platform/core/ml/nnfw.git
5 years agoIntroduce NEG operation on NeuralNetworks.h (#2813)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Thu, 27 Sep 2018 02:22:31 +0000 (07:52 +0530)]
Introduce NEG operation on NeuralNetworks.h (#2813)

This patch introduces ```ANEURALNETWORKS_NEG_EX``` in NeuralNetworks.h
NEG operator is used in mtcnn model.
Related issue : #2167

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoAdd TensorFlowSum custom operator in tflite interpreter (#2797)
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 27 Sep 2018 02:03:18 +0000 (11:03 +0900)]
Add TensorFlowSum custom operator in tflite interpreter (#2797)

This commit registers TensorFlowSum operator in tflite interpreter.
It contains the actual behavior of TensorFlowSum.

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years agoIntroduce DEPTH_TO_SPACE operation into PACL (#2781)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 24 Sep 2018 10:00:20 +0000 (15:30 +0530)]
Introduce DEPTH_TO_SPACE operation into PACL (#2781)

This patch will introduce Depth_To_Space into pure_arm_compute (#2765)

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoEnabling PAD on NEON-PACL (#2728)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 24 Sep 2018 09:59:56 +0000 (15:29 +0530)]
Enabling PAD on NEON-PACL (#2728)

This patch will add neon support for PAD op

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoRemoving unncessary CAST_NE from GenericReshapeLayer (#2774)
Devansh Bansal/System SW /SRI-Bangalore/Engineer/삼성전자 [Fri, 21 Sep 2018 00:13:43 +0000 (05:43 +0530)]
Removing unncessary CAST_NE from GenericReshapeLayer (#2774)

This patch removes unncessary CAST_NE from GenericReshapeLayer, as the configure functions of NEON Kernels expects parameters of type ITensor and the parameters are all of type ITensor.

Signed-off-by: b.devansh <b.devansh@samsung.com>
5 years agoRemove ARM Compute submodule (#2783)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Sep 2018 05:49:20 +0000 (14:49 +0900)]
Remove ARM Compute submodule (#2783)

* Remove ARM Compute submodule

Remove ARM Compute submodule and use source download

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Check ARMComputeSource_FOUND

Return ARMCompute_FOUND false if cannot find ARMComputeSource

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoRevise run & docker-run command (#2786)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Sep 2018 05:47:00 +0000 (14:47 +0900)]
Revise run & docker-run command (#2786)

Revise run & docker-run command
Same implementation with nncc

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[neurun] Add usage getter in Object class (#2784)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 20 Sep 2018 04:37:07 +0000 (13:37 +0900)]
[neurun] Add usage getter in Object class (#2784)

Part of : #2773

This commit adds usage getter in Object class.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoDelete stamp files when clean (#2785)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Sep 2018 04:36:21 +0000 (13:36 +0900)]
Delete stamp files when clean (#2785)

Delete stamp files when clean using Makefile

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoAdd copyright in model file tool & detection (#2779)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 20 Sep 2018 04:02:51 +0000 (13:02 +0900)]
Add copyright in model file tool & detection (#2779)

- Add copyright in tools/tflitefile_tool
- Add coptright in contrib/detection

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[neurun] Implement Permute for StageGenerator (#2775)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 20 Sep 2018 00:45:15 +0000 (09:45 +0900)]
[neurun] Implement Permute for StageGenerator (#2775)

Implement `IStageGenerator::generate` method for Permute operation.
Currently we handle this inserted operation as same with other
operations(Added from NN API).

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Introduce more operation methods (#2777)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 10:38:25 +0000 (19:38 +0900)]
[neurun] Introduce more operation methods (#2777)

Introduce methods for replacing operands for `operation::Node`.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Add getName interface in Node (#2776)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 10:37:44 +0000 (19:37 +0900)]
[neurun] Add getName interface in Node (#2776)

Related : #2685

This commit adds `getName` interface in Node for getting the name of Node info.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoRemoving unncessary CAST_NE from SquaredDifference Op (#2723)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 19 Sep 2018 06:58:11 +0000 (12:28 +0530)]
Removing unncessary CAST_NE from SquaredDifference Op (#2723)

