윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 Oct 2019 06:28:22 +0000 (15:28 +0900)]
[exo] Renaming FuseConv2DAddSubPass to FuseBiasAddPass (#8441)
Supporting BiasAdd is needed for more ops (other than Conv2D) so pass is renamed into more general term.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 24 Oct 2019 06:03:16 +0000 (15:03 +0900)]
Add Exp op into base_loader (#8414)
Now, base_loader supports EXP operatoin.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 24 Oct 2019 05:36:57 +0000 (14:36 +0900)]
[exo] Convert DepthwiseConv2D (#8431)
This commit introduces conversion for DepthwiseConv2D. It converts
canonical DepthwiseConv2D into TFLDepthwiseConv2D plus some auxiliary
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 24 Oct 2019 04:56:19 +0000 (13:56 +0900)]
[moco-integraion-test] turn on placeholder test (#8434)
This commit turns on placeholder no shape related test.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 24 Oct 2019 04:56:03 +0000 (13:56 +0900)]
[tf2tflite] turn on placeholder test (#8433)
This commit turns on placeholder no shape related test.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 24 Oct 2019 04:39:51 +0000 (13:39 +0900)]
Add ReduceMax into base_loader (#8415)
Now, base_loader supports ReduceMax op
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 24 Oct 2019 04:32:26 +0000 (13:32 +0900)]
[exo] Fold Reshape of Const Pass (#8432)
This commit introduces FoldReshapeOfConst Pass, which folds TFLReshape
followed by TFLConst
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 24 Oct 2019 04:29:30 +0000 (13:29 +0900)]
Introduce mio-circle (#8426)
* Introduce mio-circle
This commit introduces "mio-circle" which provides FlatBuffer generated
circle file accessor.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix Copyright year
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 24 Oct 2019 04:26:58 +0000 (13:26 +0900)]
[exo] TFLReshape inference for shape & type (#8430)
* [exo] TFLReshape inference for shape & type
This commit implements shape and type inference for TFLReshape
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Fix typo
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 Oct 2019 03:05:12 +0000 (12:05 +0900)]
[moco] as Node cast helper in support (#8420)
This will introduce as helper that casts to required type in support
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 24 Oct 2019 02:59:52 +0000 (11:59 +0900)]
[moco-tf] rewrite graphDef (#8397)
* [moco-tf] rewrite graphDef
This commit adds rewrite graphDef function to Frontend.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* split one function into two.
* change function name.
* add for supporting zero-dim-size.
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 24 Oct 2019 01:43:35 +0000 (10:43 +0900)]
[mio-tflite] Introduce mio-tflite (#8425)
* [mio-tflite] Introduce mio-tflite
This will introduce mio-tflite that produces TensorFlow lite schema header file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* follow circle for test
* provide as example not test
* remove blank
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 23 Oct 2019 23:31:27 +0000 (08:31 +0900)]
[res] add Placeholder with no shape value network (#8418)
This commit adds Placeholder with no shape value simple network.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
[mir-tflite-importer] Support quantization on tflite frontend (#8314)
* Added setting quantization to Output
* Added fused bias Covn and DWConv op creation
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[nnc/interpreter] Fix removed method getProducer (#8424)
* Fixed getting the type from input
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[mir] Fix setting output type on ConstantOp ctor (#8421)
* Fixed setOutputType on ctor
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[ncc/interpreter] Fix reading/writing tensors from/to files (#8292)
* Supported writing UINT8 DataType
* Reading files based on Input DataType size
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[nnc] Fix switcher transformation for qunatization (#8240)
* Fixed transpose inserters
* Fixed Conv2D and DepthwiseConv2D switchers
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[nnc] Quantize, Dequantize implementations on interpreter (#8175)
* Support Quantize, Dequantize operations on interpreter backend
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 23 Oct 2019 09:50:31 +0000 (18:50 +0900)]
[exo] Reshape TFL dialect IR (#8321)
* [exo] Reshape TFL dialect IR
This commit introduces TFLReshape, a TFL dialect IR for Reshape
operator. It also introduces its summary.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Add shape() as second input
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 Oct 2019 09:44:59 +0000 (18:44 +0900)]
[moco] Install support library (#8417)
This will add install support library
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 23 Oct 2019 09:01:50 +0000 (18:01 +0900)]
[moco] Install import and lang (#8411)
tf2tflite requires moco_tf_frontend,
moco_tf_frontend requires moco_import and moco_lang
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 23 Oct 2019 09:00:43 +0000 (18:00 +0900)]
[res] add no shape placeholder network (#8412)
This commit adds no shape placeholder simple network.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 23 Oct 2019 08:59:31 +0000 (17:59 +0900)]
[exo] Type & Shape inference for TFLDepthwiseConv2D (#8395)
This commit introduces type and shape inference for TFLDepthwiseConv2D
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 23 Oct 2019 06:51:07 +0000 (15:51 +0900)]
[nncc] Allow users to set INCLUDE_DIR with FlatBuffers_Target (#8391)
This commit revises FlatBuffers_Target helper to allow users to set
INCLUDE_DIR via option.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 23 Oct 2019 05:35:32 +0000 (14:35 +0900)]
[moco-tf] set shape in Frontend test (#8408)
* [moco-tf] set shape in Frontend test
This commit set shape to signature in Frontend test.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* apply comment.
