윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 09:07:15 +0000 (18:07 +0900)]
[exo-tflite] Prepare slots for template initialization (#7227)
This adds slots for template initialization in CanonicalNodeConverter, which prevents code conflict.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 09:06:06 +0000 (18:06 +0900)]
[cusop] replace new with make_shared (#7211)
custom::KernelRegistry will be created with make_shared.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 5 Sep 2019 08:35:07 +0000 (11:35 +0300)]
[custom op] Build custom kernels (#6964)
* [custom op] Build custom kernels
Update cpu backend's `KernelGenerator` to build custom operation kernels
* Fix allocations in custom node kernel generator
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
윤지영/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 08:32:18 +0000 (17:32 +0900)]
Add new backend for srcn (#7132)
* [neurun] Add new backend for srcn
This patch has a basic framework for adding new backend.
In practice, normal behavior is not implemented.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Fix an issue where arm_neon.h file is not always found
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 08:21:55 +0000 (17:21 +0900)]
[moco-tf] Return for ShapeInferencePass (#7220)
This will return value from loco shape inference in ShapeInferencePass
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 08:19:36 +0000 (17:19 +0900)]
[moco-tf] Use loco::shape in import (#7217)
This will revise import to use loco shape instead of ShapeInferenceData
- also add guards for safety
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 08:10:12 +0000 (17:10 +0900)]
[loco] Enhancing TypeInference::to() (#7206)
Now 1) TypeInference::to()returns bool 2) checks previously inferred dtype
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 08:07:23 +0000 (17:07 +0900)]
[exo-tflite] Introducing ReluConverter (#7216)
This converter converts loco::Relu to locoex::TFLRelu.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 08:02:19 +0000 (17:02 +0900)]
[moco-tf] Skip FuseBinaryIntoPreceding on Scalar (#7219)
The current implementation of FuseBinaryIntoPreceding gets stuck when
it encounters scalar constants.
Let's make FuseBinaryIntoPreceding skip on this case.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 5 Sep 2019 07:54:48 +0000 (10:54 +0300)]
[custom op] Free custom op userdata in CustomNode destructor (#7213)
- Makes userdata sized as this is required to use tflite flexbuffers format
- Changes userdata type to char* in order to properly delete it
- initialize custom kernel fields
- free memory using delete[]
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 07:50:36 +0000 (16:50 +0900)]
[cus_op] remove unnecessary header dependency in nnfw_dev.hpp (#7209)
Move the include to implementation to remove depedencies.
Forwarding declarations are enough:
- Execution.h
- Graph.h
- CustomKernelRegistry.h
Unnecessary dependency:
- compiler/Compiler.h
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 07:40:25 +0000 (16:40 +0900)]
[locop] Use shared FormattedTensorShape (#7212)
The current implementation of CanonicalNodeSummaryBuilder implements its
own TensorShape formatter.
Let's replace this local formater with the shared one.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 07:38:51 +0000 (16:38 +0900)]
[locop] Show value domain (#7202)
LinearV1 Graph Formatter now shows domain if domain(shape) is known.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 07:21:13 +0000 (16:21 +0900)]
[moco_tf] Do shape and type inference in TFOptimizer (#7215)
This will run Shape and Type inference while TF dialect optimizations
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 07:07:26 +0000 (16:07 +0900)]
[exo-tflite] introducing ShapeInferencePass (#7214)
ShapeInferencePass annotates shape of nodes (canonical/TFL/COp nodes).
