오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 19 Jul 2018 08:40:18 +0000 (17:40 +0900)]
Fix benchmark failure (#2001)
Fix benchmark test failure: migrate to armcl v18.05
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이성재/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 19 Jul 2018 07:21:08 +0000 (16:21 +0900)]
Introduce FEATURE_REQUEST prodcess. (#2012)
- Add guide for FEATURE_REQUEST.
- Add empty docs/HowToImplementOperatorKernel.md
Signed-off-by: Sung-Jae Lee <sj925.lee@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 19 Jul 2018 07:16:40 +0000 (16:16 +0900)]
[neurun] Fix inception test name (#2017)
Fix wrong name `inception` to `inceptionv3`
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 19 Jul 2018 06:39:45 +0000 (15:39 +0900)]
[neurun] Rename build variables (#1997)
Rename build variables
- BUILD_NEW_RUNTIME to BUILD_NEURUN
- LIB_NEW_RUNTIME to LIB_NEURUN
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 19 Jul 2018 06:38:57 +0000 (15:38 +0900)]
[newrt] Support Concat from acl_cl backend (#2010)
Enable Concat from acl_cl backend. So now we can run inception v3
with acl_cl backend only.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 19 Jul 2018 03:02:17 +0000 (12:02 +0900)]
Tidy cmake, separate configuration flags (#2008)
This will extract configuration flags to separate file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Thu, 19 Jul 2018 02:04:41 +0000 (11:04 +0900)]
Tidy cmake, separate gtest support (#2007)
This will extract gtest support codes to separate file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 19 Jul 2018 00:57:20 +0000 (09:57 +0900)]
[neurun] Change dir structure of cpu backend (#2006)
Move directory `internal/cpu` to `backend/cpu`.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 19 Jul 2018 00:52:45 +0000 (09:52 +0900)]
[neuron] Implement Concat acl_cl kernel (#1986)
* [neurun] Implement Concat acl_cl kernel
Implement Concat acl_cl kernel which is not exists in arm_compute lib.
Part of #1861
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Reflect comments
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Reflect comment 2
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 18 Jul 2018 08:15:55 +0000 (17:15 +0900)]
Tidy cmake, relocate variables and options (#1992)
This will move common options and variables to option_linux file
And remove unused ACL folder variables
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 18 Jul 2018 07:54:20 +0000 (16:54 +0900)]
[tool] Converts TF checkpoint file to PB file (#1965)
This tool converts TF checkpoint file to PB file and
freeze the PB file.
(Written for #1927, https://github.sec.samsung.net/STAR/nnfw/issues/1927#issuecomment-122799)
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 18 Jul 2018 07:33:35 +0000 (16:33 +0900)]
[tool] TFLITE file generator for Squeeze operations (#1948)
This file creates the following tflites:
```
/home/eric/models/squeeze/squeeze_2d.tflite
/home/eric/models/squeeze/squeeze_4d_1.tflite
/home/eric/models/squeeze/squeeze_4d_2.tflite
/home/eric/models/squeeze/squeeze_4d_3.tflite
/home/eric/models/squeeze/squeeze_4d_4.tflite
```
which are
- squeeze_2d.tflite: `squeeze (Tensor(shape=[1, 3]))`
- squeeze_4d_1.tflite: `squeeze (Tensor(shape=[1, 3, 2, 1]))`
- squeeze_4d_2.tflite: `squeeze (Tensor(shape=[1, 3, 2, 1]), axis=[0]) # squeeze [1, 3, 2, 1] to [3, 2, 1]`
- squeeze_4d_3.tflite: `squeeze (shape=Tensor([1, 3, 2, 1]), axis=[3]) # squeeze [1, 3, 2, 1] to [1, 3, 2]`
- squeeze_4d_4.tflite: `squeeze (shape=Tensor([1, 3, 2, 1]), axis=[0, 3]) # squeeze [1, 3, 2, 1] to [3, 2]`
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 18 Jul 2018 06:20:16 +0000 (15:20 +0900)]
[neurun] Rename `new_runtime` to `neurun` (#1994)
As we discussed from #1954, changing the name to `neurun`.
