Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 19:13:06 +0000 (22:13 +0300)]
[mir_onnx] Fix checking some attributes (#6796)
* Added checking that dilations is equal 1 in Conv and MaxPool
* Removed spatial attribute from BatchNormalization
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 17:42:31 +0000 (20:42 +0300)]
[mir_onnx] Support Flatten operation (#6795)
* Supported V1 and V9 Flatten op versions
* Added Flatten on registration and cmake
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[mir_onnx] Add support for Transpose operator (#6764)
Add support for `Transpose` operator.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 13:03:34 +0000 (16:03 +0300)]
Add virtual dtor to ITimer class (#6786)
Fix failed build while using clang 9.0
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
[mir_onnx] Add missing include guards (#6762)
Add include guards to operator converter headers.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Support Identity operator (#6761)
Add support for `Identity` operator.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Use new PadOp constructor (#6753)
Switch to the new `PadOp` constructor.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 11:43:36 +0000 (20:43 +0900)]
[tf2tflite] Enable valid NET tests (#6791)
This commit enables valid small network tests for tf2tflite:
NET_0004, NET_0005, NET_0006, NET_0011
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 10:31:40 +0000 (19:31 +0900)]
[neurun] Change CMake target name for neurun core (#6782)
Change target name to `neurun_core` from `neurun-core` for consistency
of target name.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 10:15:58 +0000 (13:15 +0300)]
Fix a typo in benchmark runner include guard (#6787)
__BENCHMAKR_RUNNER_H__ used instead of __BENCHMARK_RUNNER_H__
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
이춘석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 10:14:25 +0000 (19:14 +0900)]
Remove jsoncpp from line coverage (#6779)
- Remove jsoncpp from line coverage
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 10:12:27 +0000 (19:12 +0900)]
Change dimension of ACLTensor to start from higher dimension (#6765)
This commit changes dimension function of ACLTensor to start from higher dimension.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 09:45:10 +0000 (18:45 +0900)]
[res] Remove old TF unit tests (#6781)
This commit removes old Tensorflow unit tests
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 09:32:52 +0000 (18:32 +0900)]
[moco-tf] Add RemoveTFIdentityNodeTransform (#6783)
This will add RemoveTFIdentityNodeTransform to transforms list
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[nnc] Use new interface of PadOp (#6713)
Switch to new interface of `PadOp`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Use new PadOp constructor (#6752)
Switch to the new `PadOp` constructor.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Insert TransposeOp to shuffle constants (#6734)
Insert `TransposeOp`s instead of direct permutation of constants to allow non-constant weights.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 07:38:49 +0000 (16:38 +0900)]
[mocotest-tf] Enable UNIT_StopGradient_000 (#6777)
This will enable UNIT_StopGradient_000 unit test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 07:17:57 +0000 (16:17 +0900)]
[mocotest-tf] Enable UNIT_Rsqrt_000 (#6776)
This will enable UNIT_Rsqrt_000 unit test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 07:17:38 +0000 (16:17 +0900)]
[tf2tflite] Enable UNIT_StopGradient_000 (#6778)
This will enable UNIT_StopGradient_000 unit test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 07:16:49 +0000 (16:16 +0900)]
[tf2tflite] Enable UNIT_Rsqrt_000 (#6775)
This will enable UNIT_Rsqrt_000 unit test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 06:41:31 +0000 (15:41 +0900)]
Update NNAPI spec to v1.2 (#6735)
Update NNAPI spec header NeuralNetworks.h
Add new NNAPI spec header NeuralNetworksExtensions.h
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 05:54:16 +0000 (14:54 +0900)]
[res] TF NET_0016 (#6770)
* [res] NET_0016
This will introdude NET_0016 test material having Conv2D + FusedBatchNorm with Identity
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove attr use_cudnn_on_gpu
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 05:49:28 +0000 (14:49 +0900)]
[tfgraph-xform] Support constant folding (#6152)
Now, tfgraph-xform is able to fold constants in TensorFlow GraphDef.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 05:37:51 +0000 (14:37 +0900)]
[moco-tf] RemoveDeadNode for TF dialects (#6773)
This will add RemoveDeadNode optimization for TF dialect node transforms
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 05:37:39 +0000 (14:37 +0900)]
[tf2tflite] Edit unit tests into renamed one (#6769)
