platform/core/ml/nnfw.git
5 years ago[nnc] Make FullyConnectedOp treat the second tensor as ordinary argument (#2858)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 16 Jan 2019 09:23:45 +0000 (12:23 +0300)]
[nnc] Make FullyConnectedOp treat the second tensor as ordinary argument (#2858)

* Change the signature of FullyConnectedOp to identically handle both input parameters.
* Refactor uses of FullyConnectedOp.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Some ops fixes, mobilenet support on ONNX. (#2856)
Андрей Тищенко/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Wed, 16 Jan 2019 09:02:55 +0000 (12:02 +0300)]
[nnc] Some ops fixes, mobilenet support on ONNX. (#2856)

There were fixed/implemented the following operators:
PadOp, GivenTensorFillOp, ConstantOp, ConvOp.
As result we have now 2 working NNs: resnet50 and mobilenet. The last one was tested on interpreter only.

Signed-off-by: Andrew V. Tischenko <a.tischenko@partner.samsung.com>
5 years ago[enco] Fix comment for duplicate_inout_bag (#2864)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 16 Jan 2019 06:53:55 +0000 (15:53 +0900)]
[enco] Fix comment for duplicate_inout_bag (#2864)

This will fix a typo and explanation of the function

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[enco/tflite] Add Regression 0003 testcase (#2854)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 15 Jan 2019 23:55:08 +0000 (08:55 +0900)]
[enco/tflite] Add Regression 0003 testcase (#2854)

This commit introduces Regression 0003 testcase whose inputs are all
constant.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[nnc] Adapt ONNX importer to modified ScaleOp interface (#2860)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 15 Jan 2019 20:00:52 +0000 (23:00 +0300)]
[nnc] Adapt ONNX importer to modified ScaleOp interface (#2860)

Take into account modified interface of ScaleOp in ONNX importer.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Make BiasAddOp and ScaleOp treat the second tensor as ordinary argument (#2848)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 15 Jan 2019 16:16:07 +0000 (19:16 +0300)]
[nnc] Make BiasAddOp and ScaleOp treat the second tensor as ordinary argument (#2848)

* Change the signatures of BiasAddOp and ScaleOp to identically handle both input parameters.
* Refactor uses of BiasAddOp and ScaleOp.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Refactor TFLite importer to support operators with multiple outputs (#2816)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 15 Jan 2019 10:43:29 +0000 (13:43 +0300)]
[nnc] Refactor TFLite importer to support operators with multiple outputs (#2816)

Make operator conversion methods accept and return vectors of `IODescriptor`s.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[tflchef] Support Sqrt operation (#2695)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 15 Jan 2019 10:23:04 +0000 (19:23 +0900)]
[tflchef] Support Sqrt operation (#2695)

This commit supports generating tflite file of Sqrt operation.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
5 years ago[tflchef] tlchef for FullyConnected (#2852)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Jan 2019 06:15:05 +0000 (15:15 +0900)]
[tflchef] tlchef for FullyConnected (#2852)

* [tflchef] tlchef for FullyConnected

This commit adds code to convert recipe for FullyConnected to tflite file.

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

* remove comment about alphabetical order

5 years ago[enco] Refactor DuplicatePass (#2850)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Jan 2019 03:56:25 +0000 (12:56 +0900)]
[enco] Refactor DuplicatePass (#2850)

This will hide DuplicatePass class and provide duplicate_inout_bag() like the other transformation pass

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[enco] Refactor SplitPass (#2849)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Jan 2019 03:54:29 +0000 (12:54 +0900)]
[enco] Refactor SplitPass (#2849)

This will hide SplitPass class and provide split_into_phases() like the other transformation pass

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years ago[enco] Comment for bypass_shuffle (#2843)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Jan 2019 02:07:39 +0000 (11:07 +0900)]
[enco] Comment for bypass_shuffle (#2843)

* [enco] Comment for bypass_shuffle

This will add comment for generate_bypass_shuffle method

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

* apply comments

* apply comment

5 years ago[coco] Add comment of Bag Input Output (#2846)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 15 Jan 2019 01:57:30 +0000 (10:57 +0900)]
[coco] Add comment of Bag Input Output (#2846)