Note that it is `neurun`, not `neuron`.
Resolves #1987
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 18 Jul 2018 02:40:14 +0000 (11:40 +0900)]
Modify generate<uint8_t> of RandomGenerator to generate the appropriate random value. (#1912)
This commit modifies generate<uint8_t> of RandomGenerator to generate the appropriate random value.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 18 Jul 2018 01:07:57 +0000 (10:07 +0900)]
Tidy cmake, separate identify_platform (#1991)
This will separate platform identification codes to own file
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 18 Jul 2018 01:00:27 +0000 (10:00 +0900)]
Tidy cmake, apply indentation (#1989)
This will add indentation to cmake file that was left some time ago
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 17 Jul 2018 10:59:51 +0000 (19:59 +0900)]
[tool] make pb_info.py prints name filtered by prefix (#1981)
pb_info.py prints name filtered by prefix.
for example running `pb_info.py --name_prefix='Model/rnn' <more options>` prints operations with their names starting with 'Model/rnn'
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 17 Jul 2018 10:09:40 +0000 (19:09 +0900)]
Add functions for python script of test_driver (#1978)
Add `make_json_for_benchmark_result` function
Add `run_benchmarkop` function
Add related options, parameters
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 17 Jul 2018 04:55:01 +0000 (13:55 +0900)]
[tool] Remove python 2.7 restriction (#1976)
This commit removes python 2.7 restriction of `tools/tensorflow_model_freezer` tool
after testing on Python 3.6.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 17 Jul 2018 04:54:03 +0000 (13:54 +0900)]
Updates for python script of test_driver (#1971)
Add missing options(frameworktest_list_file, benchmark_op)
Fix test script paths
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 17 Jul 2018 04:26:40 +0000 (13:26 +0900)]
Updates shebang for python script of test_driver (#1975)
Add `#!usr/bin/env python` to be executed by python, not bash
Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 17 Jul 2018 01:59:37 +0000 (10:59 +0900)]
[newrt] Rename namespace `kernels` to `kernel` (#1964)
Rename `kernels` to `kernel` since our general convention is to use
singular.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 17 Jul 2018 01:06:45 +0000 (10:06 +0900)]
[newrt] Update backend name to `acl_cl` (#1972)
Update backend name to `acl_cl` from `arm_compute` since this backend
only uses CL part.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 16 Jul 2018 08:29:16 +0000 (17:29 +0900)]
[newrt] Implement SoftMax kenrel for CPU (#1968)
This commit implements SoftMax kernel for CPU in new runtime.
Add others
- QuantizeMultiplierGreaterThanOne, CalculateInputRadius
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 16 Jul 2018 08:28:12 +0000 (17:28 +0900)]
[newrt] Do not mmap for CPU tensor allocation (#1951)
* [newrt] Do not mmap for CPU tensor allocation
For CPU tensor memory we do not have to mmap for tensors, just allocate
with plain heap memory with `new`.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Add comment for cpu tensor allocation
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 16 Jul 2018 05:04:31 +0000 (14:04 +0900)]
[newrt] Implement Reshape kernel for CPU (#1950)
* [newrt] Implement Reshape kernel for CPU
This commit implements Reshape kernel for CPU in new_runtime.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
* Add errer handling in sizeOfData
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 13 Jul 2018 07:49:45 +0000 (16:49 +0900)]
Update nn_android_runtime_test to p-preview-4 (#1935)
commit:
c73accf066d4f05372
link : https://android.googlesource.com/platform/frameworks/ml/+/android-p-preview-4
cf) all *relaxed* tests are omitted
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 13 Jul 2018 07:10:57 +0000 (16:10 +0900)]
[newrt] Require ARMCompute for build (#1949)
Currently we depend on ARMCompute for abstract classes so we need it
always even we only want cpu kernels. However later we should remove
this requirement.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 13 Jul 2018 07:10:12 +0000 (16:10 +0900)]
[newrt] Implement FullyConnected kernel for CPU (#1943)
* [newrt] Implement FullyConnected kernel for CPU
This commit implements FullyConnected kernel for CPU in new runtime.
