Vladimir Plazun/AI Tools Lab/Engineer/삼성전자 [Fri, 1 Jun 2018 12:29:53 +0000 (16:29 +0400)]
Add Softmax operation description (#294)
This class is used to represent softmax operation in computation graph
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
Vladimir Plazun/AI Tools Lab/Engineer/삼성전자 [Fri, 1 Jun 2018 12:25:23 +0000 (16:25 +0400)]
Add BiasAdd operation description class (#271)
Add BiasAdd operation description class
This class used to represent bias addition in computation graph
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
Vladimir Plazun/AI Tools Lab/Engineer/삼성전자 [Fri, 1 Jun 2018 12:23:31 +0000 (16:23 +0400)]
Add Concat operation description class (#279)
This class is used to represent concatenation operation in computation graph
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
Vitaliy Cherepanov/AI Tools Lab/Engineer/삼성전자 [Fri, 1 Jun 2018 11:29:09 +0000 (14:29 +0300)]
nnc: make isOptional method const (#293)
This commit makes getter const
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vitaliy Cherepanov/AI Tools Lab/Engineer/삼성전자 [Fri, 1 Jun 2018 10:27:21 +0000 (13:27 +0300)]
nnc: Implement AbstractModule class (#268)
nnc: implement AbstractModule class
This commit implements base module class.
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vitaliy Cherepanov/AI Tools Lab/Engineer/삼성전자 [Fri, 1 Jun 2018 10:14:22 +0000 (13:14 +0300)]
nnc: Implement PluginProxy class (#267)
nnc: implement PluginProxy class
this is base class to load pluggin
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vitaliy Cherepanov/AI Tools Lab/Engineer/삼성전자 [Fri, 1 Jun 2018 07:36:36 +0000 (10:36 +0300)]
nnc: Implement AbstractPluginInstance class (#266)
nnc: implement AbstractPluginInstance class
Virtual plugin instance class.
Provides basic API for communication between plugin and nnc
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 1 Jun 2018 06:54:25 +0000 (15:54 +0900)]
[core] Add Tensor View (#281)
This commit introduces 'nncc::core::ADT::tensor::View' class which
allows users to interpret a memory region as a tensor with a specified
shape and layout.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 23:51:59 +0000 (08:51 +0900)]
[core] Add 'num_elements' on kernel shape (#253)
This commit adds 'num_elements' for kernel shape similarly as
'num_elements' for tensor shape.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 23:46:32 +0000 (08:46 +0900)]
[core] Add 'num_elements' on feature shape (#252)
This commit adds 'num_elements' for feature shape similarly as 'num_elements'
for tensor shape.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Dmitry Mozolev/AI Tools Lab/Engineer/삼성전자 [Thu, 31 May 2018 13:03:45 +0000 (16:03 +0300)]
Add TFLite IR visitor skeleton (#274)
Add TFLite IR visitor skeleton
Adds skeleton for the TFLite IR visitor,
additionally saves pointers to some useful model contents.
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 31 May 2018 09:37:54 +0000 (18:37 +0900)]
Introduce 'nncc_include' (#263)
This commit introduces 'nncc_include' macro which allows users to write
and use useful nncc-internal CMake modules.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 23:17:48 +0000 (08:17 +0900)]
[core.ADT] Add tensor::Layout interface (#244)
This commit adds tensor::Layout interface, and tensor::LexicalLayout class
which implements Layout interfaces.
Layout interface provides 'offset' method which returns an offset of each element
in flat array, and LexicalLayout assigns this offset following lexicographical order.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Dmitry Mozolev/AI Tools Lab/Engineer/삼성전자 [Wed, 30 May 2018 13:54:11 +0000 (16:54 +0300)]
Introduce a way to support all TFLite versions in one library (#172)
* Introduce a way to support all TFLite versions in one library
It is not obvious how to support all TFLite model versions in one
library, and this commit changes the structure of the code to show
how other tflite versions can be accommodated.
