- 09 Jan, 2018 1 commit
-
-
klchang authored
-
- 14 Dec, 2017 1 commit
-
-
Vitaly Tuzov authored
-
- 11 Dec, 2017 1 commit
-
-
Alexander Alekhin authored
-
- 05 Dec, 2017 1 commit
-
-
berak authored
-
- 02 Dec, 2017 1 commit
-
-
berak authored
-
- 29 Nov, 2017 1 commit
-
-
Maksim Shabunin authored
-
- 17 Nov, 2017 1 commit
-
-
klchang authored
-
- 25 Oct, 2017 1 commit
-
-
berak authored
-
- 23 Oct, 2017 11 commits
-
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
Vladislav Sovrasov authored
-
- 18 Oct, 2017 1 commit
-
-
Alexander Alekhin authored
-
- 10 Oct, 2017 2 commits
-
-
Alexander Alekhin authored
-
Vladislav Sovrasov authored
* kcf use float data type rather than double. In our practice, float is good enough and could get better performance. With this patch, one of my benchmark could get about 20% performance gain. Signed-off-by:
Zhigang Gong <zhigang.gong@intel.com> * Offload transpose matrix multiplication to ocl. The matrix multiplication in updateProjectMatrix is one of the hotspot. And because of the matrix shape is special, say the m is very short but the n is very large. The GEMM implementation in neither the clBLAS nor the in trunk implementation are very inefficient, I implement an standalone transpose matrix mulplication kernel here. It can get about 10% performance gain on Intel desktop platform or 20% performance gain on a braswell platform. And in the mean time, the CPU utilization will be lower. Signed-off-by:
Zhigang Gong <zhigang.gong@intel.com> * Add verification code for kcf ocl transpose mm kernel. Signed-off-by:
Zhigang Gong <zhigang.gong@linux.intel.com> * tracking: show FPS in traker sample * tracking: fix MSVC warnings in KCF * tracking: move OCL kernel initialization to constructor in KCF
-
- 28 Sep, 2017 1 commit
-
-
Alexander Alekhin authored
-
- 26 Sep, 2017 1 commit
-
-
Nuzhny007 authored
-
- 20 Sep, 2017 1 commit
-
-
jrobble authored
-
- 18 Sep, 2017 2 commits
-
-
klchang authored
-
Dmitry Kurtaev authored
-
- 05 Sep, 2017 2 commits
-
-
Fernando Martin authored
Updated the lambda coefficient to the one suggested in the original paper (http://www.robots.ox.ac.uk/~joao/publications/henriques_tpami2015.pdf, page 11, Table 2) which works (for me) better then the previous default one.
-
Fernando Martin authored
-
- 23 Aug, 2017 1 commit
-
-
f3rm4rf3r authored
-
- 02 Aug, 2017 1 commit
-
-
Vladislav Sovrasov authored
-
- 30 Jul, 2017 1 commit
-
-
berak authored
-
- 16 Jun, 2017 1 commit
-
-
Aleksandr Rybnikov authored
-
- 23 May, 2017 1 commit
-
-
Vladislav Sovrasov authored
-
- 25 Apr, 2017 1 commit
-
-
Vadim Pisarevsky authored
* the first commit in the merged dnn: convert some public API from Blob's to Mat's * temporarily or permantently removed OpenCL optimizations, which are not always stable nor usually very efficient; we'll likely use Halide instead * got rid of Blob and BlobShape completely; use cv::Mat and std::vector<int> instead * fixed a few compile errors * got rid of separate .hpp files with layer declarations; instead, put everything into the respective .cpp files * normalized all the layers' constructors; we concentrate on loading deep networks layers from files instead of constructing them from scratch, so we retained only SomeLayer::SomeLayer(const LayerParams& params); constructors * fixed sample compilation * suppress doxygen warnings * trying to fix python bindings generation for DNN module * temporarily disable python bindings while we refactor the module * fix win32/win64 compile errors; remove trailing whitespaces * fix win32/win64 compile errors; remove trailing whitespaces
-
- 24 Apr, 2017 1 commit
-
-
Vladislav Sovrasov authored
Use ROI selector in python samples
-
- 24 Mar, 2017 1 commit
-
-
Vladislav Sovrasov authored
-
- 20 Mar, 2017 1 commit
-
-
Alexander Alekhin authored
tldDetector.cpp:465:22: warning: declaration shadows a field of 'cv::tld::TLDDetector' [-Wshadow]
-
- 15 Mar, 2017 1 commit
-
-
Maksim Shabunin authored
- made some of dependencies explicit - removed dependencies to highgui and some other modules where possible - modified some samples to build without modules
-
- 07 Mar, 2017 1 commit
-
-
berak authored
-