* dnn: LSTM optimisation
This uses the AVX-optimised fastGEMM1T for matrix multiplications where available, instead of the standard cv::gemm.
fastGEMM1T is already used by the fully-connected layer. This commit involves two minor modifications:
- Use unaligned access. I don't believe this involves any performance hit in on modern CPUs (Nehalem and Bulldozer onwards) in the case where the address is actually aligned.
- Allow for weight matrices where the number of columns is not a multiple of 8.
I have not enabled AVX-512 as I don't have an AVX-512 CPU to test on.
* Fix warning about initialisation order
* Remove C++11 syntax
* Fix build when AVX(2) is not available
In this case the CV_TRY_X macros are defined to 0, rather than being undefined.
* Minor changes as requested:
- Don't check hardware support for AVX(2) when dispatch is disabled for these
- Add braces
* Fix out-of-bounds access in fully connected layer
The old tail handling in fastGEMM1T implicitly rounded vecsize up to the next multiple of 8, and the fully connected layer implements padding up to the next multiple of 8 to cope with this. The new tail handling does not round the vecsize upwards like this but it does require that the vecsize is at least 8. To adapt to the new tail handling, the fully connected layer now rounds vecsize itself at the same time as adding the padding(which makes more sense anyway).
This also means that the fully connected layer always passes a vecsize of at least 8 to fastGEMM1T, which fixes the out-of-bounds access problems.
* Improve tail mask handling
- Use static array for generating tail masks (as requested)
- Apply tail mask to the weights as well as the input vectors to prevent spurious propagation of NaNs/Infs
* Revert whitespace change
* Improve readability of conditions for using AVX
* dnn(lstm): minor coding style changes, replaced left aligned load
[G-API] Fix issue of getting 1D Mat out of RMat::View
* Fix issue of getting 1D Mat out of RMat::View
- added test
- fixed for standalone too (removed Assert(dims.empty()))
* Fixed asVeiw() function for standalone
* Put more detailed comment
Add capacity to Videocapture to return the extraData from FFmpeg when required
* Update rawMode to append any extra data recieved during the initial negotiation of an RTSP stream or during the parsing of an MPEG4 file header.
For h264[5] RTSP streams this ensures the parameter sets if available are always returned on the first call to grab()/read() and has two purposes:
1) To ensure the parameter sets are available even if they are not transmitted in band. This is common for axis ip camera's.
2) To allow callers of VideoCapture::grab()[read()] to write to split the raw stream over multiple files by appending the parameter sets to the begining of any new files.
For (1) there is no alternative, for (2) if the parameter sets were provided in band it would be possible to parse the raw bit stream and search for the parameter sets however that would be a lot of work when that information is already provided by FFMPEG.
For MPEG4 files this information is only suplied in the header and is required for decoding.
Two properties are also required to enable the raw encoded bitstream to be written to multiple files, these are;
1) an indicator as to whether the last frame was a key frame or not - each new file needs to start at a key frame to avoid storing unusable frame diffs,
2) the length in bytes of the paramater sets contained in the last frame - required to split the paramater sets from the frame without having to parse the stream. Any call to VideoCapture::get(CAP_PROP_LF_PARAM_SET_LEN) returning a number greater than zero indicates the presense of a parameter set at the begining of the raw bitstream.
* Adjust test data to account for extraData
* Address warning.
* Change added property names and remove paramater set start code check.
* Output extra data on calls to retrieve instead of appending to the first packet.
* Reverted old test case and added new one to evaluate new functionality.
* Add missing definition.
* Remove flag from legacy api.
Add property to determine if returning extra data is supported.
Always allow extra data to be returned on calls to cap.retrieve()
Update test case.
* Update condition which indicates CAP_PROP_CODEC_EXTRADATA_INDEX is not supported in test case.
* Include compatibility for windows dll if not updated.
Enforce existing return status convention.
* Fix return error and missing test constraints.
