platform/core/ml/nnfw.git
4 years ago[exo-tflite] Introduce TFLAdd (#7113)
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>
4 years ago[tflite_loader] implement div and sqrt (#7114)
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>
4 years ago[exo-tflite] Revise shape inf test (#7144)
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>
4 years agoEnable RNN op for ACL neon (#7137)
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>
4 years ago[mir] Pass aggregate arguments by const reference (#7143)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 3 Sep 2019 18:38:46 +0000 (21:38 +0300)]
[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>
4 years ago[mir_caffe] Do not insert Transposes (#7110)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 3 Sep 2019 17:06:46 +0000 (20:06 +0300)]
[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>
4 years ago[mir_caffe2] Do not insert Transposes (#7139)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 3 Sep 2019 17:04:14 +0000 (20:04 +0300)]
[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>
4 years ago[soft_backend] Added Resize shape checking (#7107)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 3 Sep 2019 17:03:19 +0000 (20:03 +0300)]
[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>
4 years ago[mir_onnx] Remove unsing converters before operation with NCHW layout (#7044)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 3 Sep 2019 17:02:49 +0000 (20:02 +0300)]
[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>
4 years agoEnable L2Pool2D op for ACL neon (#7134)
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>
4 years ago[loco] Add bool return type for shape infer to() (#7131)
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>
4 years ago[tflite_loader] implement squared_difference (#7127)
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>
4 years agoEnable L2Normalization op for ACL neon (#7129)
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>
4 years agoFix misapplied enum value in KernelGenerators (#7130)
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>
4 years agoEnable acl neon backend mul operation (#7105)
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>
4 years ago[tflite_loader] implement tanh (#7126)
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>
4 years agoRemove hardcode for L2Normalization (#7122)
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>
4 years ago[tflite_loader] implement rsqrt (#7124)
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>
4 years agoChange to include the integrated header of ACL NEON (#7117)
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>
4 years ago[neurun] Add srcn library for new neurun backend (#6993)
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

4 years ago[neurun] Appends apis to ITensorBuilder (#6973)
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

4 years ago[neurun] Make {pre|post}Visit of TemplTensorBuilder recursive (#7064)
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>
4 years agoUpdate dockerfile - numpy (#7111)
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>
4 years agoUse static casting to convert enum type (#7104)
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>
4 years ago[res] Introduce UNIT_Mean_00X testcases (#7051)
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>
4 years ago[exo-tflite] Adding TFLShapeInferenceRule into ShapeInference (#7096)
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

4 years agoExplicit type to prevent overflow (#7106)
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>
4 years agoFix copy constructor (#7102)
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>
4 years agoFix deref null pointer error on scheduler (#7094)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 3 Sep 2019 00:36:24 +0000 (09:36 +0900)]
Fix deref null pointer error on scheduler (#7094)

Change to runtime error instead of assert for deref null pointer error on scheduler

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[exo-tflite] Introducing TFLMaxPool2D (#7087)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 22:30:59 +0000 (07:30 +0900)]
[exo-tflite] Introducing TFLMaxPool2D (#7087)

This adds TFLMaxPool2D into TFLDialect.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[moco-tf] Bugfix of FixShapeTransform of Squeeze (#7031)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 2 Sep 2019 22:20:14 +0000 (07:20 +0900)]
[moco-tf] Bugfix of FixShapeTransform of Squeeze (#7031)

If `Squeeze` operation have `squeeze_dims` as `[-1,-2]` and input rank is 4, it should be converted to `[2, 3]`
According to current implementation, the code erase -1 first and then put 3 in the `squeeze_dims`
However, it causes some bug. If -1 is erased, iterator of `squeeze_dims` points -2.
And then if 3 is inserted, the iterator points 3 because it is `Set`!
Now, `squeeze_dims` is `[-2, 3]` and iterator try to iterate next element but there is no more element
because 3 is the last element.

