Vladislav Vinogradov
|
1c1a61dd37
|
added __forceinline__ to device functions
fixed BFM warning ("cannot tell what pointer points to")
|
14 years ago |
Anatoly Baksheev
|
8f4c7db3f6
|
~40 warnings under VS2008
HAVE_CONFIG_H -> HAVE_CVCONFIG_H
|
14 years ago |
Anatoly Baksheev
|
dc8572dc7b
|
data_mov_utils.hpp
|
14 years ago |
Vladislav Vinogradov
|
26dd71d981
|
fixed gpu::cvtColor according #5324 changes
|
14 years ago |
Vladislav Vinogradov
|
f906c9b259
|
added resetDevice function, removed MultiGpuManager
|
14 years ago |
Vladislav Vinogradov
|
926a6bba00
|
modified according to CUDA 4.0 API updates
|
14 years ago |
Vladislav Vinogradov
|
331062360d
|
fixed bug in SURF_GPU (compute descriptors, tid < 25)
|
14 years ago |
Vladislav Vinogradov
|
6259520aa1
|
fixed bug in SURF_GPU (reduce_sum25)
|
14 years ago |
Vladislav Vinogradov
|
15677d6d28
|
minor optimization of SURF_GPU (orientation calculation, changed block size to 32x4)
|
14 years ago |
Vladislav Vinogradov
|
7fbcc1ec05
|
minor SURF_GPU optimization (descriptor calculation, change block size to 6x6)
|
14 years ago |
Vladislav Vinogradov
|
ae6d5252ab
|
minor fix
|
14 years ago |
Vladislav Vinogradov
|
0b19f915be
|
minor optimization of SURF_GPU (reduce memory transfers, use structure of arrays instead of array of structures)
|
14 years ago |
Vadim Pisarevsky
|
23768b1826
|
replaced #include <some_opencv_hdr> with #include "some_opencv_hdr" (ticket #719)
|
14 years ago |
Alexey Spizhevoy
|
7d350280c0
|
compilation under mac
|
14 years ago |
Vladislav Vinogradov
|
34e2c78cec
|
minor fix
|
14 years ago |
Vladislav Vinogradov
|
f3b45af876
|
GpuMat::setTo optimization (call cudaMemcpy2D if possible)
|
14 years ago |
Vladislav Vinogradov
|
f11efdced3
|
added support of Hamming distance to BruteForceMatcher_GPU
|
14 years ago |
Vladislav Vinogradov
|
6a03be2632
|
added lightweight class DeviceBuffer to matrix_reductions.cpp
|
14 years ago |
Vladislav Vinogradov
|
1c9f4e7ca2
|
fixed gpu::meanStdDev and gpu::norm under CUDA 4.0
fixed compilation under Win64
|
14 years ago |
Vladislav Vinogradov
|
58e26313dd
|
fixed bug in cv::LUT (multi-channel source array and single-channel table)
added missing cudaSafeCall
|
14 years ago |
Anatoly Baksheev
|
1c18e5fef9
|
fixed ~300 warnings under windows (had to hack gtest a bit)
|
14 years ago |
Vladislav Vinogradov
|
6200f388dd
|
fixed bug in BruteForceMatcher_GPU::knnMatch (allDist buffer reuse)
|
14 years ago |
Vladislav Vinogradov
|
c21a783646
|
added aligned memory allocation to CudaMem (if allocation type is ZERO_COPY)
fixed bugs in gpu::cvtColor
|
14 years ago |
Anton Obukhov
|
b28c33f5dc
|
[~] Added nppStSetActiveCUDAstream and nppStGetActiveCUDAstream to the export table
|
14 years ago |
Alexey Spizhevoy
|
c9894f9655
|
fixed compile-time bug under Ubuntu
|
14 years ago |
Anton Obukhov
|
0c325cace3
|
[~] Minor refactoring, clean-up
[+] Added 128-bit transpose
|
14 years ago |
Alexey Spizhevoy
|
1a02877ab7
|
fixed gpu::downsample and gpu::blendLinear compite-time bugs under Ubuntu
|
14 years ago |
Alexey Spizhevoy
|
97282d8ff8
|
added downsample function into gpu module, refactored it a little bit, added guard for CUDA related include in cascadeclassifier_nvidia_api.cpp
|
14 years ago |
Alexey Spizhevoy
|
6cec5ff552
|
added blendLinear into gpu module
|
14 years ago |
Anton Obukhov
|
07d19c2c6f
|
[~] Refactored, cleaned up, and consolidated the code of GPU examples (cascadeclassifier and cascadeclassifier_nvidia_api)
|
14 years ago |
Anton Obukhov
|
58476b64a6
|
[*] Fixed #974 ("GPU CascadeClassifier fails with some training files"): Moved IsNodeLeaf bit from NodeDescriptor to FeatureDescriptor for both left and right nodes, therefore from now on max number of rects in a feature is 31
|
14 years ago |
Anatoly Baksheev
|
a69de4bf26
|
minor bug in hog (unbind texture)
|
14 years ago |
Anatoly Baksheev
|
5f56b27616
|
added ROI support for HOG_GPU
|
14 years ago |
Anatoly Baksheev
|
8b8ad17f4a
|
fixed extra memory allocations.
|
14 years ago |
Vladislav Vinogradov
|
57195e9627
|
fixed SURF_GPU bug (features count > max dimension of grid)
minor gpu docs fixes
|
14 years ago |
Alexey Spizhevoy
|
ca1584dd1f
|
fixed gpu::graphcut preconditions
|
14 years ago |
Vladislav Vinogradov
|
9342c4b076
|
added upright parameter to SURF_GPU
|
14 years ago |
Vladislav Vinogradov
|
fcff126086
|
fixed some warnings in surf.cu
|
14 years ago |
Vladislav Vinogradov
|
ca803e12fd
|
fixed mask calculation in SURF_GPU
|
14 years ago |
Vladislav Vinogradov
|
d05c6b8b68
|
fixed surf.cu compilation on CC 2.0
|
14 years ago |
Anatoly Baksheev
|
9214173c2c
|
some includes moved to precomp.hpp for gpu module
|
14 years ago |
Vladislav Vinogradov
|
58f6919795
|
made GPU version of SURF more consistent with CPU one
|
14 years ago |
Alexey Spizhevoy
|
23416e3db5
|
make GPU version of solvePnPRansac more consistent with CPU one
|
14 years ago |
Alexey Spizhevoy
|
1d62fddd31
|
updated solvePnpRansac performance test
|
14 years ago |
Jose Luis Blanco
|
673061fb17
|
Fixed build errors in MSVC when building without CUDA.
|
14 years ago |
Alexey Spizhevoy
|
4e6572acd9
|
removed test whether z is negative in gpu::solvePnpRansac (there is no need in this for tests passing)
|
14 years ago |
Alexey Spizhevoy
|
74c398e6b7
|
refactored gpu::solvePnpRansac a bit
|
14 years ago |
Alexey Spizhevoy
|
60e33921e3
|
added performance sample for solvePnpRansac + refactoring
|
14 years ago |
Alexey Spizhevoy
|
5e85566477
|
added distortion coefs support into gpu::solvePnpRansac
|
14 years ago |
Alexey Spizhevoy
|
eb8c0b8b4b
|
parallelized hypotheses evaluation cycle in gpu::solvePnpRansac
|
14 years ago |