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
Vladimir Plazun/AI Tools Lab/Engineer/삼성전자 [Wed, 30 May 2018 11:32:37 +0000 (15:32 +0400)]
Add TensorVariant class (#254)
Add TensorVariant class
This class is used to store and pass raw data
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 30 May 2018 08:43:05 +0000 (17:43 +0900)]
Use caffeproto instead of nncc_frontend_caffe_core (#257)
nncc_frontend_caffe_core is currently almost same as caffeproto.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 30 May 2018 07:39:22 +0000 (16:39 +0900)]
[nnkit] Introduce 'nnkit_registry_backend' (#258)
* [nnkit] Introduce 'nnkit_registry_backend'
This commit introduces 'nnkit_registry_backend' library which servers as
a global registry on various backends.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Leave a comment on thread safety
* Update comment
Dmitry Mozolev/AI Tools Lab/Engineer/삼성전자 [Tue, 29 May 2018 14:13:58 +0000 (17:13 +0300)]
Add Caffe proto reader (#255)
Add Caffe proto reader
Both reading from binary and from text files is supported.
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
Vladimir Plazun/AI Tools Lab/Engineer/삼성전자 [Tue, 29 May 2018 13:24:26 +0000 (17:24 +0400)]
Add IRNode class (#256)
Add IRNode class
This class used to represent single operation in computation graph along with its connections
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 29 May 2018 08:05:45 +0000 (17:05 +0900)]
Add 'cli' library (#249)
This commit introduces 'cli' library (under contrib/) and rewrites
caffegen, caffekit, tflitekit tools using newly introduced 'cli'
library.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Vitaliy Cherepanov/AI Tools Lab/Engineer/삼성전자 [Mon, 28 May 2018 12:30:49 +0000 (15:30 +0300)]
nnc: implement PluginSession class (#248)
nnc: implement PluginSession class
This class will be used for nnc and plugins communication
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vitaliy Cherepanov/AI Tools Lab/Engineer/삼성전자 [Mon, 28 May 2018 12:11:35 +0000 (15:11 +0300)]
nnc: implement PluginData class (#247)
nnc: implement PluginData class
This class will be used for command line arguments parsing and
and interact it with plugin params
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vladimir Plazun/AI Tools Lab/Engineer/삼성전자 [Fri, 25 May 2018 14:27:50 +0000 (18:27 +0400)]
Move ir_node.h according to changes from #158 (#260)
PR #158 renamed nnc_core into core and changed include directory structure
This commit moves ir_node.h according with these changes
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
Sergey Vostokov/AI Tools Lab/Staff Engineer/삼성전자 [Fri, 25 May 2018 09:25:19 +0000 (12:25 +0300)]
Add template of High-Level Design document (#261)
Template of High-Level Design Document v1.0
Sergey Vostokov/AI Tools Lab/Staff Engineer/삼성전자 [Fri, 25 May 2018 09:18:56 +0000 (12:18 +0300)]
SW Requirements Specification v1.0 (#70)
SW Requirements Specification v1.1
Sergey Vostokov/AI Tools Lab/Staff Engineer/삼성전자 [Fri, 25 May 2018 08:38:33 +0000 (11:38 +0300)]
SW Development Document v1.0 (#79)
* Add initial version of SW Development Document
This commit adds the initial version for SW Development Document.
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Add "support of Caffe/Caffe2" to title of SDD
This commit adds "support of Caffe/Caffe2" to the title of
the document SW Development Document
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update format of SDD to fix errors
This commit fixes format errors of SDD
* Update revision table for SDD
This commits add revision number after SE Team review
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Fix typos in SDD
This commit fixes typos (NN Model -> NN model, etc) in SDD
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Change clang to gcc/g++, and DaRT to SVACE in SDD
This commit changes tools to get SW Metrics in SDD
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update Project plan in SDD
This commit updates project plan and baseline in SDD
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Remove Reference section for SDD
This commit removes Reference section and commpetitors enumeration
from SDD. This information would be put in other document.
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Remove duplication of Reference and Competitors section
There were duplications of Reference and Competitors section
at the end of document. This commit removes them.