This patch removes unncessary CAST_NE from SquaredDifference Op, Since the configure functions of NEON Kernels expects parameters of type ITensor and the parameters input, output are all of type ITensor.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years ago[neurun] Update operand::LowerInfo (#2771)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 06:57:55 +0000 (15:57 +0900)]
[neurun] Update operand::LowerInfo (#2771)

Have use/def info as BackendSet instead of LayoutSet. This is because
each backend has its own tensors, even if many backends are of the
layout.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Use MockNode.h in verifier TC (#2772)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 06:57:43 +0000 (15:57 +0900)]
[neurun] Use MockNode.h in verifier TC (#2772)

This commit makes the verifier TC uses `MockNode.h`.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoRemoving unncessary CAST_NE from PureACL (#2718)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 19 Sep 2018 06:57:15 +0000 (12:27 +0530)]
Removing unncessary CAST_NE from PureACL (#2718)

This patch removes unncessary CAST_NE from PureACL, Since the configure functions of NEON Kernels expects parameters of type ITensor and the parameters input, output are all of type ITensor.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoRemoving GeneratedTests.l2_norm* from the skiplist (#2725)
PRAVEEN DORESWAMY NAIDU/System SW /SRI-Bangalore/Staff Engineer/삼성전자 [Wed, 19 Sep 2018 06:28:05 +0000 (11:58 +0530)]
Removing GeneratedTests.l2_norm* from the skiplist (#2725)

With #2642 the l2_pool_float* cases passed. Removing from skip list.

Signed-off-by: Praveen D N <praveen.dn@samsung.com>
5 years agoEnabling appendTanh on NEON runtime -PACL (#2762)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 19 Sep 2018 06:15:46 +0000 (11:45 +0530)]
Enabling appendTanh on NEON runtime -PACL (#2762)

This patch will add NEON runtime support for appendTanh

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years ago[neurun] Hold Backend objects as pointer (#2768)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 05:14:13 +0000 (14:14 +0900)]
[neurun] Hold Backend objects as pointer (#2768)

* [neurun] Hold Backend objects as pointer

Make `BackendManager` to return backend's pointer so it does not make
many duplicated objects of `Backend`.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* [neurun] BackendResolver as Graph member

Now that we have Backend as pointer, there is an issue on the scope of
BackendResolver.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoRemoving unncessary CAST_NE from GenericFullyConnectedLayer (#2721)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 19 Sep 2018 05:01:42 +0000 (10:31 +0530)]
Removing unncessary CAST_NE from GenericFullyConnectedLayer (#2721)

This patch removes unncessary CAST_NE from GenericFullyConnectedLayer, Since the configure functions of NEON Kernels expects parameters of type ITensor and the parameters are all of type ITensor.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years ago[neurun] Apply other types for source/sink. (#2740)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 04:53:36 +0000 (13:53 +0900)]
[neurun] Apply other types for source/sink. (#2740)

This commit applies other types for source/sink.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
5 years ago[Tools] Check tflite file correctness (#2767)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 19 Sep 2018 04:08:49 +0000 (13:08 +0900)]
[Tools] Check tflite file correctness (#2767)

- Check tflite file correctness to parse operator option table (option table type defined but undefined value)
- Print and exit if operator selector cannot support

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[neurun] Introduce ITensorBuilder::tensorAt (#2759)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 02:21:32 +0000 (11:21 +0900)]
[neurun] Introduce ITensorBuilder::tensorAt (#2759)

Introduce an interface that returns ITensor objecet for given Index.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] non-const LowerInfo accessor for operand (#2757)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 02:21:23 +0000 (11:21 +0900)]
[neurun] non-const LowerInfo accessor for operand (#2757)

Introduce non-const LowerInfo accesor for `operand::Object`.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[Tool] fix bug (ARM native build version crashes) (#2763)
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 19 Sep 2018 02:20:58 +0000 (11:20 +0900)]
[Tool] fix bug (ARM native build version crashes) (#2763)

This is a bug fix of issue #2727.
The reason is not clear but calling the following throws std::system_error from openCL (-1 : meaning 'unknown')
- cl::Device::getDefault()
- cl::Context::getDefault()
- cl::Platform::getDefault()

