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
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 13 Nov 2018 01:49:43 +0000 (10:49 +0900)]
[enco/frontend] Remove load function asserts (#2236)
This will remove model checking asserts to enable Conv2D operation import
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[nnc] Implement group in CLI (#2235)
* add group in Option class
* adapt command line parser to work with grouped options
* refactoring of CommandLine accodring to coding style
Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
[nnc] model runner (#2221)
Add final solution of model runner question
Signed-off-by: Pavel <p.fattakhov@partner.samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 10:55:50 +0000 (19:55 +0900)]
[enco/frontend] Build graph with looping operators (#2224)
* [enco/frontend] Build graph with looping operators
This will add loop of graph operators and invoke each operator building
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* apply comment: restric scope
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 10:54:21 +0000 (19:54 +0900)]
[enco/frontend] Build instruction(s) for tflite Conv2D (#2223)
* [enco/frontend] Conv2D - building objects for ifm, ofm, kernel
This code builds objects for ifm, ofm, kernel for conv2D.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* pr fix: put all conv2d code into this PR
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 10:15:51 +0000 (19:15 +0900)]
[tflchef] Add support for concatenation (#2220)
This will add concatenation operation support for tflchef
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 12 Nov 2018 10:11:55 +0000 (19:11 +0900)]
[enco.core] Remove redundant layout allocation (#2219)
This commit removes redundant feature layout allocations in enco core
implementation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 12 Nov 2018 10:08:38 +0000 (19:08 +0900)]
[coco] Introduce arity and general arg accessor (#2200)
* [coco] Introduce arity and general arg accessor
With this commit, users are able to query the number of arguments over
each coco::Op, and retrive its Nth argument without knowing its details.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix a typo
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 09:38:35 +0000 (18:38 +0900)]
[enco/frontend] Introduce TflOpCodeContext class (#2201)
* [enco/frontend] Introduce TflOpCodeContext class
This will introduce TflOpCodeContext class that holds operator codes
of the TF lite model and related methods
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* apply comment as add static
* add note for opcode_name
* move to tflimport namespace region
* add const and change comment
[nnc] Style transfer soft backend no conv transpose (#1934)
Added snippets for new ops (from TFL),
As well as Soft Backend Tests for the ops
Signed-off-by: Andrei Shedko <a.shedko@partner.samsung.com>
[nnc][utils][model_generator] Add operation tree. (#2133)
The changes add the tree of operations and builder for it.
The tree represents random model without relation
to specific format (TFLite or caffe).
The changes are needed for building random links
between operations with consistency tensor's shapes.
The tree then will be converted to specific format
(in future pull request).
Currently contains only one operation (other in future PR)
Signed-off-by: i-kulagin i.kulagin@samsung.com
Update Unit Test Report and System Test Document for October milestone (#2033)
* Add test round 2 in STD and UTR
Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 06:27:31 +0000 (15:27 +0900)]
[enco/frontend] TF lite GraphBuilderContext members (#2217)
* [enco/frontend] TF lite GraphBuilderContext members
This will add GraphBuilderContext members to import TF lite
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* apply comments
* fix format checker
* fix move
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 04:13:10 +0000 (13:13 +0900)]
[enco/frontend] Introduce Conv2DGraphBuilder (#2216)
* [enco/frontend] Introduce Conv2DGraphBuilder
This will introduce empty Conv2DGraphBuilder to handle Conv2D operation as a placeholder and register it to the Factory
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add throw
* apply comment
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 04:00:19 +0000 (13:00 +0900)]
[enco/frontend] Use pointer in GraphBuilderRegistry (#2215)
* [enco/frontend] Use pointer in GraphBuilderRegistry
This will change to return pointer of registered GraphBuilder so that
we can check BuilinOperator is registered and valid.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* ad comment and check code of validity
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 03:59:30 +0000 (12:59 +0900)]
[enco/frontend] Prepare module block (#2214)
This will prepare an empty module block
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 12 Nov 2018 02:58:17 +0000 (11:58 +0900)]
Static caffeproto library (#1220)
The current build script builds caffeproto as a shared library.
This commit revises this build script to build caffeproto as a static
library as original caffe does.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 12 Nov 2018 02:25:43 +0000 (11:25 +0900)]
[enco/frontend] Add TflBufferContext (#2192)
* [enco/frontend] Add TflBufferContext
Add TflBufferContext, which reads and provides buffer information of tflite.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* pr fix: wrong grammar, unit32_t, size->len
* prfix:renaming class, explicit constructor, etc
* make tensor_buffer() const method
[nnc] Remove `examples` directory (#2207)
* Remove `examples` directory and rename dot dumpers
Signed-off-by: Roman Rusyaev <r.rusyaev@samsung.com>
Vladimir Plazun/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 9 Nov 2018 14:12:49 +0000 (17:12 +0300)]
[nnc] Add squeeze operation support (#2138)
This commit adds squeeze operation and ShapeInference support for it
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
[nnc] added python model runner. (#2183)
added model runner for caffe, caffe2, onnx and tflite
Signed-off-by: Pavel Fattakhov <p.fattakhov@partner.samsung.com>
Ivan Vagin/AI Tools Lab /SRR/Engineer/삼성전자 [Fri, 9 Nov 2018 11:26:30 +0000 (14:26 +0300)]
[nnc] 'nnmodel' option become a vector (#2157)
Make 'nnmodel' option a vector option, because caffe2 importer consumes two files (init_net.pb and predict_net.pb)
Signed-off-by: Ivan Vagin <ivan.vagin@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 09:29:11 +0000 (18:29 +0900)]
[tflchef] Support AveragePool2D (#2175)
This patch extends tflchef for AveragePool2D operator.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 08:27:39 +0000 (17:27 +0900)]
[enco/frontend] Set module inputs and outputs (#2193)
This will set coco Module inputs and outpus from TF lite graph
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 07:45:14 +0000 (16:45 +0900)]
[enco/frontend] Modify get_padding (#2194)
Removed unnecessary assert and added comment for the origin of code.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 9 Nov 2018 07:35:08 +0000 (16:35 +0900)]
[coco] Support ReLU6 for tflite in coco (#2191)
* [coco] Support ReLU6 for tflite in coco
This commit will enable ReLU6 operation for tflite in coco
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* Add comment
* modify comment
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 07:04:12 +0000 (16:04 +0900)]
[enco/frontend] Functions to set coco module IO (#2190)
This will add two methods set_module_inputs and set_module_outputs to
set coco::Module inputs and outputs from TensorContext and TensorBags
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 06:56:31 +0000 (15:56 +0900)]
[enco/frontend] Add function to calculate padding (#2189)
Add function to calculate padding. This will be used by conv2d.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 05:40:40 +0000 (14:40 +0900)]
[enco/frontend] Added OpBuilder, InstrBuilder (#2187)
* [enco/frontend] Added OpBuilder, InstrBuilder
Added OpBuilder, InstrBuilder (copied from enco caffe frontend.)
