윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 26 Nov 2018 01:36:15 +0000 (10:36 +0900)]
[encodump] Added ReLU6 (#2395)
Withi this commit, encodump prints information about Relu6.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 23 Nov 2018 18:36:58 +0000 (21:36 +0300)]
[nnc] Implement elementwise div operation (#2363)
Added support of div elementwise:
- in tflite importer
- in interpreter
- in soft backend using Eigen
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 23 Nov 2018 17:53:52 +0000 (20:53 +0300)]
[nnc] Add support for freestanding activation functions in tflite importer (#2385)
While tflite have fused activation functions, some networks use activation functions as separate operations
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 23 Nov 2018 08:01:07 +0000 (17:01 +0900)]
[tflchef/reverse] Enable INT32 type (#2393)
This will enable tflchef-reverse to handle INT32 type
- Needed to handle Reshape operator from MobileNet
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 23 Nov 2018 04:07:20 +0000 (13:07 +0900)]
[tflchef] Update depthwiseconv2d recipe (use relu6 activation) (#2322)
depthwiseconv2d recipe will use relu6 activation.
- Mobilenet uses relu6 activation.
- It could be used as a test for relu6 activation.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 23 Nov 2018 04:06:01 +0000 (13:06 +0900)]
[tflchef] Support int32 tensortype (#2388)
This will fix to support int32 tensortype with introducing as_tflite_tensortype()
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 23 Nov 2018 01:37:19 +0000 (10:37 +0900)]
[tflchef] enable ReLU6 conversion (#2381)
This will enable ReLU6 in as_tflchef_activation()
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 23 Nov 2018 01:36:42 +0000 (10:36 +0900)]
[enco/frontend] Empty DepthwiseConv2D (#2387)
This will add placeholder for DepthwiseConv2D in frontend
- to check loading mobilenet slim model
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 23 Nov 2018 01:04:38 +0000 (10:04 +0900)]
[enco/tfl/frontend] ReLU6 Activation Layer (#2359)
* [enco/tfl/frontend] ReLU6 Activation Layer
This commit is for ReLU6 Activation Layer.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* Pr fix: add code to op/Activation.cpp
[nnc] Support Pad operation on TFLite Importer and Interpreter (#2330)
* Support Pad op in TFLite imported and interpreter
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@partner.samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 08:20:04 +0000 (17:20 +0900)]
[tflchef] Add DepthwiseConv2D for reverse (#2373)
This will add DepthwiseConv2D Op for tflchef-reverse
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 07:59:01 +0000 (16:59 +0900)]
[tflchef] Add Conv2D for reverse (#2375)
* [tflchef] Add Conv2D for reverse
This will add Conv2D Op for tflchef-reverse
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add comment
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 07:48:01 +0000 (16:48 +0900)]
[tflchef] Add MaxPool2D for reverse (#2376)
This will add MaxPool2D Op for tflchef-reverse
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 07:46:43 +0000 (16:46 +0900)]
[tflchef] Add ReLU6 for reverse (#2374)
This will add ReLU6 Op for tflchef-reverse
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 05:58:55 +0000 (14:58 +0900)]
[tflchef] Add ReLU for reverse (#2377)
This will add ReLU Op for tflchef-reverse
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 05:19:21 +0000 (14:19 +0900)]
[tflchef] Add Concat for reverse (#2370)
This will add Concatenation Op for tflchef-reverse
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 05:12:23 +0000 (14:12 +0900)]
[tflchef] Add Reshape for reverse (#2371)
This will add Reshape Op for tflchef-reverse
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 05:08:03 +0000 (14:08 +0900)]
[enco] Splitting Frontend.cpp into Op/*.cpp and more (#2362)
* [enco] Splitting Frontend.cpp into Op/*.cpp and more
Through this commit, Frontend.cpp will be refactored into several files.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* pr fix: remove useless "tflite::"
* pr fix: Split h file into h and cpp file
* pr fix: remove wrong test files
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 01:33:51 +0000 (10:33 +0900)]
[tflchef] Fix FlatBufferIntArrayToVector (#2369)
* [tflchef] Fix FlatBufferIntArrayToVector
This will rename FlatBufferIntArrayToVector to as_index_vector like enco/frontend and correct type of caller
- incorrect type may cause a problem in reading minus values in shape info
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* fix to typename
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 22 Nov 2018 01:33:22 +0000 (10:33 +0900)]
[tflchef] Prepare adding Ops with AveragePool2D (#2368)
This will add AveragePool2D operator handler and needed changes to test.