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 07:45:08 +0000 (16:45 +0900)]
[nncc.core] Reduce directory nesting level (#259)
This commit relocates "libs/core/src/nncc/core/ADT" into "libs/core/src/ADT"
to be consistent with nncc.foundation in terms of directory layout.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 25 May 2018 00:12:06 +0000 (09:12 +0900)]
Do not use plain signature on target_link_library (#242)
From 2.8.12, CMake disallow the mix of plain and keword
target_link_libraries signature (CMP0023).
This policy results in cmake configuration failure when BUILD_COVERAGE
is turned on.
This commit revises add_nncc_library in order to enforce the use of keyword
signature (e.g. PUBLIC) for following target_link_library calls.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Vitaliy Cherepanov/AI Tools Lab/Engineer/삼성전자 [Thu, 24 May 2018 14:10:57 +0000 (17:10 +0300)]
nnc: move plugin exceptions to plugin lib (#243)
* nnc: move plugin exceptions to plugin lib
This commit move config and plugin exceptions
to common plugin lib
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vitaliy Cherepanov/AI Tools Lab/Engineer/삼성전자 [Thu, 24 May 2018 14:09:30 +0000 (17:09 +0300)]
nnc: create AbstractSession class (#246)
nnc: create AbstractSession class
This class will be used for plugin and nnc communication
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vladimir Plazun/AI Tools Lab/Engineer/삼성전자 [Thu, 24 May 2018 14:06:16 +0000 (17:06 +0300)]
Add class "IR::model::OpDescription" (#158)
* Add class "IR::model::OpDescription"
This commits adds "IR::model::OpDescription" class which used to represent any operation in computation graph
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
* Fix minor issues
Add missing newline in CMakeLists.txt
Fix newline after contrib::core::IR::model namespace
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
* Fix issues
Remove duplicate check after assert
Add const where applicable
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
* Rename nnc_core into core
Update includes structure to evade header collisions
Update CMakeLists.txt
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
Dmitry Mozolev/AI Tools Lab/Engineer/삼성전자 [Thu, 24 May 2018 13:27:33 +0000 (16:27 +0300)]
Add TFLite v3 model console dumper (#171)
Using visitor interface to print TFLite v3 model contents.
Not all content is printed so far, but the code can easily be extended.
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
Vladimir Plazun/AI Tools Lab/Engineer/삼성전자 [Thu, 24 May 2018 13:11:36 +0000 (16:11 +0300)]
Add model IR visior (#173)
Add "IR::mode::Visitor" class. Which is used as base for IR traversal
Signed-off-by: Vladimir Plazun <v.plazun@partner.samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 08:10:08 +0000 (17:10 +0900)]
[nnkit] Introduce backend interface (#251)
This commit introduces 'nnkit::Backend' and 'nnkit::BackendFactory'
interfaces which abstracts various NN frameworks.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 24 May 2018 01:29:07 +0000 (10:29 +0900)]
[nnkit] Introduce 'CmdlineArgument' interface (#250)
This commit introduces 'nnkit::CmdlineArguments' interface which allows
each backend/action to access cmdline arguments provided by users.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 23 May 2018 23:48:58 +0000 (08:48 +0900)]
[nnkit] Introduce 'TensorContext' interface (#240)
* [nnkit] Introduce 'TensorContext' interface
This commit introduces 'nnkit::TensorContext' interface which all nnkit
actions and backends will use.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix typos
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 23 May 2018 06:46:29 +0000 (15:46 +0900)]
[nncc.foundation] Add 'Region' classes (#239)
This commit introduces Region interface which denotes a typed contigious
memory block, and adds OwnedRegion and ExternalRegion which implements
this 'Region' interface.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 23 May 2018 06:45:41 +0000 (15:45 +0900)]
Introduce nnkit_add_action and nnkit_add_backend (#238)
This commit introduces nnkit_add_action and nnkit_add_backend macros
which passes --whole-archive linker option to permit self-registration.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 23 May 2018 00:24:33 +0000 (09:24 +0900)]
Add 'nnkit' project (#236)
This commit adds 'nnkit' project which will includes various tools for
using NN frameworks in one common interface.
This commit currently introduces a dummy implementation of 'nni'.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Vitaliy Cherepanov/SRR-AI Tools Lab/./삼성전자 [Tue, 22 May 2018 23:11:12 +0000 (02:11 +0300)]
nnc: plugin common lib (Plugin type) (#233)
* nnc: plugin common lib (Plugin type)
This commit creates common plugin library.