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 Oct 2019 05:35:06 +0000 (14:35 +0900)]
[moco] Introduce Support (#8407)
This will introduce moco-support with TFShapeInferenceHelper and related
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 23 Oct 2019 05:17:58 +0000 (14:17 +0900)]
[logo] SimplifyDomainConversionPass for DepthwiseFilter combo (#8351)
This commit supports DepthwiseFilterEncode - DepthwiseFilterDecode combo
for SimplifyDomainConversionPass.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 23 Oct 2019 03:11:03 +0000 (12:11 +0900)]
[exo] Set FusedActivation for sub and div (#8405)
This commit will set fusedActivationFunction for `sub` and `div`
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 Oct 2019 01:45:15 +0000 (10:45 +0900)]
[moco-tf] Remove GraphBuilder tests (#8402)
This will remove GraphBuilder tests that is now migrated into moco
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 Oct 2019 00:50:02 +0000 (09:50 +0900)]
[moco-tf] Redirect Importer to moco (#8401)
This will redirect Importer header to moco and remove implementation and test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 23 Oct 2019 00:49:46 +0000 (09:49 +0900)]
[moco] Add tests for node GraphBuilder (#8400)
This will add tests for node GraphBuilder
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 23 Oct 2019 00:02:07 +0000 (09:02 +0900)]
[exo] Export TFLDepthwiseConv2D (#8396)
This commit introduces export stage for TFLDepthwiseConv2D
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
[mir] Remove unused functions (#8366)
Remove functions which were needed for transition period.
Signed-off-by: Sergei Barannikov <barannikov88@gmail.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 22 Oct 2019 22:00:48 +0000 (07:00 +0900)]
[moco-tf] use GraphBuilder of moco (#8393)
This will update to use GraphBuilder and related classes from moco
Also updates that need header changes from this change
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 22 Oct 2019 10:10:03 +0000 (19:10 +0900)]
[moco-tf] Fix for TFFormattedGraph (#8392)
This will add TFPlaceholder as a alias of moco::TFPlaceholder to make TFFormattedGraph work correctly
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 22 Oct 2019 09:32:11 +0000 (18:32 +0900)]
[exo] Fix EXO_THROW spacing (#8388)
This commit adds space ' ' to EXO_THROW macro.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 22 Oct 2019 08:17:22 +0000 (17:17 +0900)]
[moco] Importer and ModelSignature (#8383)
This will introduce Importer and ModelSignature
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 22 Oct 2019 06:52:26 +0000 (15:52 +0900)]
[exo] Remove exo_tflite target (#8378)
This commit removes unused and deprecated exo_tflite target library.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 22 Oct 2019 03:57:39 +0000 (12:57 +0900)]
[moco-integration-test] add Pad test (#8374)
This commit adds Pad test to moco-integration-test.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 22 Oct 2019 03:35:36 +0000 (12:35 +0900)]
[moco] Placeholder as TFPlaceholder (#8375)
This will import TensorFlow Placeholder node as TFPlaceholder IR instead of loco::Pull
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 22 Oct 2019 03:02:06 +0000 (12:02 +0900)]
[tf2tflite] add Pad test (#8372)
This commit adds Pad test to tf2tflite.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 22 Oct 2019 01:54:44 +0000 (10:54 +0900)]
[nncc] Rename "mocotest-onnx" project (#8356)
This commit renames "mocotest-onnx" project as oneco-integration-test,
following oneco.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 22 Oct 2019 01:38:55 +0000 (10:38 +0900)]
[stdex] Require GTest only when TEST is enabled (#8358)
GTest is required only when ENABLE_TEST is set.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 22 Oct 2019 01:26:38 +0000 (10:26 +0900)]
[exo] Support TensorConstantPad operation (#8309)
* [exo] Support TensorConstantPad operation
This commit supports TensorConstantPad operation in exo.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* change vector declaration method.