* [coco] Add comment of Bag Input Output

This will add explanation comment for input and output attributes

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

5 years ago[nnc] Refactoring cmake build system (#2844)
Роман Михайлович Русяев/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Mon, 14 Jan 2019 16:57:04 +0000 (19:57 +0300)]
[nnc] Refactoring cmake build system (#2844)

* make separate config and utils files
* refactoring CMakeLists in other components

Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
5 years ago[nnc] Refactor ONNX importer to support operators with multiple outputs (#2831)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Mon, 14 Jan 2019 15:06:55 +0000 (18:06 +0300)]
[nnc] Refactor ONNX importer to support operators with multiple outputs (#2831)

Make operator conversion methods accept and return vectors of IODescriptors.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Fix soft backend implementation for Gemm (#2750)
Андрей Тищенко/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Mon, 14 Jan 2019 14:03:01 +0000 (17:03 +0300)]
[nnc] Fix soft backend implementation for Gemm (#2750)

- Fixed generation of cpu soft backend gemm operation
- Small refactoring and typo fixes of interpreter and onnx frontend

Signed-off-by: Andrew V. Tischenko <a.tischenko@partner.samsung.com>
5 years agoIntegrate TensorFlow Lite 1.12 (#2838)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 14 Jan 2019 07:48:55 +0000 (16:48 +0900)]
Integrate TensorFlow Lite 1.12 (#2838)

* Integrate TensorFlow Lite 1.12

This commit introduces the following changes to use TensorFlow Lite 1.12
instead of TensorFlow Lite 1.7
- Use the latest Flatbuffers (v1.10)
- Update Flatbuffers Build methodology
- Update nnkit's tensorflow lite support library

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix a typo (avaialable -> available)

* Remove debug code

* Update status message

5 years ago[enco] Support constant folding for add, sub, mul, div, sqrt (#2821)
남궁석/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 14 Jan 2019 02:18:18 +0000 (11:18 +0900)]
[enco] Support constant folding for add, sub, mul, div, sqrt (#2821)

* [enco] Support constant folding for add, sub, mul, div, sqrt

Until now, only `coco::Copy` instruction was available for constant folding.
This commit will support some `coco::Eval` instructions in constant folding,
which is add, sub, mul, div, sqrt.

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* minor modifications

5 years ago[nnc] Add check for include generation correctness in acl unit tests (#2722)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Fri, 11 Jan 2019 20:56:53 +0000 (23:56 +0300)]
[nnc] Add check for include generation correctness in acl unit tests (#2722)

- Add checks for correct include DOM generation
- Fix system headers setter in ArtifactModule

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
5 years ago[nnc] Made importer error message prettier (#2761)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 11 Jan 2019 20:54:33 +0000 (23:54 +0300)]
[nnc] Made importer error message prettier (#2761)

Made importer error message more prettier
Message example:
```
NNC can't load model. Detected problems:
  * Cos: unknown layer
  * Only 'NCHW' axis order is supported
  * Sin: unknown layer
```

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
5 years ago[nnc] Remove transposes of inputs and outputs in importers (#2837)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 11 Jan 2019 19:58:47 +0000 (22:58 +0300)]
[nnc] Remove transposes of inputs and outputs in importers (#2837)

Remove transposes of input and outputs tensors in Caffe and Caffe2 importers

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Remove the debugTranspose option (#2813)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 11 Jan 2019 17:28:51 +0000 (20:28 +0300)]
[nnc] Remove the debugTranspose option (#2813)

Remove the `debugTranspose` option which is no longer needed.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Generate getters for unnamed output operations (#2830)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Fri, 11 Jan 2019 15:30:34 +0000 (18:30 +0300)]
[nnc] Generate getters for unnamed output operations  (#2830)

- Remove redundant type in operation analysis
- Move output nodes registration outside of operation analysis
- Refactor artifact tensor declaration in soft backend
- Create persistent tensor for output node without name