- Other jobs
- Add getNumberOfElements
- Add zeroPoint(offset)
- Add QuantizeMultiplierSmallerThanOne, GetQuantizedConvolutionMultipler
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
* Add TODO, Add weight/bias for quant8_asymm
* Add comment for GetQuantizedConvolutionMultipler
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 13 Jul 2018 06:23:55 +0000 (15:23 +0900)]
Change the rounding policy of MUL from TO_ZERO to TO_NEAREST_EVEN (#1940)
This commit changes the rounding policy of MUL from TO_ZERO to TO_NEAREST_EVEN.
If the rounding policy is TO_NEAREST_EVEN, it is most similar to the result of the TFLITE interpreter.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Jul 2018 23:49:02 +0000 (08:49 +0900)]
Build ACL in svace build (#1947)
Build ACL instead of using external ACL in svace build
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 11 Jul 2018 09:24:25 +0000 (18:24 +0900)]
[newrt] Let the user select backend per operation (#1929)
By default, arm_compute backend will be used for all operations.
Resolve #1878
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Jul 2018 08:33:13 +0000 (17:33 +0900)]
Change from implicit namespace to Explicit (#1938)
This commit alters namesapce name for consistency.
- change form implicit to Implicit to keep consistent with Explicit.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Jul 2018 07:22:12 +0000 (16:22 +0900)]
Introduce explicit padding in max pooling (#1923)
* Introduce explicit max pooling
This commit introduces explicit max pooling.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* Revise namespace as Explicit
This commit revises namespace as Explicit for consistency.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* Delete unused and unnecessary blanks
This commit deletes unused and unnecessary blanks.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
윤현식/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Jul 2018 06:52:18 +0000 (15:52 +0900)]
Prints summary of pb file (#1946)
Added `--summary` option to prints the list of operations and their counts in pb file.
Written for #1927.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Jul 2018 05:25:52 +0000 (14:25 +0900)]
Fix makefile for svace (#1945)
Fix build runtime only: build pure runtime
Fix testbuild: remove kernelacl_test
Fix tflite build: add googletest
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 11 Jul 2018 04:25:47 +0000 (13:25 +0900)]
[newrt] Remove unused code (#1944)
Remove unused code that is commented out
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Jul 2018 02:59:33 +0000 (11:59 +0900)]
Skip GeneratedTests.concat_quant8_2 (#1942)
1. Add GeneratedTests.concat_quant8_2 into skiplist
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Jul 2018 02:39:45 +0000 (11:39 +0900)]
Add explicit padding to dconv (#1937)
This commit adds explicit padding to dconv.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Jul 2018 01:52:12 +0000 (10:52 +0900)]
Add failed test(preview4) into skiplist (#1934)
For generated tests of android-p-preview4, add failed test into skiplist
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 11 Jul 2018 01:51:33 +0000 (10:51 +0900)]
Update ARM CL to v18.05 (#1925)
Patch to migrate ARM CL v18.05
- Use arm_compute/graph/frontend API to build graph data structure
- Update ACL submodule: v18.05
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Jul 2018 01:34:32 +0000 (10:34 +0900)]
Add explicit padding to conv (#1936)
* Add explicit padding to conv
This commit adds explicit padding to conv.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* Revise namespace as Explicit
This commit revises namespace as Explicit for consistency.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 11 Jul 2018 00:50:08 +0000 (09:50 +0900)]
Add explicit padding to average pooling (#1928)
* Add explicit padding to average pooling
This commit adds explicit padding to average pooling.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* Remove unused and unnecessary blank
This commit removes unused and unnecessary blank
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* Revise namespace as Explicit
This commit revises namespace as Explicit for consistency.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Jul 2018 23:46:57 +0000 (08:46 +0900)]
[newrt] Implement Concat kernel for CPU (#1924)
Related : #1860
This commit implements `Concat` kernel for CPU in new runtime.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 10 Jul 2018 09:53:55 +0000 (18:53 +0900)]
Update tflite file API (#1832)
Update tflite file API generated by flatc
Using updated schema in tensorflow 1.9
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 10 Jul 2018 09:53:33 +0000 (18:53 +0900)]
Set pureacl runtime to be the main runtime (#1908)
0. do not build legacy(nn) runtime into out/lib
- install legacy(nn) runtime into out/lib/legacy
1. Trigger puracl runtime build on default
2. install pureacl runtime into out/lib
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Jul 2018 08:56:50 +0000 (17:56 +0900)]
[newrt] Implement MaxPool kernel for CPU (#1919)
Related : #1860
This commit implements MaxPool kernel for CPU in new runtime.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Jul 2018 08:35:25 +0000 (17:35 +0900)]
Add QuantizationInfo to TensorInfo in operands that supports QASYMM8_TENSOR (#1893)
This commit adds QuantizationInfo to TensorInfo in operands that supports QASYMM8_TENSOR.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Jul 2018 07:10:52 +0000 (16:10 +0900)]
Fix wrong inclusion and scale value in nnapi_unittests. (#1926)
This commit fixes wrong inclusion and scale value in nnapi_unittests.