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 22 Oct 2019 01:09:35 +0000 (10:09 +0900)]
[moco-tf] Import Placeholder as TFPlaceholder (#8369)
This will import TensorFlow Placeholder node as TFPlaceholder IR instead of loco::Pull
- graph input shape setting has moved to Importer class as we cannot query node by name in Frontend
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 22 Oct 2019 00:45:56 +0000 (09:45 +0900)]
[loco] Fix typo for PermutingCodec test (#8350)
This commit fixes typo for PermutingCodec test
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 22 Oct 2019 00:30:34 +0000 (09:30 +0900)]
[neurun] Verbose output on error while model load (#8365)
Print message of thrown `std::exception` objects.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 23:51:30 +0000 (08:51 +0900)]
[moco] NodeShape of TFPlaceholder (#8360)
This will introduce tensor_shape method that returns TensorShape of TFPlaceholder node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 23:50:35 +0000 (08:50 +0900)]
[moco-tf] Note for PlaceholderCanonicalizer (#8361)
This will add a note for PlaceholderCanonicalizer about GraphInputIndex
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[nnc] Switch to Use-based interface (#8325)
Replace `Operation::Input *` with `Operation::Use` and `getConsumers()` with `getUses()`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 09:55:23 +0000 (18:55 +0900)]
[tfkit] use mio-tf (#8357)
This will let tfkit to use mio-tf so that one TensorFlow protobuf library is produced
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 09:31:14 +0000 (18:31 +0900)]
[moco-tf] Canonicalize TFPlaceholder (#8354)
This will add and enable Canonicalize TFPlaceholder
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 21 Oct 2019 07:58:18 +0000 (16:58 +0900)]
[exo] make_dw_filter_decode() helper (#8353)
This commit introduces make_dw_filter_decode() helper function
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 21 Oct 2019 07:57:56 +0000 (16:57 +0900)]
[loco] Type and shape inference for DepthwiseFilterDecode (#8349)
This commit introduces type and shape inference for
DepthwiseFilterDecode
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 07:34:18 +0000 (16:34 +0900)]
[moco] Placeholder index (#8341)
* [moco] Placeholder index
This will add methods to set/get GraphInputIndex for TFPlaceholder
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove todo, add test
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 06:30:58 +0000 (15:30 +0900)]
[exo] unit test cases for FuseReluPass (#8342)
This adds unit tests for FuseReluPass.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 06:30:47 +0000 (15:30 +0900)]
[exo] turning on a knob for FeatureBiasAdd conversion (#8334)
This turns on a knob for FeatureBiasAdd conversion.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 06:30:36 +0000 (15:30 +0900)]
[exo] Turning on knob to enabling fusion (of add/sub, relu/relu6) by default (#8333)
This turns on knobs to enabling fusion (of add/sub, relu/relu6) by default
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 21 Oct 2019 06:30:26 +0000 (15:30 +0900)]
[loco] DepthwiseFilterDecode canonical IR (#8332)
This commit introduces DepthwiseFilterDecode loco canonical IR
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 06:26:13 +0000 (15:26 +0900)]
[tf2tflite] added NET_0035-37 (CBR related test) into test.lst (#8343)
This adds NET00_35, NET_0036, NET_0037 (CBR related test) into test.lst
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 21 Oct 2019 06:24:42 +0000 (15:24 +0900)]
[exo] DepthwiseConv2D TFL dialect IR (#8320)
* [exo] DepthwiseConv2D TFL dialect IR
This commit introduces TFLDepthwiseConv2D, a TFL dialect IR for
DepthwiseConv2D. It also introduces its summary.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Add default value and test
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 06:21:57 +0000 (15:21 +0900)]
[moco-integration-test] adding NET_0035, NET_0037 into test.lst (#8346)
This adds NET_0035, NET_0037 into test.lst.