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
5 years ago[nnc] Bugfix for the SVACE warning (#2743)
Тимур Отеллович Аблязимов/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Fri, 11 Jan 2019 14:09:33 +0000 (17:09 +0300)]
[nnc] Bugfix for the SVACE warning (#2743)

Pass large arguments by reference and small by value

Signed-off-by: Timur Ablyazimov <t.ablyazimov@samsung.com>
5 years ago [nnc] Free temporary tensors to reduce memory consumption of ACL artifact (#2767)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Fri, 11 Jan 2019 09:55:25 +0000 (12:55 +0300)]
 [nnc] Free temporary tensors to reduce memory consumption of ACL artifact (#2767)

- Remove redundant reverse shape transposes like this [0,1,2,3]->[3,2,1,0]
- Refactor tensor serialization

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
5 years ago[enco] Comment for dead object elimination (#2819)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 11 Jan 2019 08:28:54 +0000 (17:28 +0900)]
[enco] Comment for dead object elimination (#2819)

This will add a comment for getting dead objects

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years agoIntroduce TensorFlow Lite 1.12 package (#2820)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 11 Jan 2019 08:05:41 +0000 (17:05 +0900)]
Introduce TensorFlow Lite 1.12 package (#2820)

This commit introduces TensorFlow Lite 1.12 package.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoIntroduce Abseil package (#2818)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 11 Jan 2019 06:37:09 +0000 (15:37 +0900)]
Introduce Abseil package (#2818)

This commit adds Abseil package which provides abseil target.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[encodump] Support Div operation (#2814)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 11 Jan 2019 00:38:45 +0000 (09:38 +0900)]
[encodump] Support Div operation (#2814)

This commit would enable encodump to get model with Div operation

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[nnsuite] Use specific tflite version (#2807)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Fri, 11 Jan 2019 00:37:51 +0000 (09:37 +0900)]
[nnsuite] Use specific tflite version (#2807)

TensorFlow Lite currently has no public API, and thus its
interface(=API) is subject to change.

Let's use specific tflite version to avoid compilation failure due to
API incompatibility.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[enco] Add comments for constant folding (#2808)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Fri, 11 Jan 2019 00:19:49 +0000 (09:19 +0900)]
[enco] Add comments for constant folding (#2808)

* [enco] Add comments for constant folding

This will add some comments of constant folding

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

* use capital letter

* fix grammer

5 years ago[enco] Add test case for Div operation (#2812)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Fri, 11 Jan 2019 00:19:29 +0000 (09:19 +0900)]
[enco] Add test case for Div operation (#2812)

This commit adds test case for Div support in enco

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[nnc] Fix incorrect operation id for leaky relu (#2815)
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 10 Jan 2019 15:40:22 +0000 (18:40 +0300)]
[nnc] Fix incorrect operation id for leaky relu (#2815)

Id of LeakyRelu operation was incorrectly set as ReLU

Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
5 years ago[nnc] Check that the model has the correct format in Caffe importer (#2753)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 10 Jan 2019 13:38:53 +0000 (16:38 +0300)]
[nnc] Check that the model has the correct format in Caffe importer (#2753)

Ensure that the model file consumed entirely, otherwise complain that the model cannot be loaded. Fixes #2050.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Support Clip and Reshape operations on caffe2 importer (#2751)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 10 Jan 2019 13:04:34 +0000 (16:04 +0300)]
[nnc] Support Clip and Reshape operations on caffe2 importer (#2751)

* Support GivenTensorInt64Fill const tensors
* Convert Clip operation in CappedRelu
* Support Reshape operation

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
5 years ago [nnc] remove redundant shape transposes from acl backend (#2764)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Thu, 10 Jan 2019 10:09:42 +0000 (13:09 +0300)]
 [nnc] remove redundant shape transposes from acl backend  (#2764)

- Remove redundant reverse shape transposes like this [0,1,2,3]->[3,2,1,0]
- Refactor tensor serialization

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
5 years ago[nnc] Fix deconv2D import in tflite importer (#2544)
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 10 Jan 2019 09:30:28 +0000 (12:30 +0300)]
[nnc] Fix deconv2D import in tflite importer (#2544)