List of fixed scale value
- add
- conv
- dconv
- mul
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 10 Jul 2018 06:56:58 +0000 (15:56 +0900)]
Add strided_slice_ex_float_10 to skip list (#1910)
Add GeneratedTests.strided_slice_ex_float_10 to skip list for linux/tizen
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Jul 2018 05:30:56 +0000 (14:30 +0900)]
Introduce new UnsupportedOperationCount class (#1876)
- This UnsupportedOperationCount class will be used for distinguishing
whether an operator can be counted on operation counts.
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Jul 2018 05:22:21 +0000 (14:22 +0900)]
[Refactor] Remove if/else(switch case) of rank for addShapeConstr (#1839)
* Remove if/else(switch case) of rank for addShapeConstr
Related : #1828
This commit removes if/else(switch cases) of rank for `addShapeConstr`.
That's because `asTensorShape` which used in `addShapeConstr` parameter includes if/else for processing shapes by each ranks.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
* Apply #1741 cases
* Update rank check for Cast
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Jul 2018 05:19:25 +0000 (14:19 +0900)]
Enable other type of operands in FC operation (#1895)
This commit enables other type of operands in FC operation.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 10 Jul 2018 01:49:32 +0000 (10:49 +0900)]
tools/nnapi_unittest runs as GTest (#1810)
Some unittest have not been modified yet, so these cases are changed to GTest.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 10 Jul 2018 01:38:47 +0000 (10:38 +0900)]
Turn off warning on g++ 6.+ (#1916)
* Turn off warning on g++ 6.+
Turn off warning by arm cl when we use cross compiler version 6.+
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Check gcc version
Check gcc version to set warning flag
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 10 Jul 2018 01:25:10 +0000 (10:25 +0900)]
Add testcase for left rank < right rank (#1787)
* Add testcase for left rank < right rank
This commit adds a testcase for different rank
-left rank < right rank
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
* Change to a gtest format
This commit changes main format to a gtest.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 9 Jul 2018 09:23:20 +0000 (18:23 +0900)]
Remove incorrect link_library to neuralnetworks (#1918)
In neural_networks_test, libneuralnetworks incorrectly is linked.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Jul 2018 07:19:46 +0000 (16:19 +0900)]
Enables other type of operands in CONV2D operation. (#1889)
* Change the type of CONV2D's Bias from QASYMM8 to INT32
This commit changes CONV2D's bias type from QASYMM8 to INT32.
According to the nnapi description, for input tensor of {@link ANEURALNETWORKS_TENSOR_QUANT8_ASYMM} type, the bias should be of {@link ANEURALNETWORKS_TENSOR_INT32}.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
* Add QuantizationInfo to TensorInfo in CONV2D operation.