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 06:55:08 +0000 (15:55 +0900)]
[exo-tflite] type inference for TFLRelu (#7208)
This adds type inference for TFLRelu.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 06:53:12 +0000 (15:53 +0900)]
[exo-tflite] shape inference for TFLRelu (#7210)
This adds shape inferene for TFLRelu.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 06:19:55 +0000 (15:19 +0900)]
Scripts to make nnpkg testsuite and test (#7199)
- Introduce script to make nnpkg testsuite in CI build server
- Introduce script to test nnpkg testsuite in xu4 farm
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 5 Sep 2019 06:15:21 +0000 (15:15 +0900)]
Enable Pad op for ACL neon (#7205)
This commit enables to support Pad op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 05:51:09 +0000 (14:51 +0900)]
[locoex] Enhance COpTypeInference test (#7204)
This includes CanonicalTypeInferenceRule check. This is required for future change of loco::TypeInference, which looks into the dtype of all input nodes. So, the type of loco::Pull should be inferred to infer the type of locoex::COpCall.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 05:27:21 +0000 (14:27 +0900)]
Update armcl-ex library cmake (#7167)
Use finding arm compute package instead of checking target arch
Use target_compile_definition for preprocessor and merge
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 05:26:44 +0000 (14:26 +0900)]
[res] TF test for SquaredDifference broadcast (#7190)
This will add SquaredDifference test material for broadcast operation
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 05:26:12 +0000 (14:26 +0900)]
[res] TF test for Add broadcast with scala (#7195)
This will add TF test material of Add operator with rank 4 tensor with scala
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 05:25:35 +0000 (14:25 +0900)]
[moco-tf] Use ShapeInferenceData for rule (#7184)
* [moco-tf] Use ShapeInferenceData for rule
This will revise TFShapeInferenceRule infer to directly use ShapeInferenceData
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* change scope
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 05:25:07 +0000 (14:25 +0900)]
[res] TF test for rank 4 StopGradient (#7191)
This will add TensorFlow test material for rank 4 StopGradient operator
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 05:24:40 +0000 (14:24 +0900)]
[res_tf] TF test for Sub broadcast (#7192)
This will add TensorFlow test material for Sub broadcast operation
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 05:24:21 +0000 (14:24 +0900)]
[exo-tflite] Added TODO for each TFL Nodes in shape & type inference code (#7203)
This creates a slots for visit() of each TFL node.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 05:22:56 +0000 (14:22 +0900)]
[loco] Introduce TensorAxis header (#7188)
Currently, PermutingCodec internally declares TensorAxis alias.
Let's extract this as a separate header and reuse it!
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 5 Sep 2019 05:22:52 +0000 (14:22 +0900)]
Enable LSTM op for ACL neon (#7201)
This commit enables to support LSTM op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 05:22:34 +0000 (14:22 +0900)]
[locop] NodeSummary with Comments (#7193)
This commit allows usersr to add multi-line comments to NodeSummary, and
revises LinearV1 Graph Formatter to show these comments properly.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 5 Sep 2019 05:22:17 +0000 (14:22 +0900)]
Enable LocalResponseNormalization op for ACL neon (#7149)
This commit enables to support LocalResponseNormalization op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 05:11:44 +0000 (14:11 +0900)]
Introduce tfts v0.1 (#7165)
* Introduce tfts v0.1
This commit introduces TensorFlow Testcase Service (tfts) v0.1.