Use output shape stored in tflite model as it's impossible to compute it from operation parameters

Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
5 years ago[enco] Support Div for tflite frontend (#2779)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 10 Jan 2019 09:26:33 +0000 (18:26 +0900)]
[enco] Support Div for tflite frontend (#2779)

* [enco] Support Div for tflite frontend

This commit extends enco tflite frontend including Div operation

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Rename ifm, ofm indices to 'num', 'denom' and 'out'

* Add activation assertion

* Input shapes may differ in case of broadcasting

* Remove redundant variable d

* Add TODO notice about object type generalization

5 years ago[ann] Fix Div operation to perform division (#2806)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 10 Jan 2019 09:16:10 +0000 (18:16 +0900)]
[ann] Fix Div operation to perform division (#2806)

This commit fixes Div operation in ann to correct way

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years agoSupport Pre/Post Package Hook (#2798)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 10 Jan 2019 08:16:53 +0000 (17:16 +0900)]
Support Pre/Post Package Hook (#2798)

With this commit, nncc_find_package invokes pre (and post) hooks before (and after)
actual find_package invocation.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoIntroduce nnkit_support_tflite-1.7 target (#2804)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 10 Jan 2019 04:46:55 +0000 (13:46 +0900)]
Introduce nnkit_support_tflite-1.7 target (#2804)

This target allows clients to specify the version of tensorflow lite that
they want to use.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[ann] Support Div operation (#2800)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 10 Jan 2019 04:16:14 +0000 (13:16 +0900)]
[ann] Support Div operation (#2800)

* [ann] Support Div operation

This commit would support Div operation in ann

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Change indent and minor refactoring

5 years agoIntroduce Abseil Source package (#2802)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 10 Jan 2019 04:08:54 +0000 (13:08 +0900)]
Introduce Abseil Source package (#2802)

* Introduce Abseil Source package

This commit introduces Abseil (C++) source package as a nncc external
package.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Update comment

5 years ago[enco] fix typo in comment (#2801)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 10 Jan 2019 04:07:23 +0000 (13:07 +0900)]
[enco] fix typo in comment (#2801)

This will fix typo in reduce_identical_object comment

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years agoUpdate external dependencies on URL change (#2799)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 10 Jan 2019 02:17:51 +0000 (11:17 +0900)]
Update external dependencies on URL change (#2799)

With this commit, ExternalSource_Download will re-download external source
if its URL has changed.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoAdd .vs folder to gitignore (#2797)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 10 Jan 2019 02:10:52 +0000 (11:10 +0900)]
Add .vs folder to gitignore (#2797)

This will add to ignore Visual Studio temporary .vs folder

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
5 years agoRemove deprecated TensorFlowLite package (#2786)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Thu, 10 Jan 2019 01:05:01 +0000 (10:05 +0900)]
Remove deprecated TensorFlowLite package (#2786)

Let's use versioned package instead.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[coco] Add comment of Locatable (#2796)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Thu, 10 Jan 2019 01:04:46 +0000 (10:04 +0900)]
[coco] Add comment of Locatable (#2796)

* [coco] Add comment of Locatable

This will add comment for Locatable interface

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

5 years ago[nnc] Support transpose in acl backend (#2746)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Wed, 9 Jan 2019 16:01:26 +0000 (19:01 +0300)]
[nnc] Support transpose in acl backend (#2746)

- Support transpose operations in acl backend
- Insert transposes in acl backend where needed
- Add test for transpose operation

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
5 years ago[nnc] Support for LSTM Caffe layer (#2721)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 9 Jan 2019 16:01:01 +0000 (19:01 +0300)]
[nnc] Support for LSTM Caffe layer (#2721)

* Add support for LSTM Caffe layer.
* Rename "SoftmaxLoss" Caffe layer to "SoftmaxWithLoss" as it should be.
* Add support for non-default axis for InnerProduct Caffe layer.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Add LeakyRelu activation (#2757)
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 9 Jan 2019 11:46:20 +0000 (14:46 +0300)]
[nnc] Add LeakyRelu activation (#2757)

* [nnc] Add LeakyRelu activation

Implement leaky relu activation function( relu with negative slope )

Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
5 years ago[enco] Fixed debugging typo (#2793)
윤지영/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 9 Jan 2019 10:57:44 +0000 (19:57 +0900)]
[enco] Fixed debugging typo (#2793)

enco_dump_all_bags, _objects, _ops, _instrs take module as a parameter.