This commit edits unit tests into renamed one in tf2tflite
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 05:37:28 +0000 (14:37 +0900)]
[mocotest-tf] Edit unit tests into renamed one (#6768)
This commit edits unit tests into renamed one in mocotest-tf project.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 05:36:52 +0000 (14:36 +0900)]
[moco-tf] Introduce RemoveTFIdentityNodeTransform (#6772)
This will introduce RemoveTFIdentityNodeTransform that disconnects TFIdentity for optimization
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 05:35:44 +0000 (14:35 +0900)]
[moco-tf] RemoveTFIdentityNode Knob (#6771)
This will add RemoveTFIdentityNode Knob to switch RemoveTFIdentityNode optimization
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Aug 2019 04:41:58 +0000 (13:41 +0900)]
[moco-tf] Remove unused files (#6756)
This will remove unused ShapeInference and TypeInference files that are replaced by transforms
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 04:34:57 +0000 (13:34 +0900)]
[loco] Remove "node" method from Graph Input/Output (#6759)
This commit removes "node" method from GraphInput/GraphOutput class.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 04:03:15 +0000 (13:03 +0900)]
[exo-tflite] Clean up deprecated code (#6757)
This commit cleans up deprecated internal shape inference implementations
in exo-tflite.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 21 Aug 2019 03:44:36 +0000 (06:44 +0300)]
Fix overloaded functions being hidden by subclasses (#6697)
void IOperationVisitor::visit(const Subgraph &subgraph) was hidden by function definitions in IKernelGenerator and KernelGenerator classes
This makes nnfw fail to build using clang 9.0
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 03:43:54 +0000 (12:43 +0900)]
[res] Add renamed unit tests (#6749)
This commit adds renamed unit tests, for example, UNIT_Add_000 for
Add_000
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 21 Aug 2019 03:43:07 +0000 (12:43 +0900)]
[tf2tflite] Add divide comment for refactoring (#6742)
This comment will be removed after test case convention refactoring
project.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 01:18:12 +0000 (10:18 +0900)]
Include xml converter in coverage suite (#6758)
To convert lcov report to xml, include xml converter tool into coverage suite
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 21 Aug 2019 00:33:24 +0000 (09:33 +0900)]
Update EigenSource-
fd6845384b86 to read URL from file (#6746)
This commit revises EigenSource-
fd6845384b86 CMake package to read URL
from file instead of environment variable.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 23:42:51 +0000 (08:42 +0900)]
[mocotest-tf] Enable NET_0015 (#6745)
This will enable NET_0015, 1/Sqrt(x), which is same as decomposed elements of Rsqrt
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 22:18:21 +0000 (07:18 +0900)]
[mocotest-tf] Epilogue test (#6750)
This commit adds Epilogue test for mocotest-tf
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 22:18:04 +0000 (07:18 +0900)]
[tf2tflite] Epilogue test (#6751)
This commit adds Epilogue test of Inception v3 for tf2tflie
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:09:20 +0000 (07:09 +0900)]
[moco-tf] Enable RsqrtCanonicalizer (#6740)
This will enable RsqrtCanonicalizer to convert TFRsqrt to canonical nodes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:09:00 +0000 (07:09 +0900)]
[moco-tf] Reserve TFShapeInference for TFStopGradient (#6739)
This will reserve place for TFStopGradient in TFShapeInference
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:08:38 +0000 (07:08 +0900)]
[moco-tf] Enable Canonicalizer for TFStopGradient (#6737)
This will add enable TFStopGradient in Canonicalizer
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:08:17 +0000 (07:08 +0900)]
[moco-tf] Type inference for TFStopGradient (#6736)
This will add TFStopGradient in type inference rule
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:07:53 +0000 (07:07 +0900)]
[tf2tflite] Enable NET_0015 (#6744)
This will enable NET_0015, 1/Sqrt(x), which is same as decomposed elements of Rsqrt
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 22:07:00 +0000 (07:07 +0900)]
[moco-tf] Remove unused header in FuseBinaryIntoPreceding (#6741)
This will remove unused header in FuseBinaryIntoPreceding
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 19:24:04 +0000 (04:24 +0900)]
[mir2loco] Remove GraphIO::node method calls (#6721)
This commit removes all the GraphInput::node and GraphOutput::node
method calls in mir2loco. This is a step toward loco GraphInput/Output
class redesign.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
[mir_onnx] Rework attribute parsing (#6651)
* Make attribute parsing functions templated and extract them to a separate file.