Removed the above from main prining section and move them into additional printing section with `try` and `catch` surrounded.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years agoRemove copyright and license from externals/CMakeLists.txt (#2697)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 19 Sep 2018 02:18:45 +0000 (11:18 +0900)]
Remove copyright and license from externals/CMakeLists.txt (#2697)

Related Issue: #2662

We don't put license and copyright on CMakeLists.txt.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years ago[neurun] Introduce OperandPass (#2758)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 19 Sep 2018 02:10:44 +0000 (11:10 +0900)]
[neurun] Introduce OperandPass (#2758)

`OperandPass` is a subclass of `Pass` that iterates for each
`operand::Object`. And subclasses of `OperandPass` must have
implementation of `callback` method.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoImplementation for LRN Layer (#2643)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 19 Sep 2018 01:32:34 +0000 (07:02 +0530)]
Implementation for LRN Layer (#2643)

This patch implements Local Response Normalization Layer in NNFW-PACL

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoEnabling Logistics Op on PureACL NEON runtime (#2715)
Devansh Bansal/System SW /SRI-Bangalore/Professional/삼성전자 [Tue, 18 Sep 2018 10:58:58 +0000 (16:28 +0530)]
Enabling Logistics Op on PureACL NEON runtime (#2715)

This patch enables Logistics Op to run on NEON runtime PureACL.

Signed-off-by: b.devansh <b.devansh@samsung.com>
5 years ago[neurun] Apply memcpy for source/sink (#2754)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 18 Sep 2018 10:58:37 +0000 (19:58 +0900)]
[neurun] Apply memcpy for source/sink (#2754)

This commit applies memcpy for source/sink.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
5 years ago[neurun] Introduce method `IBackendConfig::id` (#2753)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 18 Sep 2018 10:58:23 +0000 (19:58 +0900)]
[neurun] Introduce method `IBackendConfig::id` (#2753)

Introduce method `IBackendConfig::id()` so the backend itself holds its
string ID.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Bring source/sink codes for 2D and 3D (#2752)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 18 Sep 2018 10:58:06 +0000 (19:58 +0900)]
[neurun] Bring source/sink codes for 2D and 3D (#2752)

This commit bring source/sink codes for 2D and 3D from pureacl.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
5 years ago[neurun] Introduce method IndexSet::replace (#2751)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 18 Sep 2018 10:57:47 +0000 (19:57 +0900)]
[neurun] Introduce method IndexSet::replace (#2751)

Introduce operand::IndexSet::replace method which can update an element
in the set.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Introduce `operand::BackendSet` (#2750)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 18 Sep 2018 10:57:14 +0000 (19:57 +0900)]
[neurun] Introduce `operand::BackendSet` (#2750)

BackendSet is a class that is a set of Backends. It will be used from
`operand::LowerInfo` to express which backends need to allocate for a
operand.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Implement PermuteLayer kernel for cpu (#2749)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 18 Sep 2018 10:57:04 +0000 (19:57 +0900)]
[neurun] Implement PermuteLayer kernel for cpu (#2749)

PermuteLayer basically copies data from input tensor to output tensor,
but if the tensor must be permuted it also do permute the tensor.
Currently NHWC to NCHW and NCHW to NHWC permutation is supported.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Introduce graph::Pass (#2747)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 18 Sep 2018 10:56:47 +0000 (19:56 +0900)]
[neurun] Introduce graph::Pass (#2747)

This commit introduces `graph::Pass` that can manipulate the graph
model.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoInstall core libs into /usr/lib in tizen (#2722)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Sep 2018 10:58:38 +0000 (19:58 +0900)]
Install core libs into /usr/lib in tizen (#2722)

- For M2, libneuralnetworks.so should be installed on /usr/lib

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
5 years agoDisable x86_64, i586 build on obs (#2716)
우상정/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Sep 2018 06:46:39 +0000 (15:46 +0900)]
Disable x86_64, i586 build on obs (#2716)

There is build break on obs SR. With this commit, no build is trigged
for x86_64 and i586 arch.