The current version supports basic shape check on TensorFlow testcases
through nnkit-tf.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Use simple tfts_check instead of tfts_shape_check
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 05:09:23 +0000 (14:09 +0900)]
[exo-tflite] Remove TFLShapeAnnot and TFLTypeAnnot (#7197)
Instead of using TFLShapeAnnot and TFLTypeAnnot, we will have type and shape inference for each TFL Nodes. So these annot classes is removed.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 04:31:51 +0000 (13:31 +0900)]
[locop] Remove symbol_lookup helper (#7196)
This helper is no longer meaningful.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 5 Sep 2019 04:28:40 +0000 (07:28 +0300)]
[custom op] Implement custom op registration using public API (#7181)
* [custom op] Implement custom op registration using public API
Adds public custom operation registration method
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
* format fix
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 04:25:51 +0000 (13:25 +0900)]
[res] TF test for Mul broadcast (#7187)
This will add two Mul test materials for broadcast operation
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 5 Sep 2019 04:25:31 +0000 (13:25 +0900)]
[res] TF test for Add broadcast (#7186)
This will add two Add TF test materials for broadcast operation
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 5 Sep 2019 04:12:52 +0000 (07:12 +0300)]
[custom op] overload getName in CustomNode implementation (#7180)
Fixes CustomNode class being abstract
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Sep 2019 02:13:11 +0000 (11:13 +0900)]
Update srcn kernel library cmake (#7135)
Use finding arm_neon.h instead of checking target arch
Link libraries OpenMP_CXX_LIBRARIES
Prepare compile definition NCNN and comment out
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 22:30:46 +0000 (07:30 +0900)]
[loco] Revise shape inference condition (#7161)
* [loco] Revise shape inference condition
This will add condition to ShapeInference to infer when target node shape is unknown and input(s) shape is ready
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove print code
[mir_caffe2] Reshape bias for Convolution (#7170)
Fixes compilation error of mobilenet.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir] Change type of strides parameter (#7179)
Change the type of `strides` parameter of convolutional operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] Change type of strides argument (#7177)
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_tflite] Change type of strides argument (#7176)
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir2loco] Change type of strides argument (#7178)
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe] Change type of strides argument (#7175)
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe2] Change type of strides argument (#7174)
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_onnx] Change type of strides argument (#7173)
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 4 Sep 2019 12:50:28 +0000 (21:50 +0900)]
Fix neurun build fail (#7171)
Fix neurun build fail by ITensorManager change
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 11:56:25 +0000 (20:56 +0900)]
Enable ResizeBilinear op for ACL neon (#7151)
This commit enables to support ResizeBilinear op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 11:55:51 +0000 (20:55 +0900)]
[neurun] Nit : Put override specifier (#7154)
Nit : Put override specifier in NopFunction.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 11:54:29 +0000 (20:54 +0900)]
[neurun] Implement classes inherit to ITensorManager (#7083)
* [neurun] Implement classes inherit to ITensorManager
Implement classes inherit to ITensorManager such as cpu/TensorManager
and AclTensorManager
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Add findTensorAsParent()
* Merge two buildXXXTensor into one with as_const param
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 4 Sep 2019 11:05:11 +0000 (20:05 +0900)]
Remove unused env variable utility (#7140)
Unify environment variable utility
Remove unused environment variable utility functions
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 09:51:50 +0000 (18:51 +0900)]
[loco] Introducing BiasDecode (#7158)
This introduce loco::BiasDecode, which translate Bias domain to Tensor domain.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 09:24:22 +0000 (18:24 +0900)]
Enable LogicalNot op for ACL neon (#7159)
This commit enables to support LogicalNot op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 4 Sep 2019 08:18:45 +0000 (17:18 +0900)]
Fix memory leak in srcn (#7162)
Delete allocated array before fast return
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 08:02:42 +0000 (17:02 +0900)]
Enable Unpack op for ACL neon (#7133)
This commit enables to support Unpack op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 07:26:55 +0000 (16:26 +0900)]
[exo-tflite] renaming TFLConverter to CanonicalNodeConverter (#7152)
