an axis
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* use float val
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 3 Jun 2019 01:39:06 +0000 (10:39 +0900)]
[locomotiv] Support FeatureDecode Node (#3639)
* [locomotiv] Support FeatureDecode Node
This commit supports FeatureDecode loco node. It also adds feature
decoding part into feature codec test.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Review fix: pass perm by const ref
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 01:31:23 +0000 (10:31 +0900)]
[moco/tf] Fix shape reading for Placeholder (#3644)
* [moco/tf] Fix shape reading for Placeholder
This will fix shape information reading for Placeholder to handle unknown and future todo
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix type conversion
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 3 Jun 2019 01:23:22 +0000 (10:23 +0900)]
[moco/tf] Introduce ConcatData (#3641)
* [moco/tf] Introduce ConcatData
This will introduce ConcatData used for annotation of Concat node.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 2 Jun 2019 22:22:55 +0000 (07:22 +0900)]
[moco/tf] Add get_int_attr (#3643)
This will add get_int_attr() to read int type attribute value from TensorFlow NodeDef
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 31 May 2019 06:41:13 +0000 (15:41 +0900)]
[locomotiv] Prepare for FeatureCodec execution test (#3630)
* [locomotiv] Prepare for FeatureCodec execution test
By special relationship between FeatureEncode and FeatureDecode nodes,
it is convenient to test them at once. This commit is a preparation for
that. Code structure is changed but semantic is not.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Review feedback: simple data, correct assertion
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 31 May 2019 05:52:36 +0000 (14:52 +0900)]
[loco] add int32 type (#3636)
* [loco] add int32 type
This will add int32 type for data types
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* change order
* another change order
* move after todo
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 31 May 2019 05:45:02 +0000 (14:45 +0900)]
[moco] introduce NodeDefTable (#3637)
This will introduce NodeDefTable class to provide TensorFlow node from name query
Signed-off-by: SaeHie Park saehie.park@samsung.com
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 31 May 2019 01:25:51 +0000 (10:25 +0900)]
[loco] introduce TensorConcat (#3635)
This will introduce TensorConcat IR which will express concatenation on tensor operation
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 30 May 2019 04:16:53 +0000 (13:16 +0900)]
[moco/ONNX] Introduce Constant operation (#3626)
* [moco/ONNX] Introduce Constant operation
This commit will introduce constant operation for moco ONNX frontend
and related tests
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* add assert
* add version diff description
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 30 May 2019 04:16:24 +0000 (13:16 +0900)]
[nike] Update README.md (#3632)
This commit updates README.md to be compliant with Doxygen.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 29 May 2019 08:30:30 +0000 (17:30 +0900)]
[loco] Introduce FilterEncode (#3625)
This commit introduces FilterEncode node which expresses Tenser-to-Filter
conversion.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 29 May 2019 06:55:44 +0000 (15:55 +0900)]
[loco] Reshape with shape known at compile time (#3615)
* [loco] FixedReshape
This commit adds a loco node that reshapes a tensor with statically known shape.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* use template. revise comment
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 29 May 2019 06:55:21 +0000 (15:55 +0900)]
[loco] Reuse permutation (#3622)
This commit extends PermutingCodec with a new setter which takes
"Permutation" as its input.
This commit also updates a related code example.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 29 May 2019 04:44:27 +0000 (13:44 +0900)]
[locomotiv] Support FeatureEncode execution (#3602)
* [locomotiv] Support FeatureEncode execution
This commit supports FeatureEncode execution for loco interpreter. Note
that locomotiv saves all feature data as NHWC.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Fix typo
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 29 May 2019 04:26:34 +0000 (13:26 +0900)]
[moco/ONNX] Enable converting initializer and input tensor to loco node (#3577)
Until now, `moco` didn't handle for converting initializer and input tensors to `loco` node.
By substituting initializer to `loco::ConstGen` and converting input tensors to `loco::Pull`,
this commit will ebable converting initializer and input tensor to `loco` node
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 29 May 2019 00:52:26 +0000 (09:52 +0900)]
[loco] Introduce FilterEncoder (#3613)
* [loco] Introduce FilterEncoder
This commit introduces FilterEncoder interface as a step to support
Conv2D.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix a typo (filter_idx -> filter_index)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 28 May 2019 22:14:20 +0000 (07:14 +0900)]
[moco] Update README.md (#3614)
This commit updates moco's README.md to be compliant with Doxygen
format.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 27 May 2019 10:35:58 +0000 (19:35 +0900)]
Update Dockerfile for updating gcc version (#3606)
* Update Dockerfile for updating gcc version
This commit updates Dockerfile for updating gcc version.