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[enco] Support Div for ANN backend (#2792)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 9 Jan 2019 08:42:12 +0000 (17:42 +0900)]
[enco] Support Div for ANN backend (#2792)

* [enco] Support Div for ANN backend

This commit enables ANN backend generation for Div operation

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
* Remove irrelavant modification in 'Debugging.cpp'

5 years ago[nnc] Fix for constant in ModelAnalyzer (#2744)
Андрей Шедько/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 9 Jan 2019 08:29:33 +0000 (11:29 +0300)]
[nnc] Fix for constant in ModelAnalyzer (#2744)

Fixed constants not being visible in soft backend

Signed-off-by: Andrei Shedko <a.shedko@samsung.com>
5 years ago[enco] add comments for loads in DataLayoutConversion (#2789)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 9 Jan 2019 08:14:16 +0000 (17:14 +0900)]
[enco] add comments for loads in DataLayoutConversion (#2789)

* [enco] add comments for loads in DataLayoutConversion

This will add some comments explaining the condition

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

* add about bounded

* use 'note'

5 years ago[coco] Support Sqrt operator in coco (#2790)
장지섭/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 9 Jan 2019 04:25:53 +0000 (13:25 +0900)]
[coco] Support Sqrt operator in coco (#2790)

This commit adds Sqrt op in coco.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
5 years agoIntroduce TensorFlow 1.12 source package (#2785)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Wed, 9 Jan 2019 00:21:40 +0000 (09:21 +0900)]
Introduce TensorFlow 1.12 source package (#2785)

This commit integrates TensorFlowSource (1.12) package into nncc build
system.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[enco] Add comments to subst method (#2775)
박세희/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 8 Jan 2019 23:41:56 +0000 (08:41 +0900)]
[enco] Add comments to subst method (#2775)

* [enco] Add comments to subst method

This will add explanation comment of subst() method

Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* some changes and example code

* use word USER

* Apply suggested comment

* fix typos

* use word Consumer

5 years ago[nnkit] Use specific version of TensorFlow Lite (#2782)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 8 Jan 2019 08:44:44 +0000 (17:44 +0900)]
[nnkit] Use specific version of TensorFlow Lite (#2782)

This commit updates nnkit_support_tflite uses a specific version of
tensorflow lite (v1.7).

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoExternalSource_Download with URL keyword (#2784)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 8 Jan 2019 08:38:46 +0000 (17:38 +0900)]
ExternalSource_Download with URL keyword (#2784)

This commit updates ExternalSource_Download to accept URL keyword as an
argument of the following form:

 ExternalSource_Download(SAMPLE DIRNAME "SAMPLE" URL "...")

This change will make it easy to understand CMake build script.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years agoAdd TensorFlow Lite 1.7 package (#2778)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 8 Jan 2019 07:24:20 +0000 (16:24 +0900)]
Add TensorFlow Lite 1.7 package (#2778)

This commit introduces TensorFlow Lite 1.7 package to nncc build system.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[coco] Support Div operation (#2770)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 8 Jan 2019 00:49:54 +0000 (09:49 +0900)]
[coco] Support Div operation (#2770)

This commit extends coco IR including Div operation

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[enco] Add Sub test case (#2713)
윤지영/On-Device Lab(SR)/Engineer/삼성전자 [Thu, 3 Jan 2019 01:29:41 +0000 (10:29 +0900)]
[enco] Add Sub test case (#2713)

This commit add Sub test case for enco

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[encodump] Add Sub operator (#2731)
윤지영/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 2 Jan 2019 05:47:47 +0000 (14:47 +0900)]
[encodump] Add Sub operator (#2731)

This commit supports to print information about Sub.