* Move definition of `getKernelStridesPadding` into cpp file.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Update ONNX source to version 1.5.0 (#6748)
Update ONNX source version to support ONNX IR version 5.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 17:43:02 +0000 (20:43 +0300)]
[mir_onnx] Upsample operation versioning (#6755)
* Supported V1, V7, V9 and V10(deprecated) versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 17:27:40 +0000 (20:27 +0300)]
[mir_onnx] Reshape operation versioning (#6754)
* Supported V1, V5 reshape versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 15:24:12 +0000 (18:24 +0300)]
[mir_onnx] Pad operation versioning (#6698)
* Supported V1, V2 pad versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 15:14:07 +0000 (18:14 +0300)]
[mir_onnx] MaxPool operation versioning (#6696)
* Supported V1, V8, V10 maxpool versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 15:04:43 +0000 (18:04 +0300)]
[mir_onnx] Conv operation versioning (#6695)
* Supported single V1 version
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 14:30:24 +0000 (17:30 +0300)]
[mir_onnx] Support versioning in Add operation (#6653)
* Implemented converter versioning for Add operation, known versions: 1, 6, 7
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 14:28:27 +0000 (17:28 +0300)]
[mir_onnx] Constant operation versioning (#6694)
* Supported V1, V9, v11(partially) versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 14:01:22 +0000 (17:01 +0300)]
[mir_onnx] Concat operation versioning (#6693)
* Supported V1, V4 concatenation versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 12:55:07 +0000 (15:55 +0300)]
[mir_onnx] Average Pooling operation versioning (#6691)
* Supported V1, V7, V10 average pooling versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 12:54:06 +0000 (15:54 +0300)]
[mir_onnx] BatchNormalization operation versioning (#6692)
* Supported V1, V6, V7, V9 batch normalization versions
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[nnc] Add transpose folding optimization (#6724)
Constant fold sequence of operations Constant -> Transpose.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
Add getter for opcode name (#6658)
Added getter of opcode name in string format
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
[mir] New interface for PadOp (#6708)
* Remove redundant `num_dims` parameter of constructor.
* Make padding arguments consistent with other operations (two vectors instead of vector of pairs).
* Change the type of the value to be used for padding from `Scalar` to `float` (it is `float` in all supported input frameworks).
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 10:29:21 +0000 (19:29 +0900)]
[exo-tflite] Export DepthwiseConv2D operation (#6720)
This commit introduce DepthwiseConv2D operation to exporter.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 10:17:11 +0000 (19:17 +0900)]
Check format changed files (#6683)
Check and fix format with warning message when there is changed files
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 09:58:41 +0000 (18:58 +0900)]
Fix coverage test suite (#6725)
Add lost coverage test suite packaging files: nnas, nnfw script
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 09:56:54 +0000 (18:56 +0900)]
Introduce ThirdPartyTools module (#6730)
* Introduce ThirdPartyTools module
This commit introduces ThiryPartyTools module. The current version
includes ThirdParty_URL function which manages URLs via file.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 09:45:10 +0000 (18:45 +0900)]
[moco-tf] Shape inference on canonical optimize stage (#6722)
This commit adds shape inference at canonical optimize stage of moco.
This is required for ResolveRedundantReshape transform.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 09:35:24 +0000 (18:35 +0900)]
[moco-tf] TFNodeSummary for TFStopGradient (#6738)
This will add TFStopGradient to TFNodeSummaryBuilder
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 09:12:28 +0000 (18:12 +0900)]
[moco-tf] Update shape inference in Canonicalizers (#6732)
This will update shape inference to use loco service in Canonicalizers of Add,Mul,Realdiv and Sub nodes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 09:12:05 +0000 (18:12 +0900)]
[moco-tf] Canonicalizer for TFStopGradient (#6731)
This will introduce Canonicalizer for TFStopGradient that converts to Canonical Forward node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 08:16:44 +0000 (17:16 +0900)]
[moco-tf] GraphBuilder for StopGradient (#6729)
This will introduce GraphBuilder for StopGradient node to import as TFStopGradient IR
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 08:05:43 +0000 (17:05 +0900)]
[moco-tf] TFNodeSummaryBuilder for TFConcatV2 (#6727)
This will add TFNodeSummaryBuilder summary method for TFConcatV2
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 08:03:10 +0000 (17:03 +0900)]
[moco-tf] Turn on Knob for ImportAsTFConcatV2 (#6728)
This will turn on ImportAsTFConcatV2 knob so as to make ConcatV2 is imported as TF dialect TFConcatV2
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 07:46:48 +0000 (16:46 +0900)]
[moco-tf] Canonicalizer for TFRsqrt (#6723)
This will introduce Canonicalizer for TFRsqrt node that converts to "1/Sqrt(x)"
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 07:46:23 +0000 (16:46 +0900)]
[moco_tf] Do shape,type inference before Canonicalizer (#6718)
This will run shape and type inference before Canonicalizer and use Restart type phase when any node type has changed
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 07:44:05 +0000 (16:44 +0900)]
Make OperationValidator supports multi-layout for frontend (#6714)
This commit makes OperationValidator supports multi-layout for frontend.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 07:38:12 +0000 (16:38 +0900)]
[moco-tf] Register shape inference pass (#6726)
This commit registers shape inference pass to optimize stage transforms
list.