[GSoC] OpenCV.js: Accelerate OpenCV.js DNN via WebNN
* Add WebNN backend for OpenCV DNN Module
Update dnn.cpp
Update dnn.cpp
Update dnn.cpp
Update dnn.cpp
Add WebNN head files into OpenCV 3rd partiy files
Create webnn.hpp
update cmake
Complete README and add OpenCVDetectWebNN.cmake file
add webnn.cpp
Modify webnn.cpp
Can successfully compile the codes for creating a MLContext
Update webnn.cpp
Update README.md
Update README.md
Update README.md
Update README.md
Update cmake files and
update README.md
Update OpenCVDetectWebNN.cmake and README.md
Update OpenCVDetectWebNN.cmake
Fix OpenCVDetectWebNN.cmake and update README.md
Add source webnn_cpp.cpp and libary libwebnn_proc.so
Update dnn.cpp
Update dnn.cpp
Update dnn.cpp
Update dnn.cpp
update dnn.cpp
update op_webnn
update op_webnn
Update op_webnn.hpp
update op_webnn.cpp & hpp
Update op_webnn.hpp
Update op_webnn
update the skeleton
Update op_webnn.cpp
Update op_webnn
Update op_webnn.cpp
Update op_webnn.cpp
Update op_webnn.hpp
update op_webnn
update op_webnn
Solved the problems of released variables.
Fixed the bugs in op_webnn.cpp
Implement op_webnn
Implement Relu by WebNN API
Update dnn.cpp for better test
Update elementwise_layers.cpp
Implement ReLU6
Update elementwise_layers.cpp
Implement SoftMax using WebNN API
Implement Reshape by WebNN API
Implement PermuteLayer by WebNN API
Implement PoolingLayer using WebNN API
Update pooling_layer.cpp
Update pooling_layer.cpp
Update pooling_layer.cpp
Update pooling_layer.cpp
Update pooling_layer.cpp
Update pooling_layer.cpp
Implement poolingLayer by WebNN API and add more detailed logs
Update dnn.cpp
Update dnn.cpp
Remove redundant codes and add more logs for poolingLayer
Add more logs in the pooling layer implementation
Fix the indent issue and resolve the compiling issue
Fix the build problems
Fix the build issue
FIx the build issue
Update dnn.cpp
Update dnn.cpp
* Fix the build issue
* Implement BatchNorm Layer by WebNN API
* Update convolution_layer.cpp
This is a temporary file for Conv2d layer implementation
* Integrate some general functions into op_webnn.cpp&hpp
* Update const_layer.cpp
* Update convolution_layer.cpp
Still have some bugs that should be fixed.
* Update conv2d layer and fc layer
still have some problems to be fixed.
* update constLayer, conv layer, fc layer
There are still some bugs to be fixed.
* Fix the build issue
* Update concat_layer.cpp
Still have some bugs to be fixed.
* Update conv2d layer, fully connected layer and const layer
* Update convolution_layer.cpp
* Add OpenCV.js DNN module WebNN Backend (both using webnn-polyfill and electron)
* Delete bib19450.aux
* Add WebNN backend for OpenCV DNN Module
Update dnn.cpp
Update dnn.cpp
Update dnn.cpp
Update dnn.cpp
Add WebNN head files into OpenCV 3rd partiy files
Create webnn.hpp
update cmake
Complete README and add OpenCVDetectWebNN.cmake file
add webnn.cpp
Modify webnn.cpp
Can successfully compile the codes for creating a MLContext
Update webnn.cpp
Update README.md
Update README.md
Update README.md
Update README.md
Update cmake files and
update README.md
Update OpenCVDetectWebNN.cmake and README.md
Update OpenCVDetectWebNN.cmake
Fix OpenCVDetectWebNN.cmake and update README.md
Add source webnn_cpp.cpp and libary libwebnn_proc.so
Update dnn.cpp
Update dnn.cpp
Update dnn.cpp
Update dnn.cpp
update dnn.cpp
update op_webnn
update op_webnn
Update op_webnn.hpp
update op_webnn.cpp & hpp
Update op_webnn.hpp
Update op_webnn
update the skeleton
Update op_webnn.cpp
Update op_webnn
Update op_webnn.cpp
Update op_webnn.cpp
Update op_webnn.hpp
update op_webnn
update op_webnn
Solved the problems of released variables.