This commit adds QuantizationInfo to TensorInfo in CONV2D operation.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 9 Jul 2018 06:45:18 +0000 (15:45 +0900)]
[New runtime] Skeleton for addOperationEx (#1913)
Prepare addOperationEx
Fix link error
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Jul 2018 06:39:04 +0000 (15:39 +0900)]
Update ACL (Cast float to qasymm8) (#1881)
This commit updates ACL (Cast float to qasymm8).
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 9 Jul 2018 05:45:11 +0000 (14:45 +0900)]
Disable pureacl/new runtine build which depends on arm compute library (#1909)
On x64, disable pureacl/new runtine build which depends on arm compute library
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Jul 2018 05:43:23 +0000 (14:43 +0900)]
Change the scale value of unit test related to the convolution. (#1887)
This commit change the scale value of unit test related to the convolution.
- Change the scale value of output operand to 1.0f.
- Change the scale value of input and kernel operand to 0.02f.
- Change the scale value of bias to the value of multiplying input scale and kernel scale.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Jul 2018 05:23:42 +0000 (14:23 +0900)]
[newrt] Remove CPU prefix of ConvolutionLayer class (#1891)
This commit removes CPU prefix of ConvolutionLayer class
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 9 Jul 2018 04:54:00 +0000 (13:54 +0900)]
--env-file option for docker cross arm build (#1879)
* --env-file option for docker cross arm build
1. support --env-file option via $ENV_FILE
2. add env_file for pureacl, new_runtime build
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* Rename env files
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* remove empty line
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 9 Jul 2018 02:08:29 +0000 (11:08 +0900)]
Modify wrong values in testcases (#1865)
This commit modifies wrong values in testcases.
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 9 Jul 2018 01:45:15 +0000 (10:45 +0900)]
[newrt] Fix build failure in > gcc 5.6 (#1898)
This commit fixes build failure in > gcc 5.6.
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 9 Jul 2018 01:44:59 +0000 (10:44 +0900)]
Remove test build from newruntime build (#1903)
There is link error when building runtime_run_android_nn_test with new runtime.
Before fixing all buld error by newruntime, disable runtime_run_android_nn_test.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 9 Jul 2018 01:37:09 +0000 (10:37 +0900)]
Update NeuralNetworks.h from android-p-prevew-4 (#1905)
Related Issue: #1904
Android-p-preview-3 announced that it will have fixed NNAPI v1.1.
However I would like to update NeuralNetworks.h from android-p-preview-4's.
Because
- it updated comments (style, description, ...).
- it fixed a mistake included in android-p-preview-3.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 9 Jul 2018 01:35:38 +0000 (10:35 +0900)]
link runtime_run_android_nn_test to nnapi_puer_arm_compute (#1901)
this commit adds link runtime_run_android_nn_test to nnapi_puer_arm_compute,
which is missing now.
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 6 Jul 2018 08:14:00 +0000 (17:14 +0900)]
Fix link error when linking runtime_run_android_nn_test with pureacl (#1900)
Fix : #1899
1. add dummy APIs to fix link error
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 6 Jul 2018 06:45:02 +0000 (15:45 +0900)]
Enable the kTfLiteUInt8 of the input operands in RandomTestRunner to be random value. (#1882)
This commit enables the kTfLiteUInt8 of the input operands in RandomTestRunner to be random value.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 6 Jul 2018 02:31:51 +0000 (11:31 +0900)]
[newrt] Implement AvgPool kernel for CPU (#1880)
* [newrt] Implement AvgPool kernel for CPU
This commit implements AvgPool kernel for CPU in new runtime.
Signed-off-by:sjsujinkim sjsujin.kim@samsung.com
* Relocate to_string to support/nnapi
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 6 Jul 2018 02:09:14 +0000 (11:09 +0900)]
Introduce EnvVar class (#1884)
* Introduce EnvVar class
EnvVar reads environment variables from system and can return the
value as string, bool or int.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Move EnvVar.h to nnfw/include/util
Move the file and add namespace
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 6 Jul 2018 01:58:39 +0000 (10:58 +0900)]
Define android nn test skiplist for pure arm compute runtime (#1854)
* Define android nn test skiplist for pure arm compute runtime
1. backup the existing skiplist for legacy runtime
2. define new skiplist for pure arm compute runtime
related issue: #1851
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* rename backup file
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* add new line
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 07:30:01 +0000 (16:30 +0900)]
Add unit test for operations that support ANEURALNETWORKS_TENSOR_QUANT8_ASYMM (#1857)
This commit adds unit tests for operations that support ANEURALNETWORKS_TENSOR_QUANT8_ASYMM.