Also place holders for other operators to prevent merge conflict.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 22:18:40 +0000 (07:18 +0900)]
[tflchef] generate_recipe for each operators (#2361)
This will fill handlers for each operators
- forward filler settings for the operator
- tflchef operator build and I/O settings for corresponding tflite operator
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[nnc] Fix deconv unittest build (#2366)
Fix deconv unit test build and adjust float epsilon
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
[nnc][utils][model_generator] Add converter from tree to tflite. (#2230)
Implemented converter from randomly generated Tree representation to TFLite model.
Signed-off-by: i-kulagin i.kulagin@samsung.com
[nnc] Initial support of various operations in ONNX frontend (#2286)
Operations supported in ONNX importer:
- Conv2d
- BatchNorm
- Pool
- scale
- dropout
- Elementwise operations (add, sum, mul, max)
- Gemm
Signed-off-by: Andrew V. Tischenko <a.tischenko@partner.samsung.com>
[nnc] Conv transpose in SoftBackend (#2290)
Implements Deconvolution in Soft Backend, caffe style transfer model is fully supported.
Signed-off-by: Andrei Shedko a.shedko@partner.samsung.com
[nnc] Add `shape` parameter to constructors of operations that cannot infer shapes of their outputs (#2338)
* Add `shape` parameter to constructor of `VariableOp`;
* Add `shape` parameter to constructor of `ReshapeOp`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 10:31:57 +0000 (19:31 +0900)]
[tflchef] Implement generate_recipe (#2360)
* [tflchef] Implement generate_recipe
This implements partial of generate_recipe() for operators, operands and inputs,outputs.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove unused
* reorder a line
* fix typo
* need check quantization
* fix typo
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 10:25:15 +0000 (19:25 +0900)]
[tflchef] Introduce TFliteOpChef and Registry (#2357)
This will introduce TFliteOpChef base class for Operator handlers for translation and
TFliteOpRegistry for registeration of handlers.
All headers are included in RecipeChef to check compilation and as it will be used later codes.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 09:51:18 +0000 (18:51 +0900)]
[tflchef] Adds "comment" into recipe (#2356)
Now, recipe file can have "comment" field, which is ignored by tflchef.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 08:15:16 +0000 (17:15 +0900)]
[tflchef] Introduce TFliteImport (#2355)
* [tflchef] Introduce TFliteImport
This will introduce TFliteImport class that provides needed information from tflite::Model to build recipe
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add brief
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 05:11:59 +0000 (14:11 +0900)]
[enco/tfl/frontend] Modified wrong test number (#2354)
Conv_003 exists without Conv_002. So Conv_003 is renamed to Conv_002.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 05:11:09 +0000 (14:11 +0900)]
[tflchef] Introduce convert helpers (#2351)
This will introduce helper functions to convert tflite types to tflchef types
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 05:10:39 +0000 (14:10 +0900)]
[tflchef] Store ModelRecipe to file (#2352)
This will implement storing ModelRecipe to a file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 05:10:19 +0000 (14:10 +0900)]
[enco/tfl/frontend] Bug fix on padding (#2353)
IFM is NHWC format but the padding code was written assuming that IFM is NCHW.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 04:44:45 +0000 (13:44 +0900)]
[enco/tfl/frontend] Refactoring RELU activation (#2313)
* [enco/tfl/frontend] Refactoring RELU activation
RELU activation is commonly used by many operations. So this activation is extracted as a separate method.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* returning ifm
* ofm as param
* remove empty line
* pr fix: remove output param
* pr fix : comment, renaming vars, etc.
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 02:51:21 +0000 (11:51 +0900)]
[tflchef] Call tflchef from Driver (#2350)
This will make Driver call tflchef tflite load and save functions
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 02:18:49 +0000 (11:18 +0900)]
[tflchef] RawModel loader (#2347)
This will introduce TFlite raw model loader
- copied from enco/frontend
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 02:18:20 +0000 (11:18 +0900)]
[tflchef] Introduce entry points for tflchef-reverse (#2345)
* [tflchef] Introduce entry points for tflchef-reverse
This will introduce two empty functions for tflchef-reverse tool
- CMakeLists.txt file to build a library
- This library will read TF lite file and drop tflchef recipe file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* change header ifdef name
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 21 Nov 2018 01:19:12 +0000 (10:19 +0900)]
[tflchef] Introduce reverse tool driver (#2346)
[tflchef] Introduce reverse tool driver
[nnc] fix static analysis warning and add missed break (#2287)
- Add assert, which protects us from passing a null pointer to a function.