This library will be used by plugins and nnc for communication.
Implemented:
- Plugin type. Will be used to determinate plugin type and
for debug also.
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: plugin common lib (Plugin type)
rename typeWrong to typeInvalid
using switch case
add to make file
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: plugin common lib (Plugin type)
make code readable
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* remove HLO and LLO from plugin types
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: plugin common lib (Plugin type)
fix build
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vitaliy Cherepanov/SRR-AI Tools Lab/./삼성전자 [Tue, 22 May 2018 23:02:24 +0000 (02:02 +0300)]
nnc: plugin common lib (Plugin params) (#234)
This library will be used by plugins and nnc for communication.
Implemented:
- Plugin params. Will be used to declare plugin neccessary
configuration parameters.
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vitaliy Cherepanov/SRR-AI Tools Lab/./삼성전자 [Tue, 22 May 2018 23:02:10 +0000 (02:02 +0300)]
nnc: Create plugin exception class (#232)
Created plugin exceptions class.
This class will be used by compiler components like
frontend, optimizers, backend to inform main compiler
part about internal plugin problems during compilation
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Dmitry Mozolev/SRR-AI Tools Lab/./삼성전자 [Tue, 22 May 2018 23:01:52 +0000 (02:01 +0300)]
Add TFLite model visiting mechanism (#170)
* Add TFLite model visiting mechanism
Two main things added:
- TFLite model visitor interface
- Code for iterating over the model contents (walker)
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
* Change class names
Dmitry Mozolev/SRR-AI Tools Lab/./삼성전자 [Tue, 22 May 2018 23:00:59 +0000 (02:00 +0300)]
Add TFLite v3 format parser (#169)
* Add TFLite v3 format parser
Just using flatbuffers library to get access
to the handle for .tflite version 3 model contents.
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
* Add meta info about flatbuffers schemas
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 18 May 2018 08:23:33 +0000 (17:23 +0900)]
[nncc.foundation] Add 'absolute_epsilon_equal' (#235)
This commit introduces nncc::foundation::math::absolute_epsilon_equal,
which compares two float values and returns true if their absolute diff
is less than a specified threshold expressed as a multiple of machine
epsilon.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 18 May 2018 00:09:02 +0000 (09:09 +0900)]
[core.ADT.tensor] Squeeze Tensor Shape correctly. (#226)
Squeeze operation (in TensorFlow) removess axises whose dimensionality
is 1, but the current squeeze operation eliminates if their dimensionality
is null.
This commit fixes this mismatch on the semantics of squeeze operation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 18 May 2018 00:08:54 +0000 (09:08 +0900)]
[nncc.foundation] Add 'relative_epsilon_equal' (#227)
This commit introduces nncc::foundation::math::relative_epsilon_equal,
which compares two float values and returns true if their relative diff
is less than a specified threshold expressed as a multiple of machine
epsilon.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 18 May 2018 00:08:45 +0000 (09:08 +0900)]
[core.ADT.tensor] Add 'Accessor' interface (#231)
This commit introduces 'Accessor<T>' interface over tensor values.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Vitaliy Cherepanov/SRR-AI Tools Lab/./삼성전자 [Thu, 17 May 2018 08:38:47 +0000 (11:38 +0300)]
nnc: dynamic library interface (#228)
* nnc: dynamic library interface
This commit implements interface for loading dynamic libraries
and calling its interfaces.
This functional will be used to load and communicate with plugins.