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
Signed-off-by: Sangjung woo <sangjung.woo@samsung.com>
5 years agoRemove scripts/command/change_gitmodule.sh (#2713)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Sep 2018 06:36:14 +0000 (15:36 +0900)]
Remove scripts/command/change_gitmodule.sh (#2713)

This patch removes scripts/command/change_gitmodule.sh, since it is no
longer used, and updates its caller sites.

Same reason with #1085

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoIgnore acl dirty (#2712)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Sep 2018 05:10:41 +0000 (14:10 +0900)]
Ignore acl dirty (#2712)

Ignore acl dirty to ignore build obj and binary
To ignore build directory, you should fix .gitignore in externals/acl

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoFix comparison size_t with zero (#2710)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Sep 2018 02:02:58 +0000 (11:02 +0900)]
Fix comparison size_t with zero (#2710)

Fix comparison size_t with zero (always true)
Compare before casting from int to size_t

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoDownload tensorflow source only (#2703)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 17 Sep 2018 00:35:48 +0000 (09:35 +0900)]
Download tensorflow source only (#2703)

Instead of using submodule, download source code for tensorflow source down & build

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoFix NeuralNetworksLoadHelpers.h bug (#2707)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 14 Sep 2018 10:48:16 +0000 (19:48 +0900)]
Fix NeuralNetworksLoadHelpers.h bug (#2707)

Fix NeuralNetworksLoadHelpers.h bug: same inline function name with NeuralNetworksShims.h in tensorflow lite

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoRemove priavte server name in framework test (#2701)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 14 Sep 2018 09:20:50 +0000 (18:20 +0900)]
Remove priavte server name in framework test (#2701)

Remove priavte server name in framework test configuration
Instead we should pass by environment variable MODELFILE_SERVER
Find modelfile name for zip files

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agopackaging: fix armcl package name (#2705)
우상정/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 14 Sep 2018 09:16:13 +0000 (18:16 +0900)]
packaging: fix armcl package name (#2705)

armcl packages for arm and aarch64 have same package name so fix it.

Change-Id: I1104a35add8e0cfcd19625b4a79051e97e61df35
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Sangjung woo <sangjung.woo@samsung.com>
5 years agoChange license MIT to Apache 2.0 for our ARMComputeEx sources (#2704)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 14 Sep 2018 07:24:42 +0000 (16:24 +0900)]
Change license MIT to Apache 2.0 for our ARMComputeEx sources (#2704)

Related Issue: #2663

For sources that we added under ARMComputeEx, the license is changed
to Apache 2.0, which is our company's default license for open source.

I kept ARM copyright because some code (e.g. PixelWiseDivision) uses
their code, and basically all code are based on ARM compute's skeleton.

StridedSlice and TopKV2 are implemented using TFLite kernels.
Thus the corresponding files have TensorFlow Authors copyright also.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoUse public vanilla arm compute library in submodule (#2696)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 14 Sep 2018 06:52:54 +0000 (15:52 +0900)]
Use public vanilla arm compute library in submodule (#2696)

- change submodule url to vanilla arm compute library
- submodule commit : tag v18.05

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
5 years agoDisable sub/broadcast model test (#2700)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 14 Sep 2018 05:47:08 +0000 (14:47 +0900)]
Disable sub/broadcast model test (#2700)

`sub/broadcast` model test fails after update submodule to public acl
18.05. This commit disables sub test by default.

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
5 years agoEnvironment variable to ignore md5 (#2695)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 14 Sep 2018 05:06:08 +0000 (14:06 +0900)]
Environment variable to ignore md5 (#2695)

Environment variable to ignore md5 when model file is in cache directory

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoAdd MIT in tizen spec's license field (#2699)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 14 Sep 2018 04:18:17 +0000 (13:18 +0900)]
Add MIT in tizen spec's license field (#2699)

Related Issue: #2650, #1977

MIT is specified since ARMComputeEx is introduced, which is under MIT license.
It is required to make happy SOLVe.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoAdd MIT license in LICENSE (#2698)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Fri, 14 Sep 2018 04:11:22 +0000 (13:11 +0900)]
Add MIT license in LICENSE (#2698)