Therefore this commit will fix this bug by introducing new `Set`

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[moco-tf] Update FixShapeTransform test with AvgPool (#7041)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 22:06:44 +0000 (07:06 +0900)]
[moco-tf] Update FixShapeTransform test with AvgPool (#7041)

This will update FixShapeTransform test to test with TFAvgPool

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[mir] Remove support for Reduce and Pool (#7074)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 2 Sep 2019 14:50:30 +0000 (17:50 +0300)]
[mir] Remove support for Reduce and Pool (#7074)

- Reduce and Pool operations were replaced by `ReduceMean`, `AvgPool2D` and `MaxPool2D`.
- Make `ReduceOp` a base class for `ReduceMeanOp`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir2loco] Remove support for PoolOp (#7071)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 2 Sep 2019 10:28:26 +0000 (13:28 +0300)]
[mir2loco] Remove support for PoolOp (#7071)

This operation was replaced by `AvgPool2DOp` and `MaxPool2DOp`.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Remove support for Reduce and Pool (#7057)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 2 Sep 2019 10:25:29 +0000 (13:25 +0300)]
[nnc] Remove support for Reduce and Pool (#7057)

- These operation were replaced by `ReduceMean`, `AvgPool2D` and `MaxPool2D`.
- Pool operations are supported in DataFormatSwitcher optimization.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[exo-tflite] functions to build node (#7080)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 09:06:39 +0000 (18:06 +0900)]
[exo-tflite] functions to build node (#7080)

This adds functions to build featureEncode and featureDecode, which are frequently used.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[exo-tflite] Adding knob for AveragePool2D conversion (#7092)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 09:04:59 +0000 (18:04 +0900)]
[exo-tflite] Adding knob for AveragePool2D conversion (#7092)

This adds knob for AveragePool2D conversion. Default is false.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years agoEnable Floor op for ACL neon (#7100)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 2 Sep 2019 08:25:52 +0000 (17:25 +0900)]
Enable Floor op for ACL neon (#7100)

This commit enables to support Floor op for ACL neon.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[exo-tflite] Adding TFLTypeInferenceRule into TypeInference (#7097)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 08:24:26 +0000 (17:24 +0900)]
[exo-tflite] Adding TFLTypeInferenceRule into TypeInference (#7097)

This adds TFLTypeInferenceRule into TypeInference.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[tflite_loader] Add Mul and Sub operator (#7099)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 07:55:58 +0000 (16:55 +0900)]
[tflite_loader] Add Mul and Sub operator (#7099)

It adds mul and sub operator to run ST model.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years agoFix uninitialized field (#7089)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 2 Sep 2019 06:54:24 +0000 (15:54 +0900)]
Fix uninitialized field (#7089)

Fix uninitialized field contructor warning in neurun core and backend

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years agoEnable Exp op for ACL neon (#7093)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 2 Sep 2019 06:14:04 +0000 (15:14 +0900)]
Enable Exp op for ACL neon (#7093)

This commit enables to support Exp op for ACL neon.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[exo-tflite] Change the name of input of TFLRelu (#7081)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 04:16:38 +0000 (13:16 +0900)]
[exo-tflite] Change the name of input of TFLRelu (#7081)

* [exo-tflite] Change the name of input of TFLRelu

Input name follows TensorFlow input naming. (input -> features)

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

4 years agoApply finding frontend layout of operand (#7065)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 2 Sep 2019 04:08:32 +0000 (13:08 +0900)]
Apply finding frontend layout of operand (#7065)

This commit applies finding frontend layout of operand.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[tflite_loader] implement Relu6 operator (#7068)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 04:08:03 +0000 (13:08 +0900)]
[tflite_loader] implement Relu6 operator (#7068)

It adds `Relu6` for mobilenet v3.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years agoFix null type reference (#7059)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 2 Sep 2019 03:45:24 +0000 (12:45 +0900)]
Fix null type reference (#7059)

Instead of using getOperandSize, use type pointer to find out operand has unspecified shape

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[exo-tflite] Introducing TFLAveragePool2D node (#7054)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Mon, 2 Sep 2019 03:44:12 +0000 (12:44 +0900)]
[exo-tflite] Introducing TFLAveragePool2D node (#7054)