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: dynamic library interface
move sources to contrib/nnc
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: dynamic library interface
fix namespaces and code style
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: dynamic library interface
fix build
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: dynamic library interface
add info to "<<" operator
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: dynamic library interface
fix issues
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: dynamic library interface
fix issues
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 16 May 2018 23:45:55 +0000 (08:45 +0900)]
[core.ADT.tensor] Add 'num_elements' function (#217)
* [core.ADT.tensor] Add 'num_elements' function
This commit adds 'num_elemnets' function which takes a tensor shape and
returns the number of elements in a tensor of the given shape.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Return 0 when null dimension exists
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 16 May 2018 23:43:41 +0000 (08:43 +0900)]
Relocate and rename BaseException (#225)
* Relocate and rename BaseException
This commit relocates code related BaseException for consistency,
and renames it as 'Exception'.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Rewrite ConfigException in nnc
Dmitry Mozolev/SRR-AI Tools Lab/./삼성전자 [Wed, 16 May 2018 23:36:24 +0000 (02:36 +0300)]
Add flatbuffers schema compilation function (#229)
* Add flatbuffers schema compilation function
Now it is possible to compile flatbuffers schemas with a cmake function
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
* Change var names
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
Vitaliy Cherepanov/SRR-AI Tools Lab/./삼성전자 [Wed, 16 May 2018 10:35:19 +0000 (13:35 +0300)]
foundation nnc config exception (#204)
* Core: Create base exception classes
Created base exceptions classes.
This classes will be used by compiler components like
frontend, optimizers, backend to inform main compiler
part about some problems during compilation
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* core: Create base exception classes
move libs/core/.../plugin to libs/foundation/.../plugin
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception classe
split class methods realisation
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception class
fix format coding style
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception class
this commit to fix PR
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create config exception class
This class will be used to signalize about some configuration errors
like bad parametrs
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create config exception class
Fix build for gcc compiler
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create config exception class
move config exception to contrib
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create config exception class
fix build. Add linking with nncc_foundation
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: Create config exception class
change namespace to nncc::contrib::
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: Create config exception class
This commit to fix coding style
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* nnc: Create config exception class
This commit to fix coding style
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Dmitry Mozolev/SRR-AI Tools Lab/./삼성전자 [Wed, 16 May 2018 08:23:36 +0000 (11:23 +0300)]
Add NN importer interface and memory mapper (#168)
* Add NN importer interface and memory mapper
This commit adds common code needed by NN model importers which is
- abstract interface for NN model importers targeting CPU/GPU (possibly
also will be ok for DSP/NPU)
- code for memory mapped access of NN model files to avoid unnecessary
data copying (trained NN models can be large)
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
* Add NN importer interface and memory mapper
Change namespace names
Signed-off-by: Dmitry Mozolev <d.mozolev@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 15 May 2018 04:05:02 +0000 (13:05 +0900)]
Find GLog via internal script (#219)
This commit revises Caffe external module to lookup GLof using
nncc_find_package instead of find_package.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 15 May 2018 04:04:54 +0000 (13:04 +0900)]
Unify nncc_example_link_libraries and nncc_test_link_libraries (#220)
* Unify nncc_example_link_libraries and nncc_test_link_libraries
This commit introduces nncc_target_link_libraries function which unifies
nncc_example_link_libraries and nncc_test_link_libraries.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Use NAME instead of TARGET as an argument
Vitaliy Cherepanov/SRR-AI Tools Lab/./삼성전자 [Mon, 14 May 2018 23:19:59 +0000 (02:19 +0300)]
foundation: Create base exception classes (#165)
* Core: Create base exception classes
Created base exceptions classes.
This classes will be used by compiler components like
frontend, optimizers, backend to inform main compiler
part about some problems during compilation
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* core: Create base exception classes
move libs/core/.../plugin to libs/foundation/.../plugin
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception classe
split class methods realisation
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception class
fix format coding style
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception class
this commit to fix PR
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception class
this commit to fix PR
refactor BaseException class
fix build
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception class
this commit to fix PR
fix include
add gtest
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* foundation: Create base exception class
fix coding style
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
Vitaliy Cherepanov/SRR-AI Tools Lab/./삼성전자 [Mon, 14 May 2018 23:19:37 +0000 (02:19 +0300)]
nnc: initial commit (#161)
* tools nncc: compiler initial commit
Create makefiles and main for compiler
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* tools nncc: compiler initial commit
Move tools/nncc to contrib/tools/
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* tools nncc: compiler initial commit
code clean remove unused code
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* tools nncc: compiler initial commit
Move contrib/tools/nncc to contrib/nnc
rename cl to nnc
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* tools nnc: compiler initial commit
private nncc_core library target link
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 14 May 2018 03:17:54 +0000 (12:17 +0900)]
Allow FlatBuffers source download by default (#222)
This commit allows users to download (and build) FlatBuffers by default.