TFLConverter was renamed to CanonicalNodeConverter, meaning "convert caninical node to TFL node"
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 4 Sep 2019 06:16:46 +0000 (09:16 +0300)]
[custom op] Update custom kernel registry to use C api version (#6288)
* [custom op] Update custom kernel registry to use C api version
Split custom kernel and kernel registry into separate files
Now custom kernel uses api types
Link neurun core library with API headers
* update with latest changes to #6219
* Update kernel registry with changes to api. Link neurun core with nnfw-header
* add missed license
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 05:57:29 +0000 (14:57 +0900)]
Enable Transpose op for ACL neon (#7155)
This commit enables to support Transpose op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 05:57:17 +0000 (14:57 +0900)]
Enable Logistic op for ACL neon (#7156)
This commit enables to support Logistic op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 04:26:30 +0000 (13:26 +0900)]
[moco-tf] Use logo for Importer (#7119)
This will revise Importer to use logo Phase and ProgressReporter
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 03:59:55 +0000 (12:59 +0900)]
[exo-tflite] Export TFLAdd (#7150)
This will add export for TFLAdd node
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 4 Sep 2019 03:39:43 +0000 (06:39 +0300)]
[custom op] Update kernel registry binding (#7141)
* [custom op] Update kernel registry binding
Split kernel registry creation from backend context creation
Signed-off-by: Vladimir Plazun <v.plazun@samsung.com>
* format fix
* fix unused parameter compile error
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 03:39:18 +0000 (12:39 +0900)]
Add permutation type member into PermuteNode (#7085)
This comit adds permutation type member into PermuteNode.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 03:31:52 +0000 (12:31 +0900)]
[exo-tflite] Add knob for ADD (#7148)
This will add knob for ADD as ConvertAdd
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 4 Sep 2019 01:54:03 +0000 (10:54 +0900)]
Add missing copyright in GraphTestcase.h (#7145)
Add missing copyright phrase for loco's GraphTestcase.h
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 01:51:07 +0000 (10:51 +0900)]
[moco-tf] Revise FixShape test with Conv2D (#7116)
This will revise FixShapeTransform test with Conv2D to use moco::tf::TFConv2D from loco::Conv2D IR
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 01:45:30 +0000 (10:45 +0900)]
[neurun] Add buildSubtensor() and objects() to AclMemoryManager (#7084)
Add buildSubtensor() and objects() into AclMemoryManager to be used by AclTensorManager in the future
Apply buildSubtensor() into TemplTensorBuilder
Remove unnecessary namespace
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 01:44:40 +0000 (10:44 +0900)]
[moco-tf] Use logo for TFOptimizer (#7121)
This will revise TFOptimizer to use logo Phase and ProgressReporter
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 01:44:24 +0000 (10:44 +0900)]
[moco-tf] Use logo for Optimizer (#7120)
This will revise Optimizer to use logo Phase and ProgressReporter
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 01:44:02 +0000 (10:44 +0900)]
[moco-tf] Use logo for Canonicalizer (#7118)
This will revise Canonicalizer to use logo Phase and ProgressReporter
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 01:43:39 +0000 (10:43 +0900)]
[exo-tflite] Introduce TFLAdd (#7113)
This will introduce TFLAdd IR and required summary builder
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 01:42:04 +0000 (10:42 +0900)]
[tflite_loader] implement div and sqrt (#7114)
It adds div and sqrt in tflite_loader.
`tf2tflite` converts `rsqrt` into `sqrt` and `div`.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 4 Sep 2019 01:18:14 +0000 (10:18 +0900)]
[exo-tflite] Revise shape inf test (#7144)
This will revise shape inference test as network has TFL and Canonical dialects
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 4 Sep 2019 00:42:19 +0000 (09:42 +0900)]
Enable RNN op for ACL neon (#7137)
This commit enables to support RNN op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
[mir] Pass aggregate arguments by const reference (#7143)
clang-tidy suggests to pass by value and use `std::move`, but it is easy to forget and does not give significant benefits.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe] Do not insert Transposes (#7110)
Remove insertion of Transpose operations, set the data format on operations instead.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[mir_caffe2] Do not insert Transposes (#7139)
Remove insertion of Transpose operations, set the data format on operations instead.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[soft_backend] Added Resize shape checking (#7107)
* Checked that resize work only H and W dims
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
[mir_onnx] Remove unsing converters before operation with NCHW layout (#7044)