- Add break statement into switch in tflite_importer.
Signed-off-by: Pavel <p.fattakhov@partner.samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 20 Nov 2018 09:52:43 +0000 (18:52 +0900)]
[tflchef] Add Conv2D test recipe (#2340)
This will add Conv2D test recipe for tflchef.
- there was existing readme to show readme example works but there was no conv2d test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[nnc] Make constructors of `Operations` accept other `Operation`s as arguments (#2292)
* Make constructors of `Operations` accept `Operation`s they depend on.
* Remove `connectInput` method, which became redundant.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
[nnc] split model runner script into 4 scripts (#2285)
split model runner script into 4 scripts
Signed-off-by: Pavel <p.fattakhov@partner.samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 19 Nov 2018 08:17:54 +0000 (17:17 +0900)]
[enco] Fix typo (#2334)
This will fix typo in OwnedFileDescriptor comment
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 16 Nov 2018 02:06:49 +0000 (11:06 +0900)]
[tflchef] Add ReLU6 in activation (#2312)
This commit will add ReLU6 in activation
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 15 Nov 2018 23:09:30 +0000 (08:09 +0900)]
[enco] Remove unused variable (#2311)
This commit will remove unused varuable
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 15 Nov 2018 23:08:48 +0000 (08:08 +0900)]
[nnkit] Link backend_support library with dl (#2310)
Backend support library uses dlopen internally, but is not linked with
dl currently.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 15 Nov 2018 23:07:52 +0000 (08:07 +0900)]
[enco] Set subnet output correctly on branching (#2309)
The current implementation specifies a bag as a subnet output if the subnet
accesses it and this bag is accessed outside of this subnet.
It turns out that this algorithm may specify a network input as a subnet output
as it does not consider this bag is updated by this subnet.
This commit fixes this bug and adds a related test.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 15 Nov 2018 23:07:05 +0000 (08:07 +0900)]
[tflchef] Use safemain (#2305)
Now, tflchef and tflchef-file uses the main function that safemain
provides.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Thu, 15 Nov 2018 16:16:31 +0000 (19:16 +0300)]
[nnc] Implemented caffe2 importer interface (#2233)
* Implemented caffe2 importer interface
* Minor fixes in driver sanity checks
* Inited caffe2 model dumper
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
[nnc] Remove redundant code (#2314)
Remove redundant code from c++ snippet that prevents artifact build
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
[nnc] Replace layout of operations in cpu backend (#2258)
Order of operations in artifact is changed to RPO to optimize usage of memory caches
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
[nnc] Tfl importer eltwise (#2208)
Added elementwise operations, Tanh and Transposed Conv to tfLite importer
Signed-off-by: Andrei Shedko <a.shedko@partner.samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 15 Nov 2018 06:35:02 +0000 (15:35 +0900)]
[coco] Deprecate FeatureObject create with Shape (#2302)
This commit removes create method that takes a FeatureShape from
ObjectManager class and revises related tests.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 15 Nov 2018 06:33:14 +0000 (15:33 +0900)]
[enco/frontend] Relu activation layer for Conv2D (#2306)
* [enco/frontend] Relu activation layer for Conv2D
This commit adds Relu activation layer for Conv2D and test.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* Check NONE for actuvation
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 15 Nov 2018 04:01:34 +0000 (13:01 +0900)]
[enco] Introduce enco_dump_all_objects (#2304)
With this debugging helper, users easily enumerates all the objects in a
module with interactive debugger.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 15 Nov 2018 03:59:54 +0000 (12:59 +0900)]
[enco.tflite] Remove deprecated create method use (#2303)
FeatureObject create method (with a FeatureShape) in ObjectManager is
deprecated.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 15 Nov 2018 02:35:31 +0000 (11:35 +0900)]
[enco] Fix typos in some comments (#2301)
There are same typos in some comments
This commit will fix it
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 15 Nov 2018 02:25:53 +0000 (11:25 +0900)]
Introduce 'safemain' library (#2300)
This commit introduces 'safemain' library which provides 'main' function
that captures std::exception on RELEASE build.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 15 Nov 2018 02:23:23 +0000 (11:23 +0900)]
[enco] Modify some misunderstandable parameters name (#2297)
Some parameters are started with underbar, which can be misunderstood as private member variable
This commit will fix them not to be misunderstood
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 15 Nov 2018 02:03:40 +0000 (11:03 +0900)]
[enco] Extend frontend for ReLU (#2298)
This commit will extend the frontend of enco for ReLU
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 15 Nov 2018 01:50:32 +0000 (10:50 +0900)]
[enco] Introduce enco_dump_all_bags (#2293)