Related Issue: #2650, #1977

MIT license, used in ARMComputeEx, is added in LICENSE.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoEnvironment variable setting for modelfile server (#2691)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 13 Sep 2018 02:43:45 +0000 (11:43 +0900)]
Environment variable setting for modelfile server (#2691)

- Support environment variable "MODELFILE_SERVER" for framework test modelfile download server
- Remove argument for mirror server
- Support zip file download
- Change variable name in config.sh to set download path: MODELFILE_SERVER_PATH

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[neurun] Relocate Dumper from codegen to graph (#2690)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 13 Sep 2018 02:27:46 +0000 (11:27 +0900)]
[neurun] Relocate Dumper from codegen to graph (#2690)

* [neurun] Relocate Dumper from codegen to graph

Related : #2686

This commit relocates Dumper from codegen to graph.
Dumper does not match the meaning of code generation and introducing other dumpers such as `.dot dumper` later are also same.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
* add dumper namespace

5 years agoEnable Explicit Depth-wise Conv on NEON-PACL (#2680)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Thu, 13 Sep 2018 02:27:06 +0000 (07:57 +0530)]
Enable Explicit Depth-wise Conv on NEON-PACL (#2680)

This patch will add support for Explicit Depthwise conv on NEON.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoAdd pure_arm_compute layer for SquaredDifference (#2570)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Thu, 13 Sep 2018 02:25:27 +0000 (07:55 +0530)]
Add pure_arm_compute layer for SquaredDifference (#2570)

This patch adds the pure_arm_compute layer for SquaredDifference.

Signed-off-by: prasannar <prasanna.r@samusng.com>
5 years agoAdd failed tests on vanilla acl submodule (#2694)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 13 Sep 2018 02:22:51 +0000 (11:22 +0900)]
Add failed tests on vanilla acl submodule (#2694)

Some tests will fail after using vanilla acl submodule. To avoid CI
failure, add those tests into skip list.

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
5 years agoFix eigen package checking (#2693)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 13 Sep 2018 01:48:39 +0000 (10:48 +0900)]
Fix eigen package checking (#2693)

Fix eigen package checking in external

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoChange externals download URL (#2689)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 12 Sep 2018 10:36:17 +0000 (19:36 +0900)]
Change externals download URL (#2689)

Change externals download URL from internal mirror to github

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[Contrib] OpenCL experiment code (#2685)
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 12 Sep 2018 09:36:01 +0000 (18:36 +0900)]
[Contrib] OpenCL experiment code (#2685)

This code checks if devices in a GPU use same memory address.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years agoFix gbs build fail : add python to buildrequire (#2687)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 12 Sep 2018 09:35:45 +0000 (18:35 +0900)]
Fix gbs build fail : add python to buildrequire (#2687)

- Fix gbs build fail : add python to buildrequire

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
5 years ago[neurun] Unify duplicate DataType definition (#2671)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 12 Sep 2018 09:23:18 +0000 (18:23 +0900)]
[neurun] Unify duplicate DataType definition (#2671)

This commit unifies duplicate DataType definition.
It can remove `cpu specific` includes for acl_cl kernel.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoEnabling Tanh on pureACL NEON runtime (#2674)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 12 Sep 2018 08:47:05 +0000 (14:17 +0530)]
Enabling Tanh on pureACL NEON runtime (#2674)

This patch enables the TANH operation on pureACL NEON runtime.

Signed-off-by: prasannar <prasanna.r@samusng.com>
5 years agoEnable Squeeze on pureACL on NEON runtime (#2682)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 12 Sep 2018 08:37:13 +0000 (14:07 +0530)]
Enable Squeeze on pureACL on NEON runtime (#2682)

This patch will add Squueze op for Neon runtime in pureACL

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoFix externals CMake (#2683)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 12 Sep 2018 07:43:57 +0000 (16:43 +0900)]
Fix externals CMake (#2683)

Fix externals CMake
- Remove unused include directories
- Remove unused packages on arm cross build
- Change eigen library name

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[neurun] Introduce Permute operation (#2670)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 12 Sep 2018 06:29:22 +0000 (15:29 +0900)]
[neurun] Introduce Permute operation (#2670)