0036 fails. An issue will be created.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 21 Oct 2019 05:59:21 +0000 (14:59 +0900)]
[nnfw-api] Merge custom op API implementation (#8340)
Move custom op API implementation into neurun/api
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 21 Oct 2019 05:45:08 +0000 (14:45 +0900)]
Update BuildGraph parameter (#8337)
Current BuildGraph get subgraph parameter, not interpreter
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 05:26:59 +0000 (14:26 +0900)]
[moco] Import Nodes (#8336)
This will add Import GraphBuilder Nodes to import TensorFlow NodeDef
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 21 Oct 2019 05:26:24 +0000 (14:26 +0900)]
[loco] PemutingDecoder for DepthwiseFilter (#8331)
* [loco] PemutingDecoder for DepthwiseFilter
This commit introduces PemutingDecoder for DepthwiseFilter
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Remove unrelated
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 04:48:58 +0000 (13:48 +0900)]
[moco-tf] use mio-tf (#8328)
* [moco-tf] use mio-tf
This will let moco-tf to use mio-tf so that one TensorFlow protobuf library produced and used
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* check mio_tf cond
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 04:46:59 +0000 (13:46 +0900)]
[moco] Import requires (#8339)
This will update Import requires file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 21 Oct 2019 03:13:46 +0000 (12:13 +0900)]
[logo] Update SimplifyDomainConversionPass comment (#8323)
This commit updates SimplifyDomainConversionPass comment to cover its
whole functionality
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 21 Oct 2019 03:12:43 +0000 (12:12 +0900)]
[exo] Update make_filter_* comment (#8322)
This commit fixes typo and updates following helpers in GraphBlock.h:
- make_filter_encode
- make_filter_decode
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 03:11:05 +0000 (12:11 +0900)]
[plier-tf] use mio-tf (#8329)
* [plier-tf] use mio-tf
This will let plier-tf to use mio-tf so that one TensorFlow protobuf library is produced
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* check mio_tf cond
* match cmake if endif
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 03:09:08 +0000 (12:09 +0900)]
[moco] Convert and TestHelper (#8330)
This will introduce Convert for Import and TestHelper for Import testing
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 02:36:52 +0000 (11:36 +0900)]
[nnpkg, circle] Define instance_norm in circle_schema.fbs (#8262)
It introduces instance_norm operator in circle schema.
Also, it updates circle_schema_generated.h for circle_loader.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 01:59:19 +0000 (10:59 +0900)]
[moco-tf] Redirect GraphBuilder to moco (#8327)
This will update GraphBuilder and GraphBuilderContext to redirect to moco for migration
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 21 Oct 2019 01:45:22 +0000 (10:45 +0900)]
Relocate compute libraries (#8307)
Rename srcn to ncnn
Relocate compute libraries into compute/ (armcompute-ex, cker, ncnn)
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 21 Oct 2019 01:43:12 +0000 (10:43 +0900)]
[loco] DepthwiseFilterDecoder (#8319)
This commit introduces DepthwiseFilterDecoder class.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 21 Oct 2019 01:27:27 +0000 (10:27 +0900)]
[moco] Introduce TFPlaceholder IR (#8313)
* [moco] Introduce TFPlaceholder IR
This will introduce TFPlaceholder IR for Placeholder node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add todo comment
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 21 Oct 2019 01:01:10 +0000 (10:01 +0900)]
Support Logistic in base loader (#7942)
- Add logistic operation on base loader
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Sun, 20 Oct 2019 21:24:46 +0000 (06:24 +0900)]
[loco] Fix typo for DepthwiseFilterEncoder comment (#8318)
This commit fixes typo in DepthwiseFilterEncode comment
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 20 Oct 2019 21:19:23 +0000 (06:19 +0900)]
[moco] Include moco import (#8316)
This will update CMake to include import as sub project
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[mir] Refine operations constructors. (#8283)
Removed obsolete operations constructors in [mir].