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 07:34:00 +0000 (16:34 +0900)]
[locomotiv] Remove GraphInput/Output node method calls (#6719)
This commit removes all the GraphInput::node and GraphOutput::node
method calls in locomotiv. This is a step toward loco GraphInput/Output
class redesign.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 07:08:23 +0000 (16:08 +0900)]
[moco-tf] Canonicalize TFConcatV2 (#6703)
* [moco-tf] Canonicalize TFConcatV2
This will implement Canonicalize of TFConcatV2 to TensorConcat
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix log msg
Add ONNX sources v1.5 (#6642)
Add a cmake configs for fetching ONNX v1.5 sources.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 07:05:03 +0000 (16:05 +0900)]
[exo-tflite] Do NOT invoke GraphInput/Output node (#6717)
This commit removes all the GraphInput::node and GraphOutput::node
method calls in exo-tflite. This is a step toward loco GraphInput/Output
class redesign.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 07:04:36 +0000 (16:04 +0900)]
[moco-tf] Introduce TFStopGradient (#6715)
* [moco-tf] Introduce TFStopGradient
This will introduce TFStopGradient IR for TensorFlow StopGradient node and required codes
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix comment
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 07:02:38 +0000 (16:02 +0900)]
[moco-tf] Do NOT invoke GraphInput/Output node (#6716)
As a step to loco redesign, this commit removes all
GraphInput::node and GraphOutput::node method calls in moco-tf.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 06:43:55 +0000 (15:43 +0900)]
[neurun] Introduced ITimer, CPUTimer and CLTimer (#6690)
* [neurun] Introduced ITimer, CPUTimer and CLTimer
* Introduced ITimer, CPUTimer and CLTimer
* Added timer getters to backends config
* Made ProfileObserver to measure time with ITimer
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Review fixes
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
채성우/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 06:42:07 +0000 (15:42 +0900)]
[loco] Implement DepthwiseConv2D shape inference (#6569)
* [loco] Implement DepthwiseConv2D shape inference
This commit extends CanonicalShapeInferenceRule to accept
DepthwiseConv2D nodes.
Signed-off-by: seongwoo <sw4670.chae@samsung.com>
* fix a typo.
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 05:01:52 +0000 (14:01 +0900)]
[res] TensorFlow StopGradient_000 (#6710)
This will introduce TensorFlow StopGradient_000 test material for basic StopGradient operator test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 05:01:30 +0000 (14:01 +0900)]
[mocotest-tf] Enable Sqrt and SquaredDifference (#6711)
This will enable Sqrt and SquaredDifference basic testing
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 05:01:09 +0000 (14:01 +0900)]
[tf2tflite] Enable Sqrt and SquaredDifference (#6712)
This will enable Sqrt and SquaredDifference basic testing
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 04:44:02 +0000 (13:44 +0900)]
[moco-tf] Introduce TypeInferencePass (#6702)
This will introduce TypeInferencePass class to provide type inference as a Transform
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 04:38:39 +0000 (13:38 +0900)]
[moco-tf] Introduce ShapeInferencePass (#6701)
This will introduce ShapeInferencePass class to provide shape inference as a Transform
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 20 Aug 2019 04:10:01 +0000 (13:10 +0900)]
Make FeatureShape supports NCHW layout (#6705)
This commit makes FeatureShape supports NCHW layout.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 20 Aug 2019 04:09:27 +0000 (13:09 +0900)]
[neurun] Removed some dead code (#6709)
Removed some dead code from ExecTime test
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 04:04:37 +0000 (13:04 +0900)]
[exo-tflite] Basic Classes for TFLDialect (#6682)
These commit adds basic classes for TFLDialect.
Namespace is 'locoex' since this is an extension of `loco`.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 04:01:29 +0000 (13:01 +0900)]
[moco-tf] Type inference for TFSoftmax (#6700)
This will add type inference for TFSoftmax node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 03:46:25 +0000 (12:46 +0900)]
Use unified coverage report command (#6537)
- Use unified coverage report command in docker_coverage_report.sh
- Update Makefile.template to package infra
- Update test_coverage.sh to archive test data and codes
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 02:29:19 +0000 (11:29 +0900)]
[loco] Introduce push_node/pull_node helper (#6684)
This commit introduces push_node/pull_node helper which serves as an
alternative to "node" method in GraphInput/GraphOutput class.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 20 Aug 2019 00:42:07 +0000 (09:42 +0900)]
Replace nnapi shim headers into libs (#6588)
Introduce libs/nnapi
Replace NeuralNetworksShims.h, NeuralNetworksExShims.h NeuralNetworksLoadHelpers.h to libs/nnapi
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Aug 2019 00:41:20 +0000 (09:41 +0900)]
[moco-tf] GraphBuilder for TFConcatV2 (#6673)
This will fill GraphBuilder for TFConcatV2 and tests. Also ShapeInference implementation that is required by the test code.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 19 Aug 2019 23:34:59 +0000 (08:34 +0900)]
[tf2tflite] Test REGRESSION_0000 (#6681)
From this commit, REGRESSION_0000 is tested by tf2tflite
Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
[mir] Remove Dropout operation (#6675)
This is a no-op in inference mode.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>