* [exo-tflite] Introducing TFLAveragePool2D node

This adds TFLAveragePool2D node, which represelt AVERAGE_POOL_2D of TensorFlow Lite.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* modified per jh1304's review. Filter and Stride were made

4 years agoCoverity issue on scheduler (#7072)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 2 Sep 2019 00:56:33 +0000 (09:56 +0900)]
Coverity issue on scheduler (#7072)

- Unreached default in switch-case
- Unchecked return of library call

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[exo-tflite] Introducing TFLTypeInference (#7015)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 1 Sep 2019 23:03:02 +0000 (08:03 +0900)]
[exo-tflite] Introducing TFLTypeInference (#7015)

This adds TFLTypeInference to infer type for TFL nodes.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years ago[pepper-str] Fix "unused parameter" warning in CI (#7075)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Sun, 1 Sep 2019 23:02:26 +0000 (08:02 +0900)]
[pepper-str] Fix "unused parameter" warning in CI (#7075)

This fix "unused parameter" warning in CI.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
4 years agoRemove unnecessary helper function (#7066)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 09:59:01 +0000 (18:59 +0900)]
Remove unnecessary helper function (#7066)

This commit removes unnecessary helper function.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years agoMake ConcatLayers support NCHW frontend layout (#7063)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 09:41:08 +0000 (18:41 +0900)]
Make ConcatLayers support NCHW frontend layout (#7063)

This commit makes ConcatLayers support NCHW frontend layout.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[neurun] Use LIB_PTHREAD variable in CMake (#7069)
이한종/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 09:25:38 +0000 (18:25 +0900)]
[neurun] Use LIB_PTHREAD variable in CMake (#7069)

Use variable `${LIB_PTHREAD}` rather than hardcoded `pthread`. This is
useful for Android build which does not have pthread lib. Android
contains pthread in libc.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
4 years agoRevert commits related to mutex in acl_cl::Object (#7062)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 08:37:25 +0000 (17:37 +0900)]
Revert commits related to mutex in acl_cl::Object (#7062)

- Revert "Fix deadlock when access two acl_cl at once (#6500)"
- Revert "[neurun] Change acl_cl::Object::access to multithread safe (#5636)"

This reverts commit 51671b098692a133d86624afc5455c6e01ef9302
This reverts commit 6097ce0e7d59be4342db40e1bfc104d5ec88c5fa

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
4 years ago[mir_caffe] Switch to AvgPool2D and MaxPool2D ops (#7029)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 08:11:21 +0000 (17:11 +0900)]
[mir_caffe] Switch to AvgPool2D and MaxPool2D ops (#7029)

Switch from `PoolOp` to `AvgPool2DOp` and `MaxPool2DOp`. The former ones are deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years agoCheck dladdr return value (#7061)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Aug 2019 07:32:17 +0000 (16:32 +0900)]
Check dladdr return value (#7061)

Check dladdr return value and log if fail to load

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years agoFix unused return value (#7060)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Aug 2019 07:17:14 +0000 (16:17 +0900)]
Fix unused return value (#7060)

Fix unused return value of call for dimension valid check

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[mir_onnx] Switch GlobalAveragePool converter to AvgPool2DOp (#7049)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 07:14:22 +0000 (16:14 +0900)]
[mir_onnx] Switch GlobalAveragePool converter to AvgPool2DOp (#7049)

Switch from `PoolOp` to `AvgPool2DOp` in `GlobalAveragePool` converter. The former one is deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[exo-tflite] Make "Check.h" to use pepper instead of pp (#7038)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 30 Aug 2019 07:07:32 +0000 (16:07 +0900)]
[exo-tflite] Make "Check.h" to use pepper instead of pp (#7038)

* [exo-tflite] added pp into cmake scripts

`pp` is added into cmake scripts to use "Check.h", which includes a header in pp.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* pp to lightweight pepper::str

4 years ago[mir] Remove operation names (#7016)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 07:06:58 +0000 (16:06 +0900)]
[mir] Remove operation names (#7016)

Names on operations were difficult to maintain.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years agoFix uncatched exception (#7058)
오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Aug 2019 05:49:30 +0000 (14:49 +0900)]
Fix uncatched exception (#7058)