Signed-off-by: Dmitry Gusev <d.gusev@partner.samsung.com>
[mir] Remove Operation::Input class (#8294)
Remove `Operation::Input` class and add lightweight `Use` class.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir] Remove unused functions (#8324)
Remove `replaceWithInputNode` and `replaceInputNodes` functions which were only used in unittests.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir] Introduce new fused bias constructors (#8186)
* Conv2DOp ctor (and fix copy)
* DepthwiseConv2DOp ctor (and fix copy)
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 09:37:30 +0000 (18:37 +0900)]
[base-loader] Change SubNode to MulNode in loadMul (#8311)
It fixes wrong code in loadMul.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 18 Oct 2019 07:24:39 +0000 (16:24 +0900)]
[moco-tf] fix PadCanonicalizer (#8298)
* [moco-tf] fix PadCanonicalizer
This commit fixs PadCanonicalizer in moco-tf.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* add comment.
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 07:11:38 +0000 (16:11 +0900)]
[moco] Import: Introduce GraphBuilder (#8306)
This will introduce moco-import target with GraphBuilder and related classes copied from moco-tf
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 07:11:17 +0000 (16:11 +0900)]
[moco-tf] Refactor TF node graph builder test part 2 (#8297)
This will refactor test NOT to use Importer module of node graph builder from MaxPool to Tanh
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 07:10:48 +0000 (16:10 +0900)]
[moco-tf] Refactor TF node graph builder test part 1 (#8296)
This will refactor test NOT to use Importer module of node graph builder from Add to FusedBatchNorm
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 05:08:20 +0000 (14:08 +0900)]
[exo] replace PhaseStrategy of TestHelper.h from Saturate to Restart (#8304)
This replaces PhaseStrategy of TestHelper.h from Saturate to Restart
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 05:07:29 +0000 (14:07 +0900)]
[res/TensorFlowTests] NET_0037 test case (#8302)
* [res/TensorFlowTests] NET_0037 test case
This adds NET_0037, Conv2D + ReLU + Add. By exo, Conv2D and ReLU are fused but Add isn't.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* simple description
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 18 Oct 2019 04:28:40 +0000 (13:28 +0900)]
[nnfw-gbs] Merge build require and option setting (#8232)
- Remove python3 build require
- Require libarmcl-devel and python on aarch target only
- Merge build option setting for coverage build, test build and general build
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 04:26:00 +0000 (13:26 +0900)]
[exo] adding FuseReluPass into TFLOptimize.cpp (#8280)
This adds FuseReluPass into TFLOptimize.cpp. When a knob is on, this pass will run.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 04:23:12 +0000 (13:23 +0900)]
[exo] rewriting a function to handle Mixin (#8281)
Instread of trying to cast to a lot of type, code was re-written to try one-time cast to Mixin.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 18 Oct 2019 04:19:49 +0000 (13:19 +0900)]
[lib/tflite] Update operation register (#8278)
Update register.h/cpp to match tflite v1.13.1
Support new operations introduce on v1.13.1
Support more upstream custom operation
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 03:27:40 +0000 (12:27 +0900)]
[exo] FuseConv2DAddSubPass checks Conv2D's fused activation function (#8268)
* [exo] FuseConv2DAddSubPass checks Conv2D's fused activation function
This enables FuseConv2DAddSubPass to check Conv2D's fused activation function
and perform fusion considering the status of fused activation function.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remove unused var
* test case
* one more test case
* float act_func(...) -> void act_func(..)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 18 Oct 2019 02:20:46 +0000 (11:20 +0900)]
[mio-tf] TensorFlow model library (#8274)
* [mio-tf] TensorFlow model library
This will introduce mio-tf as a separate project for accessing TensorFlow protobuf model file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* merge cmake and apply comments
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 18 Oct 2019 02:09:37 +0000 (11:09 +0900)]
[neurun] Backend priority by OP_BACKEND_ALLOPS (#8124)
- Try backend loading from default backend setting, but not fail if backend is not exist
- Fail if there is no loaded backend
- Reorder to load acl(cl, neon) first
- If OP_BACKEND_ALLOPS is empty, use first loaded backend
- Set default OP_BACKEND_ALLOPS emptyy
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 18 Oct 2019 00:48:40 +0000 (09:48 +0900)]
Rename moco-onnx as oneco (#8251)
Let's use moco only for TensorFlow Frontend modules.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>