Fixed the bugs in op_webnn.cpp
Implement op_webnn
Implement Relu by WebNN API
Update dnn.cpp for better test
Update elementwise_layers.cpp
Implement ReLU6
Update elementwise_layers.cpp
Implement SoftMax using WebNN API
Implement Reshape by WebNN API
Implement PermuteLayer by WebNN API
Implement PoolingLayer using WebNN API
Update pooling_layer.cpp
Update pooling_layer.cpp
Update pooling_layer.cpp
Update pooling_layer.cpp
Update pooling_layer.cpp
Update pooling_layer.cpp
Implement poolingLayer by WebNN API and add more detailed logs
Update dnn.cpp
Update dnn.cpp
Remove redundant codes and add more logs for poolingLayer
Add more logs in the pooling layer implementation
Fix the indent issue and resolve the compiling issue
Fix the build problems
Fix the build issue
FIx the build issue
Update dnn.cpp
Update dnn.cpp
* Fix the build issue
* Implement BatchNorm Layer by WebNN API
* Update convolution_layer.cpp
This is a temporary file for Conv2d layer implementation
* Integrate some general functions into op_webnn.cpp&hpp
* Update const_layer.cpp
* Update convolution_layer.cpp
Still have some bugs that should be fixed.
* Update conv2d layer and fc layer
still have some problems to be fixed.
* update constLayer, conv layer, fc layer
There are still some bugs to be fixed.
* Update conv2d layer, fully connected layer and const layer
* Update convolution_layer.cpp
* Add OpenCV.js DNN module WebNN Backend (both using webnn-polyfill and electron)
* Update dnn.cpp
* Fix Error in dnn.cpp
* Resolve duplication in conditions in convolution_layer.cpp
* Fixed the issues in the comments
* Fix building issue
* Update tutorial
* Fixed comments
* Address the comments
* Update CMakeLists.txt
* Offer more accurate perf test on native
* Add better perf tests for both native and web
* Modify per tests for better results
* Use more latest version of Electron
* Support latest WebNN Clamp op
* Add definition of HAVE_WEBNN macro
* Support group convolution
* Implement Scale_layer using WebNN
* Add Softmax option for native classification example
* Fix comments
* Fix comments
In case of very small negative h (e.g. -1e-40), with the current implementation,
you will go through the first condition and end up with h = 6.f, and will miss
the second condition.
issue #20617 addresses lack of warnings on
seamlessClone() function when src is None.
This commit adds source check using CV_Assert
therefore debugging would be easier.
Signed-off-by: nickjackolson <metedurlu@gmail.com>
Add a warning message using CV_LOG__WARNING().
This way api behaviour is preserved. Outputs are
the same but user gets an extra warning in case
fopen() fails to access image file for some reason.
This would help new users and also debugging
complex apps which use imread()
Signed-off-by: nickjackolson <metedurlu@gmail.com>
G-API: Removing G-API test code that is a reflection of ts module
* gapi: don't hijack testing infrastructure
* Removed initDataPath functionality (ts module exists)
* Removed false for ocv_extra data from findDataFile
Co-authored-by: Alexander Alekhin <alexander.a.alekhin@gmail.com>
QR code (encoding process)
* add qrcode encoder
* qr encoder fixes
* qr encoder: fix api and realization
* fixed qr encoder, added eci and kanji modes
* trigger CI
* qr encoder constructor fixes
Co-authored-by: APrigarina <ann73617@gmail.com>
[G-API] Fix bugs in GIEBackend
* Remove inputs/outputs map from IEUnit
* Add test
* Add NV12 test
* Reorganize setBlob function
* Check that backend don't overwrite blob precision
* Stop setting config to global IE::Core
* Replace mutable to const_cast
* Update modules/gapi/test/infer/gapi_infer_ie_test.cpp
* Update modules/gapi/test/infer/gapi_infer_ie_test.cpp
* Make blob parameter as const ref
* Cosmetic fixes
* Fix failed test on inferROI
* Removed double ref for ii
* Disable tests
* Skip tests if device not available
* Use Sync prim under shared_ptr to avoid issue on MAC