Operand::operandSize() can throw exeception because sizeOfDataType() in DataType.h can throw runtime exception

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
4 years ago[neurun] Resolve Division by zero in Softmax layer (#7055)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 05:02:07 +0000 (14:02 +0900)]
[neurun] Resolve Division by zero in Softmax layer (#7055)

This commit will resolve division by zero in Softmax layer

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[pepper-str] make a function in header inline (#7043)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 30 Aug 2019 02:41:38 +0000 (11:41 +0900)]
[pepper-str] make a function in header inline (#7043)

* [pepper-str] make a function in header inline

This adds `inline` keyword to `str_impl(...)` function in header.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* added inline to all str_impl

4 years ago[neurun] Implemented scheduler test with branched graph (#6926)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 02:17:48 +0000 (11:17 +0900)]
[neurun] Implemented scheduler test with branched graph (#6926)

* [neurun] Implemented scheduler test with branched graph

* Implemented scheduler test with branched graph and known execution time
* Added set time methods to ExecTime
* Refactored existing scheduler test a little bit

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* 'set' methods from ExecutionTime replaced with helper functions

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* remove profile data before test

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

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Increased execution time for GPU in last test

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
* Set correct large exec time for gpu

Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
4 years ago[neurun] Prettified HE scheduler a little bit (#6982)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 01:43:27 +0000 (10:43 +0900)]
[neurun] Prettified HE scheduler a little bit (#6982)

* [neurun] Prettified HE scheduler a little bit

* Removed backend transfer time from _run_cache
* _run_cache replaced with _preferred_operations
* Profiling information existence checks added

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

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
4 years ago[neurun] Made scheduler to shuffle backends after all nodes are profiled (#7010)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 30 Aug 2019 01:39:28 +0000 (10:39 +0900)]
[neurun] Made scheduler to shuffle backends after all nodes are profiled (#7010)

[neurun] Made scheduler to shuffle backends after all nodes are already profiled

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
4 years ago[neurun] Introduce ITensorManager to be used as MemoryManager (#7048)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 00:59:05 +0000 (09:59 +0900)]
[neurun] Introduce ITensorManager to be used as MemoryManager (#7048)

Introduce ITensorManager to be used as MemoryManager instead of existing
MemoryManager in the future.

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[moco-tf] Delete FixPaddingTransform (#7042)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 30 Aug 2019 00:44:59 +0000 (09:44 +0900)]
[moco-tf] Delete FixPaddingTransform (#7042)

This will delete unused FixPaddingTransform

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[tf2tflite] Enable moco logs via TF2TFLITE_Log_Frontend (#7040)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 30 Aug 2019 00:04:32 +0000 (09:04 +0900)]
[tf2tflite] Enable moco logs via TF2TFLITE_Log_Frontend (#7040)

Let's use TF2TFLITE_Log_Frontend instead of MOCO_LOG.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[res] Introduce UNIT_Squeeze_003 test (#7039)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 30 Aug 2019 00:04:20 +0000 (09:04 +0900)]
[res] Introduce UNIT_Squeeze_003 test (#7039)

This test is for checking that `Squeeze` operation handle multiple negative
squeeze_dims or not

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
4 years ago[mir_tflite] Switch to AvgPool2D and MaxPool2D ops (#7024)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:59:11 +0000 (06:59 +0900)]
[mir_tflite] Switch to AvgPool2D and MaxPool2D ops (#7024)

Switch from `PoolOp` to `AvgPool2DOp` and `MaxPool2DOp`. The former ones are deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_caffe2] Switch to AvgPool2D and MaxPool2D ops (#7032)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:52:24 +0000 (06:52 +0900)]
[mir_caffe2] Switch to AvgPool2D and MaxPool2D ops (#7032)

Switch from `PoolOp` to `AvgPool2DOp` and `MaxPool2DOp`. The former ones are deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Switch to AvgPool2D and MaxPool2D ops (#7023)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:34:27 +0000 (06:34 +0900)]
[mir_onnx] Switch to AvgPool2D and MaxPool2D ops (#7023)