Operation list of added unit test
- ANEURALNETWORKS_TENSOR_ADD
- ANEURALNETWORKS_AVERAGE_POOL_2D
- ANEURALNETWORKS_CAST_EX (QUANT8_ASYMM to FLOAT32)
- ANEURALNETWORKS_CONCATENATION
- ANEURALNETWORKS_CONV_2D
- ANEURALNETWORKS_DEPTHWISE_CONV_2D
- ANEURALNETWORKS_FULLY_CONNECTED
- ANEURALNETWORKS_MAX_POOL_2D
- ANEURALNETWORKS_MUL
- ANEURALNETWORKS_RELU
- ANEURALNETWORKS_RELU6
- ANEURALNETWORKS_RESHAPE
- ANEURALNETWORKS_SOFTMAX
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Jul 2018 07:12:08 +0000 (16:12 +0900)]
Add buildscript for new runtime (#1875)
This script is used on CI to build new runtime
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 06:04:37 +0000 (15:04 +0900)]
Apply OperatorParser to model_parser.py (#1871)
Apply OperatorParser to model_parser.py. Now model_parser.py
uses OperatorParser.
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 05:49:21 +0000 (14:49 +0900)]
[newrt] Use ACL backend for all operations (#1874)
Currently we cannot run with heterogeneous backends, set all backends as
ACL. Later, we are going to control it with environment variables.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 05:28:38 +0000 (14:28 +0900)]
Apply format checker to new runtime (#1872)
This commit applies format checker to new runtime
Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 05:14:11 +0000 (14:14 +0900)]
[CMake] Extract building runtime test as a param (#1870)
Before `add_subdirectory(tests)` was called twice if we run both two
runtimes which causes cmake error.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Jul 2018 05:04:09 +0000 (14:04 +0900)]
Create frameworktest list file for new runtime (#1869)
convolution1 and convolution2 model added
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 04:06:20 +0000 (13:06 +0900)]
Introduce OperatorParser for model_parser (#1858)
* Introduce OperatorParser for model_parser
- To remove `TFLiteModelFileParser`'s dependencies for tflite.operator,
tflite.tensor, introduce new class `OperatorParser`.
- `OperatorParser` class handles `Operator` class and `Tensor` class.
- Not yet changed model_parser.py. To test this, it needs another commit
for new operator counter and changes on model_parser.py
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Rename __ to _wrapping
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 04:06:03 +0000 (13:06 +0900)]
Introduce OperationCount and PerfPredictor (#1859)
* Introduce OperationCount and PerfPredictor
- For #1836
- OperationCount class has count units and these will be calculated for
total cycle by PerfPredictor
- PerfPredictor class will calculate total cycles with OperationCount.
By setting each cycle's value, performance prediction will be
calculated.
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Add more description for how to calc in detail
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 03:46:23 +0000 (12:46 +0900)]
Add nnapi_unittest for ReLU1 (#1864)
relu1_1 is for 2 ranks input model.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 5 Jul 2018 03:20:42 +0000 (12:20 +0900)]
Disable logistic/l2pool2d on framework test (#1856)
On pure arm compute runtime, logistic/l2pool2d fail on framework test.
This commit makes CI to run seamless when pureacl runtime runs as default runtime.
Related issue : #1851
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 03:17:39 +0000 (12:17 +0900)]
Definitions for supporting Tanh in pureacl runtime (#1846)
Define namespace, node, param for Tanh
Signed-off-by: seok <sk.namkoong@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 03:14:13 +0000 (12:14 +0900)]
Support other types for TfLiteInterpMatchApp (#1842)
This commit supports other types for TfLiteInterpMatchApp.
