- 12 7月, 2019 1 次提交
-
-
由 Lubov Batanina 提交于
* Support Conv3D on OCV backend * Add header * Add perf tests * Support pool3d * Enable Resnet34_kinetics on OCV backend * Add test * Fix conv * Optimize Conv2D
-
- 09 7月, 2019 4 次提交
-
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
由 Tomasz Gorochowik 提交于
-
由 Alexander Alekhin 提交于
-
- 08 7月, 2019 1 次提交
-
-
由 jxu 提交于
-
- 06 7月, 2019 2 次提交
-
-
由 Alexander Alekhin 提交于
OpenCV upstream stuff may reinterpret vector as column.
-
由 Alexander Alekhin 提交于
-
- 05 7月, 2019 4 次提交
-
-
由 Alexander Alekhin 提交于
-
由 Tomoaki Teshima 提交于
-
由 Alexander Alekhin 提交于
from CameraBridgeViewBase (common base with JavaCameraView)
-
由 Diego 提交于
Instancenorm onnx (#14858) * Onnx unsupported operation handling * instance norm implementation * Revert "Onnx unsupported operation handling" * instance norm layer test * onnx instancenorm layer
-
- 04 7月, 2019 9 次提交
-
-
由 Alexander Alekhin 提交于
-
由 Vitaly Tuzov 提交于
-
由 Alexander Alekhin 提交于
-
由 Diego 提交于
* onnx clip operation
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
- 03 7月, 2019 11 次提交
-
-
由 Alexander Alekhin 提交于
-
由 gal0is 提交于
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
由 Rafa Gomez-Jordana 提交于
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
由 arnaudbrejeon 提交于
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
- 02 7月, 2019 6 次提交
-
-
由 Tomoaki Teshima 提交于
-
由 Alexander Alekhin 提交于
-
由 armenpoghosov 提交于
Merge pull request #14828 from armenpoghosov:parmen_RANSACPointSetRegistrator_getSubset_disaster_cleanup Parmen ransac point set registrator get subset disaster cleanup (#14828)
-
由 Alexander Alekhin 提交于
-
由 Alexander Alekhin 提交于
-
由 Vitaly Tuzov 提交于
* Avoid using v_signmask universal intrinsic and mark it as deprecated * Renamed v_find_negative to v_scan_forward
-
- 01 7月, 2019 2 次提交
-
-
由 Alexander Alekhin 提交于
-
由 StefanBruens 提交于
Crosscorr cleanup (#14936) * Simplify code for convolution destination type/size For the 2d filter code, destination size equals source size, and the crossCorr function even (re-)creates the output matrix with the given size. The number of channels also have to match. The destination type() is the one used to create the output matrix, so we can use its type() here. This is a preparatory patch. Signed-off-by: NStefan Brüns <stefan.bruens@rwth-aachen.de> * Remove redundant destination size and type parameters from crossCorr All calling sites of crossCorr already use (..., mat, mat.size(), mat.type(), ...), so the parameters are redundant. Signed-off-by: NStefan Brüns <stefan.bruens@rwth-aachen.de>
-