This commit also revises docker build script to pass FLATBUFFERS_URL
(which is necessary to allow CI to download and build FlatBuffers).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 11 May 2018 05:48:02 +0000 (14:48 +0900)]
Find GFlags via internal script when building Caffe (#218)
This commit revises Caffe external module to lookup GFlags using
nncc_find_package instead of find_package.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 10 May 2018 23:57:28 +0000 (08:57 +0900)]
Add glog target cmake configure file (#216)
* Add glog target cmake configure file
This will add glog configure file that adds glog target.
Unlike gflags, latest glog source archieve has issue(namespace difference) with latest gflags so cannot use built from source glog at the moment.
So this commit only includes adding target interface with system installed version.
Download and build from source may be added later when isses are fixed somehow.
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* move status message
* remove empty line
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 10 May 2018 23:57:14 +0000 (08:57 +0900)]
Build shared GFlags library (#215)
The default GFlag build script dose not specify -fPIC option when
building static gflags library, and thus it is impossible to use built
library when building other shared libraries.
This commit addresses this issue by building shared library instead of
static library.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 10 May 2018 01:37:45 +0000 (10:37 +0900)]
Add ExternalProjectTools (#213)
This commit introduces ExternalProjectTools module which allows users to
import external CMake projects in a systematic way.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 9 May 2018 23:24:41 +0000 (08:24 +0900)]
Add gflags download and build (#210)
* Add gflags download and build
This will add download and build gflags within cmake
- default action is off
- system installed version can be used when download is off
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* apply comments
* move compile line
* use interface and move build options settings
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 9 May 2018 05:40:36 +0000 (14:40 +0900)]
[core] Add 'fill' method to ADT::tensor::Index (#198)
This commit adds 'fill' method (to ADT::tensor::Index class) which sets
all the indices as the given value.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 9 May 2018 01:47:44 +0000 (10:47 +0900)]
[core.ADT.tensor] Introduce 'squeeze' operation (#207)
* [core.ADT.tensor] Introduce 'squeeze' operation
This commit introduces 'squeeze' operation on tensor shape which eliminates
axies with null dimensionality.
This commit also introduces several related unittests which show how to
use this operation and describes the expected operation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Return reference correctly
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 9 May 2018 01:34:23 +0000 (10:34 +0900)]
Update .gitignore for vscode (#208)
This will add .vscode to .gitignore for the users
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 8 May 2018 03:47:24 +0000 (12:47 +0900)]
[caffekit] Run inference without caffemodel (#206)
This commit revises 'caffekit run' to performe inference with random weight
even when caffemodel is not provided.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 8 May 2018 01:13:06 +0000 (10:13 +0900)]
Introduce 'caffekit' (#154)
This commit introduces 'caffekit' which will include various tools for
supporting caffe. Currently, 'caffekit' supports only 'run' command which
loads .prototxt and .caffemodel and runs one inference.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Tue, 8 May 2018 01:09:13 +0000 (10:09 +0900)]
[core.ADT.tensor] Add 'range' function (#205)
This commit adds 'range' function which creates a 'IndexRange'
object from a 'Shape' object.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 4 May 2018 08:37:44 +0000 (17:37 +0900)]
[core.ADT.tensor] Add 'TextFormatted<Index>' class (#202)
This commit adds 'TextFormatted<Index' class which is useful for
logging.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 4 May 2018 06:30:11 +0000 (15:30 +0900)]
[core] Introduce 'Printable' interface (#199)
This commit introduces 'Printable' interface for printable objects. This
commit also introduces related tests.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 4 May 2018 06:00:17 +0000 (15:00 +0900)]
Add 'Caffe' as an external module (#195)
This commit adds 'Caffe' external module which builds libcaffe.so from
Caffe source (with CPU_ONLY flag).