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[tflchef] Support Div operation for reverse (#2760)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 2 Jan 2019 04:15:42 +0000 (13:15 +0900)]
[tflchef] Support Div operation for reverse (#2760)

This commit will enable Div operation in tflchef-reverse

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[enco] Add cassert headerfile (#2749)
윤지영/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 2 Jan 2019 00:08:49 +0000 (09:08 +0900)]
[enco] Add cassert headerfile (#2749)

Add cassert header file in operator cpp files

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[RefNN] Remove commented code (#2748)
윤지영/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 2 Jan 2019 00:08:36 +0000 (09:08 +0900)]
[RefNN] Remove commented code (#2748)

Remove unnecessary comment for readability.

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[tflchef] Support Div operation (#2755)
박천교/On-Device Lab(SR)/Engineer/삼성전자 [Wed, 2 Jan 2019 00:08:17 +0000 (09:08 +0900)]
[tflchef] Support Div operation (#2755)

This commit will let tflchef cook Div operation

Signed-off-by: Cheongyo Bahk <ch.bahk@samsung.com>
5 years ago[nnc] Add more tests for acl dom to text operations (#2719)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Wed, 26 Dec 2018 20:30:54 +0000 (23:30 +0300)]
[nnc] Add more tests for acl dom to text operations (#2719)

Tested entities:
- ArtifactIndex
- ArtifactRet
- ArtifactBreak
- ArtifactCont
- ArtifactVariable
- ArtifactBlock
- ArtifactForLoop
- ArtifactIf
- ArtifactFunction
- ArtifactClassVariable
- ArtifactClassFunction
- ArtifactClass
- ArtifactModule

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
5 years ago[nnc] Fix interpreter deconv implementation (#2756)
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 26 Dec 2018 14:18:41 +0000 (17:18 +0300)]
[nnc] Fix interpreter deconv implementation (#2756)

Rotate kernel index prior to input index calculation

Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
5 years ago[nnc] Support constant in acl backend (#2723)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Mon, 24 Dec 2018 10:42:32 +0000 (13:42 +0300)]
[nnc] Support constant in acl backend (#2723)

- Support generation of constant operation in acl backend
- Add test for constant operation

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
5 years agoTensorFlowSource v1.7 package (#2715)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Mon, 24 Dec 2018 08:21:06 +0000 (17:21 +0900)]
TensorFlowSource v1.7 package (#2715)

This commit adds "version" property to TensorFlowSource CMake package
in nncc.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[ann] Implement Sub (#2714)
윤지영/On-Device Lab(SR)/Engineer/삼성전자 [Mon, 24 Dec 2018 06:03:12 +0000 (15:03 +0900)]
[ann] Implement Sub (#2714)

* [ann] Implement prepare for Sub

This patch implements a prepare for Sub operation in ann backend

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* [ann] Implement float32 operation for Sub

This commit implements a float32 operation for Sub operator

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[nnc] Caffe2 importer unittest (#2735)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 21 Dec 2018 13:07:31 +0000 (16:07 +0300)]
[nnc] Caffe2 importer unittest (#2735)

Implemented caffe2 importer unittest for unsupported op

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
5 years ago[nnc] Merge frontend libraires (#2737)
Роман Михайлович Русяев/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Fri, 21 Dec 2018 10:53:11 +0000 (13:53 +0300)]
[nnc] Merge frontend libraires (#2737)

* add one frontend library as interface
* remove redundant `target_include_directories`

Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
5 years ago[nnc] The first ONNX model resnet50 works on NNC interpreter (#2718)
Андрей Тищенко/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Fri, 21 Dec 2018 10:45:26 +0000 (13:45 +0300)]
[nnc] The first ONNX model resnet50 works on NNC interpreter (#2718)

Several operators were fixed: BatchNormalization, Reshape, Gemm and Pooling. Now NNC is available to convert the ONNX resnt50 network, play it back in interpreter and to produce the out which is totally comparable with reference data.