This commit introduces enco_dump_all_bags which shows the details of all
the allocated bags in a given module.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 15 Nov 2018 01:48:47 +0000 (10:48 +0900)]
[enco/frontend] Support Reshape of TF lite (#2294)
* [enco/frontend] Support Reshape of TF lite
This will add Reshape operator for TF lite import
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* use ifm_bag->size()
* change test out shape
* fix shape again
* fix typo
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 15 Nov 2018 00:29:02 +0000 (09:29 +0900)]
[enco] Extend frontend for ReLU6 (#2275)
* [enco] Extend frontend for ReLU6
This commit will extend the frontend of enco for ReLU6
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* modify variable name
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 23:51:53 +0000 (08:51 +0900)]
[enco/frontend] test case for MaxPool2D tflite frontend (#2272)
This commit adds a test case for MaxPool2D tflite frontend
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 23:51:27 +0000 (08:51 +0900)]
[enco/frontend] fix bug about padding calculation (#2280)
* [enco/frontend] fix bug about padding calculation
Wrong layout (NCHW) of kernel caused this bug. Fixed to NHWC.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* more complex test (no identical number in ifm shape)
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 14 Nov 2018 23:51:13 +0000 (08:51 +0900)]
[enco] Show Conv2D op details (#2281)
With this commit, enco_dump_all_ops and enco_dump_op methods show the
additional information if a given op is a Conv2D op.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 14 Nov 2018 23:50:53 +0000 (08:50 +0900)]
[tflchef] Support ReLU in tflchef (#2283)
This commit will enable ReLU in tflchef
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
[nnc] Replace ASSERT_NEAR with custom comparator (#2231)
Replace ASSERT_NEAR in soft backend unit tests with custom ULP comparator to add flexibility
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
added assert for result of ftell function (#2278)
added assert for result of ftell function in interpreter.
Signed-off-by: Pavel <p.fattakhov@partner.samsung.com>
[nnc] Make the class `Graph` intrusive (#2261)
* Remove `INode`, `AbstractNode`, `Node`, `OpDescription` classes.
* Add `Operation` class, derive all `Op`s from it.
* Modify `Graph` to work with `Operation`s instead of `Node`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 10:45:47 +0000 (19:45 +0900)]
[enco/frontend] MaxPool2D for tflite frontend (#2270)
* [enco/frontend] MaxPool2D for tflite frontend
This commit adds MaxPool2D for tflite frontend.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* 'auto' to explicit type
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 10:12:42 +0000 (19:12 +0900)]
[tflchef] Support DepthwiseConv2D (#2277)
This patch extends tflchef for DepthwiseConv2D operator.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 14 Nov 2018 08:19:29 +0000 (17:19 +0900)]
[enco] Bugfix about ReLU6 for backend (#2273)
There are some typos for ReLU6 operation
This commit will fix them
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 08:11:02 +0000 (17:11 +0900)]
[tflchef] Support Reshape (#2268)
This will extend to support Reshape operator
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 04:35:50 +0000 (13:35 +0900)]
[enco/frontend] Added test cases for AvgPool2D (#2244)
* [enco/frontend] added a test case for AvgPool2D
Two test cases for AvgPool2D are added. (paddiang for SAME and VALID)
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* avgpool2d -> averagepool2d
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 14 Nov 2018 03:58:12 +0000 (12:58 +0900)]
[enco] Rename caffe tests (#2267)
This commit appends layer prefix (such as Convolution) to each caffe tests and
assign new numbers in order to make it easy to find.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 14 Nov 2018 03:53:07 +0000 (12:53 +0900)]
[enco] Extend backend for ReLU6 (#2265)
This commit will extend the backend of enco for ReLU6
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 03:52:31 +0000 (12:52 +0900)]
[enco/frontend] Test for TF lite concat (#2264)
This will add test recipe for Concat operator
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 01:54:17 +0000 (10:54 +0900)]
[enco/frontend] Introduce ConcatenationGraphBuilder (#2262)
* [enco/frontend] Introduce ConcatenationGraphBuilder
This will introduce ConcatenationGraphBuilder for importing Concat operator from TF lite
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove unused
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 14 Nov 2018 01:11:38 +0000 (10:11 +0900)]
[enco/frontend] Revise Conv2D build using copy (#2255)
* [enco/frontend] Revise Conv2D build using copy
This will revise Conv2D to use InstrBuilder::copy method so that cascading new coco IR operator would be easy
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* renamve var
* fix comment
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 14 Nov 2018 01:09:58 +0000 (10:09 +0900)]
[enco] Remove caffe build tests (#2263)
Build test was introduced to check whether the source code that enco emits
is valid in terms of its syntax at the early stage, but this test is no longer
meaningful.