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* Separate into a new file
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 05:36:51 +0000 (14:36 +0900)]
[enco/frontend] Introduce TensorContext and TensorBags (#2188)
* [enco/frontend] Introduce TensorContext and TensorBags
This will introduce TensorContext to extract and hold informations of
tensors such as shape and name and pre-creates coco::Bag for each tensors
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* apply comments
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 02:19:28 +0000 (11:19 +0900)]
[enco/frontend] GraphBuilder for tflite op and factory (#2171)
This commit introduces GraphBuilder, and its child classes and factory.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 9 Nov 2018 02:15:18 +0000 (11:15 +0900)]
[ANN] Introduce ReLU6 ops (#2176)
* [ANN] Introduce ReLU6 ops
This commit will introduce ReLU6 ops for ANN and execute ReLU6 in ANN
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* align column
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 9 Nov 2018 02:14:56 +0000 (11:14 +0900)]
[tflchef] Support ReLU6 operation (#2179)
* [tflchef] Support ReLU6 operation
This commit will enable ReLU6 operation in tflchef
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
* resize the channel size
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 9 Nov 2018 02:07:50 +0000 (11:07 +0900)]
[enco.caffe] Remove redundant layout allocations (#2180)
There are many redundant FeatureLayout allocations in the current caffe
frontend; frontend currently allocates a FeatureObject with deprecated
FeatureObject create method which internally allocates Generic FeatureLayout),
and then updates it with a valid FeatureLayout.
This commit aims to eliminate such redundant layout allocations.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 01:19:18 +0000 (10:19 +0900)]
[enco/frontend] Introduce as_tensor_shape (#2181)
This will introduce as_tensor_shape method to convert flatbuffers::Vector
as nncc::core::ADT::tensor::Shape that will be used for reading tensor shape
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 9 Nov 2018 01:12:52 +0000 (10:12 +0900)]
[tflchef] Bugfix of wrong variable in CMakeLists.txt (#2185)
Originally, `RECIPE_PREFIX` is used for indicating the prefix of each test
However until now, `PREFIX` is used for that
This commit will fix it as correct variable name
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 9 Nov 2018 00:55:59 +0000 (09:55 +0900)]
[enco] fix as_index_vector usage of Vector methods (#2182)
This will fix to use correct flatbuffers::Vector method and type
- Length() is deprecated, should use size()
- size return type is uint32_t not int
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
[nnc] Refactor caffe importer to support layers with multiple outputs (#2154)
- add type alias IODescriptorVector;
- make layer conversion methods accept IODescriptorVector and return IODescriptorVector;
- add support for InputLayer with several inputs and single shape;
- refactor according to coding style.
Signed-off-by: Sergei Barannikov s.barannikov@samsung.com
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 8 Nov 2018 10:18:02 +0000 (19:18 +0900)]
[enco/frontend] Introduce as_index_vector (#2177)
* [enco/frontend] Introduce as_index_vector
This will introduce as_index_vector method to convert
flatbuffers::Vector to IndexVector as
std::vector<int32_t> that will be used to for reading
index values of operators and operands.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* add a blank line
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 07:47:06 +0000 (16:47 +0900)]
[enco] Introduce enco_dump_all_ops debugging helper (#2170)
This commit introduces enco_dump_all_ops debugging helper which dumps
all the allocated Ops in a given module.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 01:19:34 +0000 (10:19 +0900)]
[enco] Introduce enco_dump_op debugging helper (#2152)
This commit introduces enco_dump_op helper function to allows users
to inspect the details of coco::Op value from a debugger such as GDB.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 00:48:32 +0000 (09:48 +0900)]
Use PRE_BUILD hook in FlatBuffers_Target (#2161)
It turns out that Ninja failed to propely manage the dependencies of
generated files of a STATIC library.
To address this Ninja build issue, this commit revises FlatBuffers_Target
to insert explicitly dependencies between target and generated files via
using PRE_BUILD hook.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Nov 2018 07:18:09 +0000 (16:18 +0900)]
[enco.caffe] Simplify code using padding helpers (#2151)
This commit simplifies ConvolutionSpec and PoolingSpec code using
build_raw_padding and build_spatial_padding helpers.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>