Signed-off-by: Andrew V. Tischenko a.tischenko@partner.samsung.com
5 years agoMake onnxproto as static library (#2738)
Роман Михайлович Русяев/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Thu, 20 Dec 2018 23:34:24 +0000 (02:34 +0300)]
Make onnxproto as static library (#2738)

* make onnxproto as static library

Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
5 years ago[nnc] Support sigmoid operation in acl backend (#2739)
Efimov Alexander/AI Tools Lab/./Samsung Electronics [Thu, 20 Dec 2018 18:31:53 +0000 (21:31 +0300)]
[nnc] Support sigmoid operation in acl backend (#2739)

- Generate code for sigmoid activation function
- Add unit tests for sigmoid, tanh and capped_relu activation functions

Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
5 years ago[nnc] Sub and Squared Diff (#2679)
Андрей Шедько/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 20 Dec 2018 17:51:03 +0000 (20:51 +0300)]
[nnc] Sub and Squared Diff (#2679)

- Refactored tflite import of various elementwise ops
- Added support for sub and SquaredDiff to C++ SB and Interpreter
- Fixed assert in c++ CPU artifact

Signed-off-by: Andrei Shedko <a.shedko@samsung.com>
5 years ago[nnc] Do not transpose weights when serializing FullyConnected operation for x86...
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 20 Dec 2018 17:36:02 +0000 (20:36 +0300)]
[nnc] Do not transpose weights when serializing FullyConnected operation for x86-spp back end (#2736)

Remove call to transposeTensor<1, 0> when serializing weights tensor for FullyConnected op for x86-cpp backend.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Fix buid target name (#2740)
Роман Михайлович Русяев/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Thu, 20 Dec 2018 16:50:27 +0000 (19:50 +0300)]
[nnc] Fix buid target name (#2740)

* correct target name in CMakeLists.txt

Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
5 years ago[nnc] Cleanup dead code in interpreter backend (#2734)
Сергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 20 Dec 2018 12:04:42 +0000 (15:04 +0300)]
[nnc] Cleanup dead code in interpreter backend (#2734)

Removed no longer used variable `_opByName` and methods working with it.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
5 years ago[nnc] Refactor ONNX importer and fix ONNX importer build bug (#2733)
Роман Михайлович Русяев/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Thu, 20 Dec 2018 11:29:07 +0000 (14:29 +0300)]
[nnc] Refactor ONNX importer and fix ONNX importer build bug (#2733)

* remove redundant classes from ONNX

Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
5 years ago[enco] IRValidator test code for conv2D (#2707)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Wed, 19 Dec 2018 23:19:15 +0000 (08:19 +0900)]
[enco] IRValidator test code for conv2D (#2707)

* [enco] IRValidator test code for conv2D

This commit adds test code to check output shape of conv2D.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* pr fix: using std::array, removed <iostream>

* pr fix: test when validate fails

* pr fix: remove iostream

5 years ago[nnc] Added Unsqueeze to ONNX (#2729)
Андрей Шедько/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 19 Dec 2018 18:32:09 +0000 (21:32 +0300)]
[nnc] Added Unsqueeze to ONNX (#2729)

Added Unsqueeze to ONNX with Reshape

Signed-off-by: Andrei Shedko <a.shedko@samsung.com>
5 years ago[nnc] Create interface for NN importers (#2728)
Роман Михайлович Русяев/AI Tools Lab /SRR/Staff Engineer/삼성전자 [Wed, 19 Dec 2018 18:20:47 +0000 (21:20 +0300)]
[nnc] Create interface for NN importers (#2728)

* added factory method to create importer objects
* added template method to manage `run` method for all importers
* ONNX importer wasn't changed

Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
5 years ago[nnc] Added Resize implementation in SB (#2398)
Андрей Шедько/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 19 Dec 2018 16:05:46 +0000 (19:05 +0300)]
[nnc] Added Resize implementation in SB (#2398)

SoftBackend implementation of Resize Nearest Neighbor
Lifted from TFLite Reference ops.
Fixed Interpreter implementation.