Related issue:#3332
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* This commit remove some unnecessary codes.
* This commit modify codes for consistency
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 27 May 2019 10:04:27 +0000 (19:04 +0900)]
[nnkit/moco/tf] Enable building nnkit when moco is disabled (#3609)
This commit enables building nnkit even when there is no moco.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 27 May 2019 03:15:27 +0000 (12:15 +0900)]
[loco] Introduce FilterIndex (#3600)
* [loco] Introduce FilterIndex
This commit introduces FilterIndex class which specifies one element in
a convolutional filter.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix typos
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 27 May 2019 03:12:46 +0000 (12:12 +0900)]
[moco] Introduce Logging Framework (#3593)
This commit introduce very basic logging framework into moco.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 27 May 2019 02:08:36 +0000 (11:08 +0900)]
[locomotiv] Assert on push_data not push node (#3599)
There has been a mistake on assertion. The intension here is to
check push_data whether it is null or not, not push node itself.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 27 May 2019 01:40:43 +0000 (10:40 +0900)]
[loco] Update MaxPool2D comment (#3596)
* [loco] Update MaxPool2D comment
This commit explains MaxPool2D pre-conditions through its comment.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Use mathmetical notation
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 27 May 2019 00:01:02 +0000 (09:01 +0900)]
[locomotiv] Supporting MaxPool2D (#3576)
* [locomotiv] Supporting MaxPool2D
This commit enables locomotiv to run loco MaxPool2D.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* modify Copyright
* leave the latest copyright
* revised for comments
* adding two assert()s
* adding TODO comment
* fix wrong comment
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 24 May 2019 06:26:47 +0000 (15:26 +0900)]
[locomotiv] Additional example on argument shape mismatch (#3591)
One more thing to consider when support new node execution: Some nodes
expect specific shape for its input.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 24 May 2019 04:58:17 +0000 (13:58 +0900)]
[loco] Update README (#3590)
This commit adds leading section header to make README compatible with
Doxygen.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 24 May 2019 04:02:56 +0000 (13:02 +0900)]
[loco] Introduce FilterShape (#3587)
This commit introduces FilterShape class which repesents the shape of
Conv2D filter shape.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 24 May 2019 03:52:36 +0000 (12:52 +0900)]
[cwrap] Update README.md (#3589)
This commit updates README.md as a doxygen-compatible form.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 24 May 2019 01:19:53 +0000 (10:19 +0900)]
[hermes] Introduce Context class (#3585)
This commit introduces Context class which serves as a central
controller for hermes logging subsystem.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 23 May 2019 08:36:19 +0000 (17:36 +0900)]
[hermes] Introduce Source class (#3574)
* [hermes] Introduce Source class
This commit introduces "Source" class which serves as an actual
interface with application.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Use virtual destructor
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 23 May 2019 07:10:26 +0000 (16:10 +0900)]
[locomotiv] Using shape({ .. }) instead of rank(..), make_dimension(..) (#3583)
This commit replace rank(..) and make_dimension(..) with shape({..}) to shorten the code.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 23 May 2019 01:44:01 +0000 (10:44 +0900)]
[moco] enable const_000 test of TensorFlow frontend (#3580)
This will enable TensorFlow frontend testing with locomotiv for const_000 test.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 22 May 2019 09:28:50 +0000 (18:28 +0900)]
[moco/ONNX] Remove deprecated functions (#3578)
This commit will remove deprecated functions in Identity operation
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 22 May 2019 08:19:39 +0000 (17:19 +0900)]
[moco/ONNX] Introduce convert tool for ONNX moco frontend (#3563)
* [moco/ONNX] Introduce convert tool for ONNX moco frontend
This commit will introduce convert too for ONNX moco frontend
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* remove tensor_dtype in runtime_error
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 22 May 2019 08:19:29 +0000 (17:19 +0900)]
[moco/ONNX] Apply opset version to operator and frontend (#3557)
* [moco/ONNX] Apply opset version to operator and frontend
This commit will apply opset version to moco ONNX frontend and
ONNX operators.
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* Repositioning REGISTER_OP_BUILDER