* Removed converters
* Fixed some params
* Fixed consant shape in BatchNormalization (for right work of
broadcasting in elementwise operations)
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 3 Sep 2019 11:24:57 +0000 (20:24 +0900)]
Enable L2Pool2D op for ACL neon (#7134)
This commit enables to support L2Pool2D op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 3 Sep 2019 10:14:24 +0000 (19:14 +0900)]
[loco] Add bool return type for shape infer to() (#7131)
This will set boolean return type for ShapeInferenceSession to() method
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 3 Sep 2019 08:23:17 +0000 (17:23 +0900)]
[tflite_loader] implement squared_difference (#7127)
It adds squared_difference operator in tflite_loader.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 3 Sep 2019 08:12:48 +0000 (17:12 +0900)]
Enable L2Normalization op for ACL neon (#7129)
This commit enables to support L2Normalization op for ACL neon.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 3 Sep 2019 08:12:14 +0000 (17:12 +0900)]
Fix misapplied enum value in KernelGenerators (#7130)
This commit fixes misapplied enum value in KernelGenerators.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 3 Sep 2019 08:11:22 +0000 (17:11 +0900)]
Enable acl neon backend mul operation (#7105)
Update acl neon backend ShapeFixer's mul
Remove exception in kernel generator for mul
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 3 Sep 2019 06:52:46 +0000 (15:52 +0900)]
[tflite_loader] implement tanh (#7126)
It adds tanh operator in tflite_loader.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 3 Sep 2019 05:50:11 +0000 (14:50 +0900)]
Remove hardcode for L2Normalization (#7122)
This commit removes hardcode for L2Normalization from KernelGenerator of acl_cl
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 3 Sep 2019 05:49:01 +0000 (14:49 +0900)]
[tflite_loader] implement rsqrt (#7124)
It adds rsqrt operator in tflite_loader.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 3 Sep 2019 05:48:07 +0000 (14:48 +0900)]
Change to include the integrated header of ACL NEON (#7117)
This commit changes to include the integrated header of ACL NEON.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
윤지영/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 3 Sep 2019 05:46:42 +0000 (14:46 +0900)]
[neurun] Add srcn library for new neurun backend (#6993)
* Add srcn library for new neurun backend
This patch includes implementation of srcn kernel.
It only supports Convolution and TransposeConv operations.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Fix format checker errors
* Remove unused code and unnecessary comments
* Remove ${} from REMOVE_ITEM in cmakelist file
* Do not build srcn library on x86_64 machine
* Add return case for OpenMP library not installed
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 3 Sep 2019 05:39:38 +0000 (14:39 +0900)]
[neurun] Appends apis to ITensorBuilder (#6973)
* [neurun] Appends apis to ITensorBuilder
Appends apis to ITensorBuilder for deallocating constant tensors if they
are unused and separating constant tensors and nonconstant tensors
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Change afterFunctionPrepare to postFunctionPrepare
* Fix default parameter of registerTensorInfo
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 3 Sep 2019 04:52:29 +0000 (13:52 +0900)]
[neurun] Make {pre|post}Visit of TemplTensorBuilder recursive (#7064)
Make {pre|post}Visit of TemplTensorBuilder recursive to support for more
than two consecutive concat layers
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 3 Sep 2019 04:33:20 +0000 (13:33 +0900)]
Update dockerfile - numpy (#7111)
Install python3 numpy for andorid-q test generator
Change python-pip to python3-pip
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 3 Sep 2019 02:24:21 +0000 (11:24 +0900)]
Use static casting to convert enum type (#7104)
To resolve implicit enum type casting warning, introduce convert helper and use static casting
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 3 Sep 2019 01:08:24 +0000 (10:08 +0900)]
[res] Introduce UNIT_Mean_00X testcases (#7051)
This commit will introduce `UNIT_Mean_000` ~ `UNIT_MEAN_004`
testcases
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 3 Sep 2019 01:03:04 +0000 (10:03 +0900)]
[exo-tflite] Adding TFLShapeInferenceRule into ShapeInference (#7096)
* [exo-tflite] Adding TFLShapeInferenceRule into ShapeInference
This adds TFLShapeInferenceRule into ShapeInference.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* restore empty line
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 3 Sep 2019 00:41:42 +0000 (09:41 +0900)]
Explicit type to prevent overflow (#7106)
To remove integer overflow warning by svace, use explicit type int64_t, not auto
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 3 Sep 2019 00:38:54 +0000 (09:38 +0900)]
Fix copy constructor (#7102)
Fix uninitialized field in copy constructor
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>