Commit Graph

608 Commits

Author SHA1 Message Date
Vladislav Vinogradov
e7502e7641 implemented gpu::gemm via CUBLAS 2011-10-19 13:29:54 +00:00
Vladislav Vinogradov
90ff3dd990 added cublasSafeCall 2011-10-19 11:49:44 +00:00
Vladislav Vinogradov
40ee754e28 added WITH_CUFFT and WITH_CUBLAS flags to cmake scripts
fixed gpu module error reporting
added asynchronous version of some functions
2011-10-19 09:53:22 +00:00
Vladislav Vinogradov
b0536279eb added wrappers for BroxOpticalFlow and interpolateFrames 2011-10-17 13:12:39 +00:00
Vladislav Vinogradov
87f3451ec6 fixed warnings 2011-10-17 06:44:40 +00:00
Alexey Spizhevoy
8cebb0982b Updated optimal DFT size estimation in gpu::convolve() 2011-10-14 09:42:25 +00:00
Anatoly Baksheev
7076dfd7d6 gpu module: refactored devmem2d.hpp (atomic bomb) 2011-10-13 15:14:04 +00:00
Alexey Spizhevoy
916703c6e5 Updated optimal block size estimation in gpu::convolve() 2011-10-13 13:02:41 +00:00
Vladislav Vinogradov
631d4b483a minor fix 2011-10-12 11:36:10 +00:00
Vladislav Vinogradov
8f108b4e7e bug fix 2011-10-12 11:01:11 +00:00
Vladislav Vinogradov
d3c4e90760 new optimized implementation of BruteForceMatcher_GPU (~2-3x faster) 2011-10-12 10:23:03 +00:00
Vadim Pisarevsky
b74116e694 unified norm computing; added generalized Hamming distance 2011-10-11 15:13:53 +00:00
Vladislav Vinogradov
f38596b783 implemented brute force convolve for small kernel sizes 2011-10-10 11:58:47 +00:00
Anatoly Baksheev
ee768d4605 fixed bug in ptr in optflow.cu 2011-10-10 09:37:08 +00:00
Vladislav Vinogradov
ed749c4bfe added missing arithm operations to gpu module 2011-10-10 08:19:11 +00:00
Anatoly Baksheev
f444f9b43e optflow gpu compilation fix under vs2010 2011-10-04 17:37:05 +00:00
Vladislav Vinogradov
d6d7ac9cee fixed tests for BruteForceMatcher_GPU::radiusMatch 2011-10-04 10:03:52 +00:00
Alexey Spizhevoy
8a799aa89a Updated optimal block size estimation for the convolve() function 2011-10-03 14:05:52 +00:00
Vadim Pisarevsky
60ebe2003f fixed multiple warnings on Windows. fixed bug #1368 2011-10-03 11:00:28 +00:00
Anatoly Baksheev
923f771cfc warnings
optical flow gpu cosmetics
2011-10-03 09:26:00 +00:00
Alexey Spizhevoy
dce50b67fc Fixed support of translation in the GPU-based plane warper 2011-10-03 07:42:16 +00:00
Anatoly Baksheev
0fc8fc77c0 eliminated shread_ptr dependency from optical flow gpu. It caused compilation errors. 2011-09-30 11:27:30 +00:00
Anatoly Baksheev
b9ea3ef741 compilation under ubuntu 2011-09-30 09:02:03 +00:00
Anton Obukhov
42c7aece36 [+] Added Brox optical flow (implementation courtesy of Michael Smirnov) 2011-09-29 14:46:39 +00:00
Vladislav Vinogradov
4d3b1a4a02 fixed build for compute capability < 2.0 2011-09-28 16:24:51 +00:00
Vladislav Vinogradov
f536dfa439 fixed build under linux 2011-09-28 12:08:17 +00:00
Vladislav Vinogradov
9da6d78989 optimized gpu filters, added buffered version for different filters 2011-09-28 11:52:26 +00:00
Vladislav Vinogradov
ea4f65b570 implemented optimized version of bf_radius_match for train collection 2011-09-27 06:45:17 +00:00
Vladislav Vinogradov
b119833ad1 implemented optimized version of gpu::bf_radius_match 2011-09-26 11:18:30 +00:00
Vladislav Vinogradov
67a9b79433 added performance tests for gpu::reduce 2011-09-26 08:14:31 +00:00
Alexey Spizhevoy
48dec9c03a Fixed GPU version of multi-band blending in stitching module 2011-09-24 05:58:29 +00:00
Vladislav Vinogradov
8b23c79294 implemented gpu::reduce 2011-09-22 07:08:26 +00:00
Vladislav Vinogradov
0aaaad1ea8 implemented gpu::addWeighted 2011-09-21 08:58:54 +00:00
Vladislav Vinogradov
64119dd924 implemented gpu::copyMakeBorder for all border modes 2011-09-21 07:02:45 +00:00
Vladislav Vinogradov
5ed65979c1 fixed bug in gpu::HOGDescriptor::getBuffer (ticket #1379) 2011-09-20 06:38:40 +00:00
Alexey Spizhevoy
23636433d7 Updated bundle adjustment in stitching module: 1) it minimizes reprojection error now, 2) it minimizes error over focal, aspect, p.p.x, p.p.y parameters. Refactored and updated warpers. 2011-09-16 12:25:23 +00:00
Anatoly Baksheev
ffc5a7b809 minor 2011-09-15 05:51:41 +00:00
Vladislav Vinogradov
be8e31f14d minor gpu module refactoring: split big .cu files, disabled unnecessary template instantiation 2011-09-14 06:23:46 +00:00
Alexey Spizhevoy
a72da12c80 Added fix for 0 found features in stitching matcher 2011-09-13 14:15:18 +00:00
Vladislav Vinogradov
4b46e35287 minor 2011-09-12 15:15:02 +00:00
Vladislav Vinogradov
dac9f69ba4 fixed bug in SURF_GPU (memory access error) 2011-09-12 15:14:02 +00:00
Alexey Spizhevoy
485e71bcc2 Bug in multiply was fixed (by Vlad Vinogradov) 2011-09-12 14:58:56 +00:00
Vladislav Vinogradov
29b9720aab added check if src.size() == dst.size() to gpu::resize 2011-09-12 10:23:20 +00:00
Vladislav Vinogradov
b2079d6de1 implemented gpu::resize for all types 2011-09-12 10:13:14 +00:00
Vladislav Vinogradov
acac27d8fe optimized gpu::multiply 2011-09-12 08:45:56 +00:00
Vladislav Vinogradov
6763bd6d01 added padded performance tests for gpu module 2011-09-12 07:48:09 +00:00
Alexey Spizhevoy
fd5b0c1f18 Reverted some unnecessary changes in GPU module 2011-09-10 12:30:28 +00:00
Alexey Spizhevoy
a7c6b84390 Added TODOs into GPU module 2011-09-10 12:28:03 +00:00
Alexey Spizhevoy
903f835d9f added support of 8UC4*32FC1 multiply into GPU module 2011-09-10 11:56:55 +00:00
Andrey Kamaev
6cb1036e04 Perf tests: method ::perf::TestBase::getDataPath made public static; added base CUDA detection into run.py script 2011-09-08 11:01:45 +00:00