Signed-off-by: Andrei Shedko <a.shedko@samsung.com>
5 years ago[nnc] Fixed caffe2 maxpool border type (#2727)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 19 Dec 2018 15:30:44 +0000 (18:30 +0300)]
[nnc] Fixed caffe2 maxpool border type (#2727)

Fixed caffe2 importer maxpool border type

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
5 years ago[nnc] Fix strided slice shrink axis mask (#2725)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 19 Dec 2018 12:17:20 +0000 (15:17 +0300)]
[nnc] Fix strided slice shrink axis mask (#2725)

* Fix processing shrink axis mask on StridedSlice operation creation on TFLite importer

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
5 years ago[nnc] Support StridedSlice operation on TFLite importer (#2720)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 19 Dec 2018 10:50:13 +0000 (13:50 +0300)]
[nnc] Support StridedSlice operation on TFLite importer (#2720)

Support StridedSlice operation on TFLite importer only for strides array of ones

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
5 years ago[nnc] Fixed memory leak and heap overflow (#2703)
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 18 Dec 2018 16:23:34 +0000 (19:23 +0300)]
[nnc] Fixed memory leak and heap overflow (#2703)

* Fixed memory leak and heap overflow in softbackend elementwise op
* Collect caffe2 model problems before tensors loading

Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
5 years ago[nnc] Support Transpose operation on TFLite importer (#2716)
Павел Ильютченко/AI Tools Lab /SRR/Engineer/삼성전자 [Tue, 18 Dec 2018 13:57:06 +0000 (16:57 +0300)]
[nnc] Support Transpose operation on TFLite importer (#2716)

* Support TransposeOp on TFLite importer
* Add const where needed in TFLite op creator

Signed-off-by: Pavel Iliutchenko <p.iliutchenk@samsung.com>
5 years agoTake DIRNAME as an optional argument (#2709)
박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 [Tue, 18 Dec 2018 07:49:13 +0000 (16:49 +0900)]
Take DIRNAME as an optional argument (#2709)

This commit refines the implementation of ExternalSourceDownload; Now,
users can pass DIRNAME as an optional argument.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[enco] Add tflite frontend for Sub (#2710)
윤지영/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 18 Dec 2018 07:43:39 +0000 (16:43 +0900)]
[enco] Add tflite frontend for Sub (#2710)

This commit will add the tflite frontend of enco for Sub.

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[enco] Add ann backend for Sub (#2711)
윤지영/On-Device Lab(SR)/Engineer/삼성전자 [Tue, 18 Dec 2018 07:11:41 +0000 (16:11 +0900)]
[enco] Add ann backend for Sub (#2711)

This commit will add the ann backend of enco for Sub.

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[enco] Comparing Featureshape using operator "!=" (#2708)
윤현식/On-Device Lab(SR)/Principal Engineer/삼성전자 [Tue, 18 Dec 2018 06:07:55 +0000 (15:07 +0900)]
[enco] Comparing Featureshape using operator "!=" (#2708)

Code were modified to use newly defined operator "!=" of FeatureShape.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years ago[enco] Bugfix to throw error when file do not exist (#2104)
남궁석/On-Device Lab./Engineer/삼성전자 [Tue, 18 Dec 2018 01:35:46 +0000 (10:35 +0900)]
[enco] Bugfix to throw error when file do not exist (#2104)

Until now, there was no error even when prototxt or caffemodel do not exist
This commit will fix the bug

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
5 years ago[coco] Support Sub operator (#2698)
윤지영/On-Device Lab./Engineer/삼성전자 [Mon, 17 Dec 2018 23:59:29 +0000 (08:59 +0900)]
[coco] Support Sub operator (#2698)

This commit add Sub operator in coco

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years agoRemove deprecated nncc_foundation (#2694)
박종현/On-Device Lab./Staff Engineer/삼성전자 [Mon, 17 Dec 2018 23:58:43 +0000 (08:58 +0900)]
Remove deprecated nncc_foundation (#2694)

There is no code that uses nncc_foundation.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
5 years ago[tflchef] Add Sub for reverse (#2697)
윤지영/On-Device Lab./Engineer/삼성전자 [Mon, 17 Dec 2018 23:58:32 +0000 (08:58 +0900)]
[tflchef] Add Sub for reverse (#2697)

This will add Sub Op for tflchef-reverse

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>