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
Sergey Vostokov/SRR-AI Tools Lab/./삼성전자 [Fri, 4 May 2018 06:00:02 +0000 (09:00 +0300)]
SW System Test Document v1.0 (#77)
* Add initital version of Test Plan Document
This commit adds the initital version for
SW Test Plan document
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Add section SW System Test Items
This commit adds the list of functions to be tested and not
to be tested
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Fix mistakes
This commit fixes some mistakes in text
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Add software items to table 4-3
Add CI and VCS systems to table 4-3. Software
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Add risk management plan
This commit adds the risk management plan to the section 4.3
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update risk management table
The risk "SmartMachine OS targets are not available" was added
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update formulation of the Scope section
Some changes to reflect the exact scope.
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Change RST format to MD
This commit adds the same content of Test Plan, but in MD format
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update SW Test document by comments from SRR SE Team
This commit add more details in Scope, updates test items,
and test tools
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Fix format errors
Fix format errors
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Remove test item 1 and test item 2. Update numbering
This commit removes test items1/2 as they are considered as a
part of other tests
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update test tescription for test item 2/3
This commit updates the test items description for the
test item 2 and test item 3
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update SW Test Document to follow SW Requirements Specification
This commit updates test Item to follow the SW Requirements Specification
content
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Add separated test items for testing of import Caffe/Caffe2
This commit adds new test items for each reqirements:
- test import of Caffe NN model format
- test import of Caffe2 NN model format
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update reuirements mapping for test items
This commit fixes wrong requirements mapping for test items
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Fix wrong numbering for test items
This commit fixes wrong numbering for test item and
for manual testing of functional requirement
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Remove RF-9::LLO from STD and fix typos
This commit removes test item for RF-9:LLO as it is not
presented in SRS
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
* Update revision of STD to 1.0
This commit updates revision of SW Test Document to Rev1.0
Signed-off-by: Sergey Vostokov <s.vostokov@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 4 May 2018 01:15:27 +0000 (10:15 +0900)]
[nncc.core] Simplify tensor tests with constructor (#194)
This commit simplifies tensor tests with recently introduce constructors
based on brace initialization.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 4 May 2018 01:14:35 +0000 (10:14 +0900)]
Add 'CaffeProto' as an external module (#193)
This commit adds 'CaffeProto' external module which provides
'libcaffeproto' library. This library allows us to parse .prototxt
and .caffemodel files.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Fri, 4 May 2018 01:13:47 +0000 (10:13 +0900)]
Add 'tflitekit' (#192)
This commit adds 'tflitekit' which provides various command
related with TensorFlow Lite.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 3 May 2018 05:34:03 +0000 (14:34 +0900)]
Add 'TensorFlowLite' as an external module (#188)
This commit adds 'TensorFlowLite' external module which builds a
'libtensorflowlite.a' from TensorFlow Lite source.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 11:00:15 +0000 (20:00 +0900)]
[nncc.core] Initialize tensor::Index via ctor (#191)
This commit introduces a constructor for tensor::Index which takes an
initializer list as its argument.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 10:59:59 +0000 (19:59 +0900)]
Add 'CaffeSource' an an external module (#190)
This commit adds 'CaffeSource' external module which downloads Caffe
source from the URL specified by CAFFE_URL environment variable.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 10:50:38 +0000 (19:50 +0900)]
[nncc.core] Add 'Iterable' class (#189)
This commit adds 'Iterable' class which faciliates the use of
'iterate' method based on lambda.
