opencv

Commit Graph

Author	SHA1	Message	Date
Dmitry Kurtaev	17dcf0e82d	ROIPooling layer	8 years ago
Dmitry Kurtaev	ef0650179b	Fix conv/deconv/fc layers FLOPS computation	8 years ago
Li Peng	59cbaca4d3	detection_output layer ocl implementation Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Li Peng	66feea6cac	region layer ocl implementation Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Li Peng	7707c9bfba	reorg layer ocl implementation Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Li Peng	85b1c4060c	support axis in concat layer ocl path Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Li Peng	07bec6bdcd	reshape layer ocl implementation Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Alexander Alekhin	d8a737b4b0	dnn: SSD performance test	8 years ago
Li Peng	7b7033ac60	permute layer ocl implementation Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Dmitry Kurtaev	bbbec300a6	nn.BatchNormalization and nn.Dropout layers from Torch	8 years ago
Wu Zhiwen	1f465a0ef9	dnn(ocl4dnn): fuseLayer() use umat_input/outputBlobs for OpenCL target Also, fix bug when use OPENCL target but no OpenCL runtime Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>	8 years ago
Li Peng	a47fbd2610	Add ocl accuracy test for a few dnn nets They are alexnet, mobilenet-ssd, resnet50, squeezeNet_v1_1, yolo and fast_neural_style. Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Dmitry Kurtaev	99ed085752	Update PriorBox layer	8 years ago
Alexander Alekhin	13f374660f	dnn(ocl4dnn): drop unused batch_size_ in pooling	8 years ago
Alexander Alekhin	e34b64c979	dnn(ocl4dnn): refactor pooling OpenCL calls	8 years ago
Li Peng	636d6368ee	use OutputArrayOfArrays in net forward interface It allows umat buffers used in net forward interface Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Wu, Zhiwen	04edc8fe3a	cleanup ocl4dnn spatial convolution kernels remove unused macros and half definition macros, also remove unused ocl::Queue Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Alexander Alekhin	b29893b938	dnn: autogenerated files	8 years ago
Alexander Alekhin	1c88a566e0	dnn: rename caffe protobuf package	8 years ago
Alexander Alekhin	9db5cbf9a4	dnn: sync output/internals blobs back	8 years ago
Alexander Alekhin	0f34628af7	dnn: drop OpenCL code path for DetectionOutputLayer getUMat()/getMat() calls are scope based. Results of these calls can't be stored somewhere for future usage.	8 years ago
Alexander Alekhin	f19f2bbcde	dnn: autogenerated files rename caffe.proto => opencv-caffe.proto	8 years ago
Alexander Alekhin	f6d927ef3b	dnn: avoid conflicts with original caffe.proto rename caffe.proto => opencv-caffe.proto	8 years ago
David Geldreich	f723cede2e	add loading TensorFlow/Caffe net from memory buffer add a corresponding test	8 years ago
Dmitry Kurtaev	6c5dd5cf6d	Replace caffe::NormalizedBBox to local structure	8 years ago
Wu Zhiwen	45d11dde57	dnn(ocl4dnn): add fusion support for Power activation and eltwise add Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>	8 years ago
Wu Zhiwen	394101d6ed	dnn(ocl4dnn): Fix relu fusion bug Incorrect type of negative_slope result in this bug. Also and OCL test for darknet to validate this patch. Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>	8 years ago
Jcrist99	0608227e10	Merge pull request #9698 from abratchik:parse.doxygen Support @deprecated tag in java wrappers (#9698)	8 years ago
Wu Zhiwen	88e6daa315	dnn(ocl4dnn): Fix wrong measurement for tuning time convolution kernel use default queue to run, so that ocl::Timer , to measure the kernel run time, should use the default queue too. Also remove useless parameter for convolve() Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>	8 years ago
Li Peng	55260a8d3c	reshape mat before doing computation in fc layer Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Hamdi Sahloul	06bda58a2c	DNN Torch - workaround when torch importer is disabled	8 years ago
Li Peng	8f99083726	Add new layer forward interface Add layer forward interface with InputArrayOfArrays and OutputArrayOfArrays parameters, it allows UMat buffer to be processed and transferred in the layers. Signed-off-by: Li Peng <peng.li@intel.com>	8 years ago
Alexander Alekhin	97181a90ba	dnn(ocl4dnn/conv): bailout on missing kernel configuration	8 years ago
Dmitry Kurtaev	20a2dc6ac5	Fix multiple inputs models from Caffe. Fixed Concat optimization.	8 years ago
Alexander Alekhin	bacc96f4e8	dnn(ocl): fix softmax global/local size consistency	8 years ago
Dmitry Kurtaev	14af2a0c0c	Fixed Halide's copy_to_device invocation	8 years ago
Dmitry Kurtaev	e1ebc4e991	Specify layer types for Caffe FP32->FP16 weights converter	8 years ago
Dmitry Kurtaev	03cefa7bfe	Set zero confidences in case of no detections	8 years ago
Dmitry Kurtaev	4b52b8df34	Layers for fast-neural-style models: https://github.com/jcjohnson/fast-neural-style	8 years ago
Vladislav Sovrasov	5bf39ceb5d	dnn: handle 4-channel images in blobFromImage (#9944 )	8 years ago
Alexander Alekhin	436a1f72a5	dnn: fix sporadic crashes in getUMat() Incorrect "total" buffer size calculated in StdMatAllocator::allocate() due wrong step values.	8 years ago
Vladislav Sovrasov	7e3e9144de	dnn: add an accuracy test for NMS	8 years ago
Vladislav Sovrasov	c704942b8a	dnn: add a documentation for NMS, fix missing experimantal namespace	8 years ago
Vladislav Sovrasov	acedb4a579	dnn: make NMS function public	8 years ago
Dmitry Kurtaev	a36ebaecdc	PReLU layer for multidimensional input	8 years ago
Dmitry Kurtaev	410d44d67d	Binary data for batch normalization test from Torch	8 years ago
Alexander Alekhin	185faf99bd	ocl: simplify ocl::Timer interface	8 years ago
Dmitry Kurtaev	b903ff8992	Ceil mode from experimental version of Caffe, https://github.com/BVLC/caffe/pull/3057	8 years ago
Dmitry Kurtaev	a3a446c197	Output blobs shapes initialization in case of identity permutation (NCHW->NCHW)	8 years ago
Wu Zhiwen	2d8f2c2aea	dnn(ocl4dnn): add fusion support ocl4dnn supports following fusion styles: Conv + [BN] + [Scale] + [ReLU/PReLU] Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>	8 years ago

1 2 3 4 5

222 Commits (a2811d93ddc97751a4b6eb37534366e78236517f)