Switch from `PoolOp` to `AvgPool2DOp` and `MaxPool2DOp`. The former ones are deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir2loco] Add support for AvgPool2D and MaxPool2D (#7022)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:33:27 +0000 (06:33 +0900)]
[mir2loco] Add support for AvgPool2D and MaxPool2D (#7022)

These operations are the future replacement of the `Pool` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_tflite] Switch to ReduceMean op (#7004)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:30:21 +0000 (06:30 +0900)]
[mir_tflite] Switch to ReduceMean op (#7004)

Switch from `ReduceOp` to `ReduceMeanOp`. The former one is deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir_onnx] Switch to ReduceMean op (#7003)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 21:28:37 +0000 (06:28 +0900)]
[mir_onnx] Switch to ReduceMean op (#7003)

Switch from `ReduceOp` to `ReduceMeanOp`. The former one is deprecated.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Implemented Data Format Switcher (#6932)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 19:02:44 +0000 (22:02 +0300)]
[nnc] Implemented Data Format Switcher (#6932)

* Implemented PoolOp visitor in switcher

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
4 years ago[neurun] Introduce AclInternalBufferManager class (#6983)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 29 Aug 2019 10:00:48 +0000 (19:00 +0900)]
[neurun] Introduce AclInternalBufferManager class (#6983)

Introduce AclInternalBufferManager class which will be used by acl's
layers

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[neurun] Fix nnfw_output_tensorinfo (#7035)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 09:48:23 +0000 (18:48 +0900)]
[neurun] Fix nnfw_output_tensorinfo (#7035)

nnfw_session::output_tensoninfo should uses output size, instead of input size.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[moco-tf] Use logo Pass (#7030)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 09:35:02 +0000 (18:35 +0900)]
[moco-tf] Use logo Pass (#7030)

* [moco-tf] Use logo Pass

This will update to use logo Pass as transformations for two Optimiziers

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* use moco::tf::Knob

4 years ago[moco-tf] Use loco::NodeShape for inputs (#7008)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 09:20:58 +0000 (18:20 +0900)]
[moco-tf] Use loco::NodeShape for inputs (#7008)

* [moco-tf] Use loco::NodeShape for inputs

This will change fix_shape() to use loco::NodeShape for input's shape information

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

4 years ago[nnc] Add support for ReduceMean (#7002)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 08:52:38 +0000 (17:52 +0900)]
[nnc] Add support for ReduceMean (#7002)

This operation is the future replacement of the `Reduce` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnc] Add support for AvgPool2D and MaxPool2D (#7011)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 08:52:13 +0000 (17:52 +0900)]
[nnc] Add support for AvgPool2D and MaxPool2D (#7011)

These operations are the future replacement of the `Pool` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[exo-tflite] Placeholders for TFL nodes (#7021)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 08:27:01 +0000 (17:27 +0900)]
[exo-tflite] Placeholders for TFL nodes (#7021)

* [exo-tflite] Placeholders for TFL nodes

This will add TODO comment as placeholders for TFL nodes to come

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* use name from schema

4 years ago[exo-tflite] Introducing TFLShapeInference (#6991)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 08:19:11 +0000 (17:19 +0900)]
[exo-tflite] Introducing TFLShapeInference (#6991)

* [exo-tflite] Introducing TFLShapeInference

This adds TFLShapeInference that infer the shape of TFL nodes and TFLShapeAnnot that passes shape from canonical node.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* adding missing graph input

* fix typo

* remove Forward word from internal class naming

4 years ago[neurun] Add iterate() to FunctionSequence (#6977)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 29 Aug 2019 07:25:31 +0000 (16:25 +0900)]
[neurun] Add iterate() to FunctionSequence (#6977)

Add iterate() to FunctionSequence for #6156

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[nnpkg_tool] Revise nnpkg_test and model2nnpkg for readable log (#7028)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 07:05:30 +0000 (16:05 +0900)]
[nnpkg_tool] Revise nnpkg_test and model2nnpkg for readable log (#7028)

`nnpkg_test`
- distinguish the run and compare result.
- shows the errors after a blank line.
- does not use `set -e` to continue after error for pretty printing.