Introduce Permute operation which is for tensor permutation. This
operation is not one of NNAPI operations but inserted internally in the
graph to convert different tensor layouts.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoRemove git submodule and use download (#2678)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 12 Sep 2018 05:46:30 +0000 (14:46 +0900)]
Remove git submodule and use download (#2678)

Instead of using git submodule, use download for externals
(except tensorflow and acl)

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoFix copyright in ARMComputeEx (CLReductionMean.h, fixed_point.h) (#2665)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 12 Sep 2018 05:43:56 +0000 (14:43 +0900)]
Fix copyright in ARMComputeEx (CLReductionMean.h, fixed_point.h) (#2665)

Related Issue: #2663

- Add our copyright since we added `CLReductionMean` kernel.
- Add our copyright since `fixed_point.h` (not existing since ACL18.08) was modified
from ACL18.x.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoUse CLKernellibraryEx on our own kernels (#2675)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 12 Sep 2018 05:39:48 +0000 (14:39 +0900)]
Use CLKernellibraryEx on our own kernels (#2675)

* Use CLKernellibraryEx on our own kernels

- Change  CLKernellibrary to CLKernellibraryEx
- add initilaization of CLKernellibraryEx before creating kernel
FIXME: please suggest better way

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* CLKernellibraryEx initialization on Compilation_finish

- Remove initialization on kernel's configure step
- Add initialization on Compilation_finish

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
5 years agoMake resolve_includes.py work for Python 2 and 3 (#2681)
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 12 Sep 2018 04:26:44 +0000 (13:26 +0900)]
Make resolve_includes.py work for Python 2 and 3 (#2681)

Previously lines with `print` work only on Python 2. Modified for Python 3.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years agoImplementing L2Normalization operation in NNAPI (#2642)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 12 Sep 2018 04:26:12 +0000 (09:56 +0530)]
Implementing L2Normalization operation in NNAPI (#2642)

This commit implements L2Normalization operation in pure_arm_compute runtime.

Signed-off-by: prasannar <prasanna.r@samusng.com>
5 years ago[neurun] Fix Index casting (#2666)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 11 Sep 2018 10:37:42 +0000 (19:37 +0900)]
[neurun] Fix Index casting (#2666)

* [neurun] Fix Index casting

Before Index was used `int32_t` but now it is `uint32_t`. However in
some code the casting is not changed accordingly. This commit changes
those unchanged code and fix misleading comments.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Return BAD_DATA instead of assertion

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoUse include instead of find_package for module (#2667)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Sep 2018 09:24:45 +0000 (18:24 +0900)]
Use include instead of find_package for module (#2667)

Define nnfw_include to use include instead of find_package
Change ExternalProjectTools, ExternelSourceTools, and OptionTools to use nnfw_include (same with nncc)

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoEnable FLOOR on pureacl NEON runtime (#2664)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 11 Sep 2018 08:30:42 +0000 (14:00 +0530)]
Enable FLOOR on pureacl NEON runtime (#2664)

This patch enables the ```Floor``` operation on pureACL ```NEON``` runtime.

Signed-off-by: prasannar <prasanna.r@samusng.com>
5 years agoIntroduce HashtableLookup op in PACL runtime (#2655)
Siva Sai Vaddipati/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 11 Sep 2018 08:27:56 +0000 (13:57 +0530)]
Introduce HashtableLookup op in PACL runtime (#2655)

This commit introduces ANEURALNETWORKS_HASHTABLE_LOOKUP in PACL.
Related issue: #2654

Signed-off-by: Siva Sai <siva.sai@samsung.com>
5 years ago[neurun] Update operand use/def info when inserting operation (#2660)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 11 Sep 2018 08:25:46 +0000 (17:25 +0900)]
[neurun] Update operand use/def info when inserting operation (#2660)

* [neurun] Update operand use/def info when inserting operation

Close : #2619

This commit updates operand use/def info when inserting operation)

- Update Use/Def info while inserting operation
- Do not allow inserting while model building
- Update TCs

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
* Seperate block for updating use/def and fix format break

5 years agoRemoving GeneratedTests.l2_pool_float* from the skiplist (#2648)
PRAVEEN DORESWAMY NAIDU/System SW /SRI-Bangalore/Staff Engineer/삼성전자 [Tue, 11 Sep 2018 08:11:54 +0000 (13:41 +0530)]
Removing GeneratedTests.l2_pool_float* from the skiplist (#2648)

With #2587 and #2633   the l2_pool_float* cases passed. Removing from skip list.