- Change TfLiteInterpMatchApp::compareSingleTensorView() to the template method.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 5 Jul 2018 01:34:07 +0000 (10:34 +0900)]
Add Kernel ACL test case for ReLU6 (#1766)
Add tests for both NEON and CL kernel were added
Support tests for 2d-tensors and 4d-tensors
To compare a performance btw BOUNDED_RELU and LU_BOUNDED_RELU,
add two kinds of ReLU6 implementation
- BOUNDED_RELU : Upper Bounded Rectifier (f(x) = min(a, max(0,x))
- LU_BOUNDED_RELU : Lower and Upper Bounded Rectifier (f(x) = min(a, max(b,x))
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 4 Jul 2018 09:32:47 +0000 (18:32 +0900)]
[new_runtime] Support CPU backend (#1847)
Conv2D Operation is only supported yet.
Implement #1607 into the current runtime structure.
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 4 Jul 2018 07:30:34 +0000 (16:30 +0900)]
Support other types for RandomGenerator (#1831)
This commit supports other types(int32_t, uint8_t) for RandomGenerator.
- Add quantization info to RandomGenerator.
- Change class RandomGenerator to not be the template class.
- Change operator method to template method(generate<>()).
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 4 Jul 2018 07:22:59 +0000 (16:22 +0900)]
Add ops_counter for operator types in Inceptionv3 (#1824)
Add ops_counter for operator types in Inceptionv3.
- Pooling, Softmax, FullyConnected.
- LogSoftmax: this is added but not used.
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 4 Jul 2018 07:11:12 +0000 (16:11 +0900)]
Add inline keyword to `iterate()` (#1848)
To avoid multiple definition error
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 4 Jul 2018 05:31:01 +0000 (14:31 +0900)]
[new_runtime] Initial structure change (#1843)
Change runtime structure to support multiple backends
- Introduce `Backend` which contains IInitializerGenerator and
IStageGenerator
- Introduce `BackendResolver` so we can choose which backend for each
operation
- Introduce `IObject` so it can access any kind of tensors from different
backends
- Move arm_compute-specific implementation to arm_compute directory
- Keep Concat layer for later elimination since it is hard to know at
first if we have heterogeneous backends
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 4 Jul 2018 03:59:49 +0000 (12:59 +0900)]
Add a float variable of nearest to 1 (#1837)
This commit adds a float variable of nearest to 1.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 4 Jul 2018 02:47:31 +0000 (11:47 +0900)]
Change install dir of new runtime (#1844)
1. install new runtime into lib/new_runtime
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
남궁석/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 4 Jul 2018 01:36:52 +0000 (10:36 +0900)]
Recover the sequence of LD_LIBRARY_PATH (#1838)
The sequence of LD_LIBRARY_PATH should be remained as it was.
Recover the sequence of LD_LIBRARY_PATH
Signed-off-by: seok <sk.namkoong@samsung.com>
tflite_benchmark: use get_env_bool instead of getenv (#1812)
* tflite_benchmark: use get_env_bool instead of getenv
Replace std::getenv by nnfw::util::get_env_bool for USE_NNAPI
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* Update tflite_benchmark.cc
tflite_benchmark: get env refactor (#1801)
* tflite_benchmark: get env refactor
using nnfw::util::get_env_int instead of custom get_env call
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* add const spec
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
* fix compare signed/unsigned issue
tflite_benchmark: use get_env_int for THREAD (#1840)
Replace std::getenv by nnfw::util::get_env_int for THREAD
Signed-off-by: Vitaliy Cherepanov <v.cherepanov@samsung.com>
최성진/동작제어Lab(SR)/Principal Engineer/삼성전자 [Tue, 3 Jul 2018 10:34:36 +0000 (19:34 +0900)]
Consider different rank between left and right operands for broadcasting (#1786)
This commit resolve different rank between left and right operands for broadcasting
Signed-off-by: SungJin Choi <lotieye.choi@samsung.com>