Age | Commit message (Collapse) | Author | Files | Lines |
|
It introduces `tflite2circle` tool.
Its input is `tflite` and output is `circle`.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
- Change to use the 'tensorflow' module installed on the system by
default.
Signed-off-by: Sung-Jae Lee <sj925.lee@samsung.com>
|
|
- Introduce script to make nnpkg testsuite in CI build server
- Introduce script to test nnpkg testsuite in xu4 farm
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
`nnpkg_test`
- distinguish the run and compare result.
- shows the errors after a blank line.
- does not use `set -e` to continue after error for pretty printing.
`model2nnpkg`
- It becmome less noisy.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
Introduce tool for converting nncc testcase to nnpkg testcase.
Please read README.md for usage.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
Introduce a tool for running an nnpackage testcase.
It will run nnpackage with nnpackage_run, and compare the result.
For usage, find README.md.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
This patch introduces model2nnpackage.
It will take model file (either circle or tflite) and generate
containing nnpackage.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
I would like to put all nnpackage-related tools under one directory.
Thus, I introduce `tools/nnpackage_tool` and move `nnpackager` into it.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
Update ACL version for Android RootFS - v18.03 to v19.05
Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
|
|
- Install hdf5f and dependent libraries on arm rootfs
- Update CMakeLists.txt
- Create HDF5Config.cmake
- Update nnpackage_run's dump with dummy hdf5 creating code.
- To test whether hdf5 works.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
* Change to use the 'tensorflow' module installed on the system by default.
Signed-off-by: Sung-Jae Lee <sj925.lee@samsung.com>
|
|
This commit fixes converting type of zero point in select_operator.py.
Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
|
|
Use "nnpackage -c path_to_nnpackage_root" to get compressed nnpackage.
Also it removed redundant parenthesis in if condition.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
nnpackger always verified. Now, it verifies if verify is given.
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
This PR introduces nnpackager, which provides verify function only.
It checks:
- the existence of nnpackager root directory
- the existence of MANIFEST
- the validity of json format
- the existence of models file
Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
|
|
* Change old API `gfile.FastGFile` to `tf.gfile.GFile`
Signed-off-by: Sung-Jae Lee <sj925.lee@samsung.com>
|
|
Pylint warning: pointless-string-statement
Change to comment
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
Change to instance method in _OperationComputeMethod class
Not working now because static method don't have "__name__" field
Change operation comment
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
Fix pylint warning by
- Pointless string (for comment): change to comment
- Bad super parameter: change old style self.__class__ to classname itself
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
* Upgrade to tensorflow v1.13.1
- update link to v1.13.1
- tensorflow/contribe/lite to tensorflow/lite
- TFLITE_MINOR_VER to 13
Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* upgrade absl to 389ec3f90
* add custom for SquaredDifference
* Fix x64 build error(Eigen)
- update eigen version to 88fc23324517
* fix wrong comment : lite -> contrib/lite
|
|
Update generated API files from schma.fbs in tensorflow 1.13.1
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
* [kbenchmark] rename acl kernel directory
armcl to acl_cl
armne to acl_neon
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Change the include directory path
* Do not print psABI warnings
|
|
Fix pylint warning for print syntax in image importer
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
Fix pylint warning for print syntax in weight extract tool
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
Fix pylint warning (anomalous backslash) in summarize pb file tool by attaching "r" prefix
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
Fix pylint warning in tflitefile_tool
- "dummy_" prefix for unused variable
- staticmethod keyword for static method
- Use sharp for comment instead of triple quote
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
Move externals/lcov-to-cobertura-xml directory to tools/
Remove external tool dependency in gen-coverage-report command
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
- Change CMAKE_SOURCE_DIR/externals to NNFW_EXTERNALS_DIR
- Remove some target_include_directories using CMAKE_SOURCE_DIR: because of linked libraries already include with PUBLIC
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
This patch adds acl cl and neon TransposeConv kernel test sets.
It also tests CLDeconvolutionLayerEx.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
* [kbenchmark] Update summary view of html file
This patch generates a summary view of html file.
This will help you to see at a glance which graph shows
which kernel performs well in the current layer.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Change the location of the html_report_template.g.h++ that needs copy to cmake/packages/Nonius directory
|
|
This patch separates the result files if it is not html reporter type.
Becuase other reporters store only one test result in one file.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
This option allows to run benchmark whose name matches the regex.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
This patch loads operation informations from config file.
And it executes kernel benchmark test using the operation info.
The result is stored by default in text file.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
This patch parses the given configuration file.
Each layer is tested in a given set of kernel benchmark tests.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
kernels (#5346)
This patch loads kernel benchmark library using dynamic loader.
It also adds the draft test conv kernel for armcl and armne.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
This patch adds argument parsers for kbenchmark tool.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
This patch creates kbenchmark directory.
It is an initial commit for kbenchmark.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
This patch fixes the depthwise typo in config_saver
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
file (#5145)
* [tflitefile_tool] Add config option for benchmark tool
This patch adds the `-c` and `--config` options.
This option will print the configuration information of each operator.
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Save configuration file
This patch allows to save the configuration info about model
Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
|
|
Introduce build option for tflite accuracy tool and set off as default
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
* Related: #4405
The batch execution tool can be used to run experiments. It reads a neural network model from a file and a series of input images from a directory, runs each image through the network, and collect
statistics, such as execution time and accuracy.
Signed-off-by: Saulo A. Moraes <s.moraes@samsung.com>
* Remove boost_ext reference
Build script cleanup, remove unnecessary reference to boost_ext.
Signed-off-by: Saulo A. Moraes <s.moraes@samsung.com>
* Related: #4405
Code review fixes and tool rename from batch_run to tflite_accuracy.
Signed-off-by: Saulo A. Moraes <s.moraes@samsung.com>
|
|
* Add printing info for filled memory in model_parser
Add printing info for filled memory such as weight in model_parser
Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* fix failed format-check
|
|
* [Tools] Convert pb file to pbtxt file
This tool converts frozen pb file in tensorflow to pbtxt text file.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* remove common.py
* remove underbar from parameter
|
|
Check format all c and c++ files as default
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
This commit simplifies "contrib/CMakeLists.txt" and
"tools/CMakeLists.txt" using "add_subdirectories" function.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
This commit introduces BUILD_TOOLS option and partially removes the
the occurence of OBS_BUILD in CMakeLists.txt by using this BUILD_TOOLS
option.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
* Modified for Tensorflow 1.12
Fixed error while converting pb to tflite by applying changes in Tensorflow 1.12.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* Modified to a TF 1.12 term "Tensorflow Lite Converter"
|
|
Since we don't build tools/nnapi_quickcheck, it's far behind from
current state. So, this change updates all files of this dir to be able
to build and run them
Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
|
|
Update cmake for android and gbs build for revised directory structure
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|
|
Move test-related codes in tools into tests
- nnapi_test
- tflite_run
- tflite_benchmark
- tflite_benchmark_model
Update cmake, root makefile, and spec file
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
|