This commit also revises 'tensor::IndexRange' class using newly
introduced 'Iterable' class.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 01:21:08 +0000 (10:21 +0900)]
Add 'FlatBuffer' as an external module (#186)
This commit adds 'FlatBuffer' external module which compiles
libflatbuffers.a library and flatc executable from the flatbuffers
source that 'FlatBufferSource' provides.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 01:15:32 +0000 (10:15 +0900)]
[nncc.core] Set tensor::Shape values via constructor (#181)
This commit introduces a constructor for tensor::Shape which takes an
initializer list as its argument.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 01:11:36 +0000 (10:11 +0900)]
Add 'NEON2SSE' as an external module (#185)
This commit adds 'NEON2SSE' library module (which provide a header-only
neon2sse library target using NEON2SSESource) which is necessary to
build tensorflow lite.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 01:11:26 +0000 (10:11 +0900)]
Add 'GEMMLowp' as an external module (#184)
This commit adds 'GEMMLowp' library module (which provide a header-only
gemmlowp libary target using GEMMLowpSource) which is necessary to build
tensorflow lite.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 01:11:16 +0000 (10:11 +0900)]
Add 'Farmhash' as an external module (#183)
This commit adds 'Farmhash' as an external module which provides
'farmhash' library target.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Wed, 2 May 2018 01:11:08 +0000 (10:11 +0900)]
Add 'Eigen' as an external module (#182)
This commit adds 'Eigen' module which provides 'eigen' interface library
if it is successfully loaded.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 30 Apr 2018 08:35:25 +0000 (17:35 +0900)]
[nncc.core] Add 'tensor::IndexRange' (#180)
This commit adds 'tensor::IndexRange' class which helps users to iterage
over all the index valid for a certain tensor shape.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 30 Apr 2018 08:34:50 +0000 (17:34 +0900)]
Add 'NEON2SSESource' as an external module (#179)
This commit adds 'NEON2SSESource' (which is necessary to build
tensorflow lite) as an external module that nncc_find_package can load.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 30 Apr 2018 08:08:41 +0000 (17:08 +0900)]
Add 'GEMMLowpSource' as an external module (#178)
This commit adds 'GEMMLowpSource' (which is necessary to build
tensorflow lite) as an external module that nncc_find_package can load.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 30 Apr 2018 07:44:24 +0000 (16:44 +0900)]
Add 'FarmhashSource' as an external module (#177)
This commit adds 'FarmhashSource' (which is necessary to build
tensorflow lite) as an external module that nncc_find_package can load.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Mon, 30 Apr 2018 05:14:10 +0000 (14:14 +0900)]
Add 'EigenSource' as an external module (#176)
This commit adds 'EigenSource' (which is necessary to build tensorflow
lite) as an external module that nncc_find_package can load.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Sun, 29 Apr 2018 23:36:53 +0000 (08:36 +0900)]
Add 'FlatBuffersSource' as an external module (#156)
This commit adds 'FlatBuffersSources' as an external module used by
nncc_find_package.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 26 Apr 2018 06:45:26 +0000 (15:45 +0900)]
Add 'TensorFlowSource' as an external module (#155)
This commit adds 'TensorFlowSource' as an external module. Any
components in nncc are now able to download TensorFlowSource (if
DOWNLOAD_TENSORFLOW is set as true) and access it through
nncc_find_package macro.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 26 Apr 2018 05:00:37 +0000 (14:00 +0900)]
[nncc.core] Equality over tensor shape (#153)
This commit introduces == operator between two tensor::Shape class.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 26 Apr 2018 04:25:24 +0000 (13:25 +0900)]
Generage coverage report only for libs and tools (#152)
This commit revises 'gen-coverage-report' to consider sources under libs
and tools (which nncc officially provides) when generating coverage
report.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 26 Apr 2018 03:48:29 +0000 (12:48 +0900)]
Add Protobuf as an external module (#151)
This commit adds Protobuf as an external module that can be checked and
imported via nncc_find_package macro.
This commit also simplifies build scripts using this external module.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 26 Apr 2018 01:56:30 +0000 (10:56 +0900)]
Simplify C++ standard configuration (#150)
Now, CMake 3.1 is the minimum requirement for nncc, and thus workaround for
legacy CMake (based on CMAKE_CXX_FLAGS) is no longer required.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 26 Apr 2018 01:56:19 +0000 (10:56 +0900)]
Define 'nncc_find_package' as macro (#149)
In CMake, function creates a new scope, and thus it interfers the
behavior of 'find_package' command if its wrapper ('nncc_find_package')
is implemented as a function.
This commit rewrites 'nncc_find_package' as a macro (which does not
create a new scope) to avoid scope issue, and updates existing
configurations accordingly.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 [Thu, 26 Apr 2018 00:41:48 +0000 (09:41 +0900)]
[caffegen] Add 'decode' command (#148)
This commit supports 'decode' command in caffegen tool which takes
binary caffemodel via standard input, and shows its content in text
format via standard output.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>