Signed-off-by: Praveen D N <praveen.dn@samsung.com>
5 years agoChange gtest download cmake script (#2659)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Sep 2018 07:39:27 +0000 (16:39 +0900)]
Change gtest download cmake script (#2659)

Change gtest download cmake script simliar with nncc
Prepare supporting public server and mirror server download

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[Generated Tests] Update tests for embedding lookup (#2657)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 11 Sep 2018 06:41:39 +0000 (15:41 +0900)]
[Generated Tests] Update tests for embedding lookup (#2657)

* [Generated Tests] Update tests for embedding lookup

- Remove embedding_lookup in skip lists for pure-acl
- Add embedding_lookup_2d_nnfw for testing 2d tensor
- Add embedding_lookup_4d_nnfw for 4d tensor

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Append embed_xd_nnfw tests to neuron list

5 years agoarm_compute extended library for nnfw (#2653)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Sep 2018 06:35:04 +0000 (15:35 +0900)]
arm_compute extended library for nnfw (#2653)

* arm_compute extented library for nnfw

1. Add libarm_compute_ex.so into nnfw
 - Add CLKernelLibraryEx class : For newly added ops(e.g. cast,
 gather, topk2 ..), CLKernelLibraryEx will be used on next patch.

2. Generate clembed files
 - now, generate embeded_kernel by default
 - add python script
 - add generated files into gitignore list

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* Add samsung license / update gitignore

- Add samsung license into CLKernellibraryEx.h
- Update gitignore for embeded files and comments

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
5 years ago[neurun] Introduce set operators for LayoutSet (#2658)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 11 Sep 2018 06:23:48 +0000 (15:23 +0900)]
[neurun] Introduce set operators for LayoutSet (#2658)

Introduce Union, Intersect and Minus operators to operand::LayoutSet.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Add assert condition to insertOperation (#2639)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 11 Sep 2018 06:23:10 +0000 (15:23 +0900)]
[neurun] Add assert condition to insertOperation (#2639)

The node to be added in `Graph::insertOperation` must not have any
inputs.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoImplement EMBEDDING_LOOKUP op in pure_acl on cpu (#2647)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 11 Sep 2018 04:28:31 +0000 (13:28 +0900)]
Implement EMBEDDING_LOOKUP op in pure_acl on cpu (#2647)

* Implement EMBEDDING_LOOKUP op in pure_acl on cpu

Implement EMBEDDING_LOOKUP op in pure_acl on cpu

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Apply comments

- For 1d tensor, asTensorShape(shape, true)
- Use output_info for offset

* Change output to values

5 years agoAdd run_benchmark_tflite_model.sh (#2640)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 11 Sep 2018 04:14:06 +0000 (13:14 +0900)]
Add run_benchmark_tflite_model.sh (#2640)

Related Issue: #2544

`run_benchmark_tflite_model.sh` will run `tflite_benchmark_model` tool
with `run_benchmark_tflite_model.in` as input.

`run_benchmark_tflite_model.in` can have several lines.
Each line is a pair of (model name, its parameters for `tflite_benchmark_model`).
Its delimeter is `\t`.

For example, see `run_benchmark_tflite_mode.in`.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoAdd our license under runtimes/pure_arm_compute (#2649)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 11 Sep 2018 01:15:36 +0000 (10:15 +0900)]
Add our license under runtimes/pure_arm_compute (#2649)

Related Issue: #2644

Add our licenses for all *.[cpp,cc,h] under runtimse/pure_arm_compute

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years ago[neurun] Add license to source files (#2651)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 11 Sep 2018 01:13:09 +0000 (10:13 +0900)]
[neurun] Add license to source files (#2651)

This commit prepends license comment to the source files.