* Apply WA for IE::Core
* Apply WA for MAC build
* Try to apply another WA
* Not release IE::Core for apple
* Put comment
* Support PreprocInfo for
* InferROI
* InferList
* InferList2
* Remove empty line
* Fix alignment
Co-authored-by: Maxim Pashchenkov <maxim.pashchenkov@intel.com>
Fix the following build failure with gcc 4.8:
In file included from /home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/videoio/src/cap_ffmpeg_impl.hpp💯0,
from /home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/videoio/src/cap_ffmpeg.cpp:50:
/home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/videoio/src/cap_ffmpeg_hw.hpp: In constructor 'HWAccelIterator::HWAccelIterator(cv::VideoAccelerationType, bool, AVDictionary*)':
/home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/videoio/src/cap_ffmpeg_hw.hpp:939:23: error: use of deleted function 'std::basic_istringstream<char>& std::basic_istringstream<char>::operator=(const std::basic_istringstream<char>&)'
s_stream_ = std::istringstream(accel_list);
^
In file included from /home/buildroot/autobuild/instance-3/output-1/host/opt/ext-toolchain/arm-none-linux-gnueabi/include/c++/4.8.3/complex:45:0,
from /home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/core/include/opencv2/core/cvstd.inl.hpp:47,
from /home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/core/include/opencv2/core.hpp:3306,
from /home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/videoio/include/opencv2/videoio.hpp:46,
from /home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/videoio/src/precomp.hpp:57,
from /home/buildroot/autobuild/instance-3/output-1/build/opencv4-4.5.4/modules/videoio/src/cap_ffmpeg.cpp:42:
/home/buildroot/autobuild/instance-3/output-1/host/opt/ext-toolchain/arm-none-linux-gnueabi/include/c++/4.8.3/sstream:272:11: note: 'std::basic_istringstream<char>& std::basic_istringstream<char>::operator=(const std::basic_istringstream<char>&)' is implicitly deleted because the default definition would be ill-formed:
class basic_istringstream : public basic_istream<_CharT, _Traits>
^
/home/buildroot/autobuild/instance-3/output-1/host/opt/ext-toolchain/arm-none-linux-gnueabi/include/c++/4.8.3/sstream:272:11: error: use of deleted function 'std::basic_istream<char>& std::basic_istream<char>::operator=(const std::basic_istream<char>&)'
Fixes:
- http://autobuild.buildroot.org/results/60f8846b435dafda0ced412d59ffe15bdff0810d
Signed-off-by: Fabrice Fontaine <fontaine.fabrice@gmail.com>
* dnn(ocl4dnn): fix LRN layer accuracy problems
- FP16 intermediate computation is not accurate and may provide NaN values
* dnn(test): update tolerance for FP16
1. Code uses PPC_FEATURE_HAS_VSX, but it's not checked similarly to
PPC_FEATURE2_ARCH_3_00 and PPC_FEATURE2_ARCH_3_00 for availability. FreeBSD has
those macros in machine/cpu.h, but I went with the way chosen for
PPC_FEATURE2_ARCH_3_00 and PPC_FEATURE2_ARCH_3_00. Other than that, FreeBSD also
has sys/auxv.h and that's where elf_aux_info() is defined.
2. getauxval() is actually Linux-only, but code checked for __unix__. It won't
work on all UNIX, so change it back to __linux__. Add another code variant
strictly for FreeBSD.
3. Update comment. This commit adds code for FreeBSD, but recently there
appeared support for powerpc64 in OpenBSD.
G-API: oneVPL - Performance: Add async decode pipeline & add cached pool
* Add async decode pipeline & intro cached pool
* Fix performacne test with checking OPENCV_EXTRA
* Add sip perf test with no VPL
* Fix misprint
* Remove empty line..
* Apply some comments
* Apply some comments
* Make perf test fail if no OPENCV_TEST_DATA_PATH declared
Smirnov Egor
Alexander Alekhin
Andrew Ryrie
utibenkei
Anna Khakimova
Supernovae
yuki takehara
Orest Chura
Maxim Pashchenkov
Christian Clauss
cudawarped
Hanxi Guo
ShuangLiu1992
Sergey Ivanov
zcx
Vincent Rabaud
nickjackolson
Anatoliy Talamanov
Qiushi Zheng
Trutnev Aleksei
Fabrice Fontaine
tv3141
SegaraRai
Piotr Kubaj