`model2nnpkg`
- It becmome less noisy.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[nnpkg_tool] Introduce nncc-tc-to-nnpkg-tc (#7005)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 07:02:38 +0000 (16:02 +0900)]
[nnpkg_tool] Introduce nncc-tc-to-nnpkg-tc (#7005)

Introduce tool for converting nncc testcase to nnpkg testcase.
Please read README.md for usage.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[mir] Add AvgPool2D and MaxPool2D operations (#6996)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 05:55:26 +0000 (14:55 +0900)]
[mir] Add AvgPool2D and MaxPool2D operations (#6996)

These are the future replacement of the `Pool` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[mir] Add ReduceMean operation (#6994)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 29 Aug 2019 05:55:13 +0000 (14:55 +0900)]
[mir] Add ReduceMean operation (#6994)

This is a future replacement of `Reduce` operation.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
4 years ago[nnpkg_tool] Introduce nnpkg_test.sh (#7020)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 05:39:06 +0000 (14:39 +0900)]
[nnpkg_tool] Introduce nnpkg_test.sh (#7020)

Introduce a tool for running an nnpackage testcase.
It will run nnpackage with nnpackage_run, and compare the result.
For usage, find README.md.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[neurun] Apply InternalBufferManager to RNN on acl_cl (#6978)
김용섭/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 29 Aug 2019 05:35:18 +0000 (14:35 +0900)]
[neurun] Apply InternalBufferManager to RNN on acl_cl (#6978)

Apply InternalBufferManager to RNN on acl_cl

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
4 years ago[moco-tf] Introduce ProgressReporter (#7013)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 05:26:09 +0000 (14:26 +0900)]
[moco-tf] Introduce ProgressReporter (#7013)

* [moco-tf] Introduce PhaseEventListener

This will introduce PhaseEventListener that implements logo::PhaseEventListener that dumps Phase event logs

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

4 years agoIntroduce model2nnpackage (#6976)
이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 04:52:16 +0000 (13:52 +0900)]
Introduce model2nnpackage (#6976)

This patch introduces model2nnpackage.
It will take model file (either circle or tflite) and generate
containing nnpackage.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
4 years ago[exo-tflite] Placeholders for TFLNodes.lst (#7019)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 04:41:13 +0000 (13:41 +0900)]
[exo-tflite] Placeholders for TFLNodes.lst (#7019)

This will add TODO comments in TFLNodes.lst as placeholders for new TFL nodes to come

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Use throw instead of assert (#7006)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 29 Aug 2019 03:48:56 +0000 (12:48 +0900)]
[exo-tflite] Use throw instead of assert (#7006)

The current implementation of translateLocoTypeToTFLite may return an
invalid value if the code is built with release configuration.

This commit replaces assert with throw to prevent undefined behavior.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-log] Extract LoggingContext class (#6999)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 29 Aug 2019 03:48:35 +0000 (12:48 +0900)]
[moco-log] Extract LoggingContext class (#6999)

LoggingContext class is currently declared in Log.h, and thus it is
impossible to access this class declaration without including macros
defined in Log.h, which leads to macro name conflicts in some case.

This commit introduce a dedicated file for LoggingContext class to
allow users to access LoggingContext class without the risk of macro
name conflicts.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[nnkit] Remove empty directories (#6967)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 29 Aug 2019 01:09:26 +0000 (10:09 +0900)]
[nnkit] Remove empty directories (#6967)

All the components are now at the top-level.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
4 years ago[moco-tf] Use make_shape_inference_data in fix_shape (#6998)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 00:38:47 +0000 (09:38 +0900)]
[moco-tf] Use make_shape_inference_data in fix_shape (#6998)

This will use make_shape_inference_data() for patterns of make_unique() + copy_shape_values() with ShapeInferenceData

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
4 years ago[exo-tflite] Enabling OperationExporter to handle TFLNode (#7001)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 29 Aug 2019 00:30:55 +0000 (09:30 +0900)]
[exo-tflite] Enabling OperationExporter to handle TFLNode (#7001)

This enables OperationExporter to handle TFLNode

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