Resovle #2645

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoParameter to set mirror sever (#2652)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 11 Sep 2018 01:02:14 +0000 (10:02 +0900)]
Parameter to set mirror sever (#2652)

Add new parameter in run_test.sh to set model file's mirror server

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoSet umask for temp file generation (#2637)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 10 Sep 2018 04:21:19 +0000 (13:21 +0900)]
Set umask for temp file generation (#2637)

Set umask and recover after generate temporary file to avoid security issue

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoAdding explicit padding support for L2Pool2D (#2633)
Siva Sai Vaddipati/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 10 Sep 2018 02:18:01 +0000 (07:48 +0530)]
Adding explicit padding support for L2Pool2D (#2633)

This commit enables L2Pool2D operation with explicit padding.
Related issue: #2562

Signed-off-by: Siva Sai <siva.sai@samsung.com>
5 years agoRemove tensor.h deps of RSQRT, SQDiff (#2638)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 10 Sep 2018 02:16:49 +0000 (11:16 +0900)]
Remove tensor.h deps of RSQRT, SQDiff (#2638)

To fix gbs build, remove tensor.h deps of RSQRT and SQDiff

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
5 years agoBUILD_TYPE=Release is specified in docker_env for tflite_benchmark_model (#2641)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 10 Sep 2018 02:06:40 +0000 (11:06 +0900)]
BUILD_TYPE=Release is specified in docker_env for tflite_benchmark_model (#2641)

Previously, build_type was specified in CI's groovy script.
But I would like to set all environment in one place - docker env file.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoRevise framework test list (#2636)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 7 Sep 2018 04:01:00 +0000 (13:01 +0900)]
Revise framework test list (#2636)

- Change directory structure: test/{tflite op name}/{testname}
- Add new framework tests to support more operators
- Update test list for neurun and benchmark_op

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoIntroduce EMBEDDING_LOOKUP op to pure_acl (#2631)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 7 Sep 2018 01:07:09 +0000 (10:07 +0900)]
Introduce EMBEDDING_LOOKUP op to pure_acl (#2631)

Introduce EMBEDDING_LOOKUP op to pure_acl

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
5 years ago[neurun] Implement Lowering operands (#2630)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 7 Sep 2018 01:00:00 +0000 (10:00 +0900)]
[neurun] Implement Lowering operands (#2630)

This commit implements lowering for operands in `Graph::lower`.
operands lowering does the following:

- Normalize to 4D shape (rank greater than 4 does not supported)
- Collect info of operand layouts for def/use

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Introduce asShape4D (#2626)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 6 Sep 2018 10:24:06 +0000 (19:24 +0900)]
[neurun] Introduce asShape4D (#2626)

This commit introduces asShape4D function to convert from
`operand::Shape` to `operand::LowerInfo::Shape4D`. This is
normalization to 4D shape.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Add LowerInfo to operand::Object (#2628)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 6 Sep 2018 10:23:56 +0000 (19:23 +0900)]
[neurun] Add LowerInfo to operand::Object (#2628)

Add LowerInfo to operand::Object as a member.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoDiff: initialize output tensor (#2627)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 6 Sep 2018 10:23:45 +0000 (19:23 +0900)]
Diff: initialize output tensor (#2627)

Initialize output tensor as zero
Need to RNN hidden state initialize

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years ago[neurun] Introduce operand::LowerInfo (#2622)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 6 Sep 2018 09:48:48 +0000 (18:48 +0900)]
[neurun] Introduce operand::LowerInfo (#2622)

This commit introduces operand::LowerInfo which contains normalized
4D shape and tensor layout.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoAdd Transpose into nnapi_delegate (#2624)
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 6 Sep 2018 09:23:52 +0000 (18:23 +0900)]
Add Transpose into nnapi_delegate (#2624)

This commit enables TF Lite to call Transpose operation of NNAPI.

Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
5 years ago[neurun] Add basic methods to LayoutSet (#2623)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 6 Sep 2018 08:24:01 +0000 (17:24 +0900)]
[neurun] Add basic methods to LayoutSet (#2623)

Introduce `contains` and `size` method for user queries.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>