This commit removes caffe build tests and related infrastructure to
simplify build process.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
[nnc] Support PAD operation on modelIR (#2232)
* Create new class for PAD operation and visitors
* Support pad operation in shape Inference
* fix ElementwiseOp dump in irDotDumper
Signed-off-by: Pavel Iliutchenko <p.iliutchenk@partner.samsung.com>
[nnc] Problems fixed during the debug of the Convolution and the Softmax operations (#2142)
- Tensor and tensor shapes transposed in certain places.
- Serialization operation changed to save tensors starting from lower to higher dimensions (to be easily readable by the standard ACL routine).
Signed-off-by: Timur Ablyazimov <t.ablyazimov@samsung.com>
First implementation of some Onnx operators. (#2140)
The following operators were implemented (without any debugging):
Dropuot, Concat, Scale, Reshape, Rel, Softmax.
Signed-off-by: Andrew V. Tischenko a.tischenko@partner.samsung.com
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 13 Nov 2018 10:43:38 +0000 (19:43 +0900)]
[enco] Introduce enco_dump_all_instrs (#2252)
This commit implements enco_dump_all_instrs debugging helper.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 10:43:11 +0000 (19:43 +0900)]
[enco/frontend] Add AvgPool2DGraphBuilder into registry (#2253)
With this commit, AvgPool2DGraphBuilder is added into registry.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 10:14:37 +0000 (19:14 +0900)]
[enco/frontend] Add AvgPool2DGraphBuilder for tflite frontend (#2249)
* [enco/frontend] Add AvgPool2DGraphBuilder for tflite frontend
AvgPool2DGraphBuilder was added for tflite frontend.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* Divisor , assert for fused activation
* tensorflow -> tensorflow lite
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 10:14:04 +0000 (19:14 +0900)]
[enco/frontend] Introduce copy to InstrBuilder (#2251)
* [enco/frontend] Introduce copy to InstrBuilder
This will add copy method to InstrBuilder to make a copy instruction
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add comment
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 10:11:50 +0000 (19:11 +0900)]
[tflchef] Support MaxPool2D (#2248)
This patch extends tflchef for MaxPool2D operator.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 13 Nov 2018 09:40:09 +0000 (18:40 +0900)]
[enco] Common nullptr handler in debuging API (#2247)
With this commit, every debugging API shares the same nullptr handler
(which is generated via macro).
This change makes it easy to extend debugging API.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 13 Nov 2018 08:06:00 +0000 (17:06 +0900)]
[enco] Do NOT eliminate output objects (#2246)
The current implementation of identical object reducation pass
may eliminate output objects (i.e. objects over output bags), which
results in incorrect results.
With this commit, identical object reducation pass no longer eliminates
output objects.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 06:08:44 +0000 (15:08 +0900)]
[enco/frontend] Add padding functions for conv and avgpool (#2243)
Add two more padding functions: One is for conv2d, another for avgpool.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 05:16:31 +0000 (14:16 +0900)]
[enco] remove underscore in build method argument (#2242)
This will remove underscore used in build method argument
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 05:08:16 +0000 (14:08 +0900)]
[tflchef] Remove unnecessary bias input operand from avgpool2d (#2241)
`bias` operand is not used in averagepool2d.
The operand is removed from recipe.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 04:44:22 +0000 (13:44 +0900)]
[enco/frontend] Enable Conv2D test (#2240)
This will add INFERENCE file to enable TF lite Conv2D operator load test
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 04:12:18 +0000 (13:12 +0900)]
[enco/frontend] Add convolution recipe file Conv2D_000 (#2167)
This will add tflchef recipe file that has one convolution operator
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 02:14:42 +0000 (11:14 +0900)]
[enco/frontend] Fix shape input for object layout (#2237)
This will fix shape input for object layout with correct value
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 13 Nov 2018 01:53:35 +0000 (10:53 +0900)]
[enco] Add enco_dump_op_tree debugging helper (#2227)
This commit implements enco_dump_op_tree debugging helper which dumps
all the descendents of a given op as a tree.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 01:53:15 +0000 (10:53 +0900)]
[enco/frontend] revise opcode_name method (#2228)
* [enco/frontend] revise opcode_name method
This will revisit opcode_name method with opcode index value to invalid opcode name
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* return non const