opencv

Commit Graph

Author	SHA1	Message	Date
Liubov Batanina	97455f1593	Remove useless condition	5 years ago
Liubov Batanina	08ba63da02	Add global pool flags	5 years ago
ashishiva3@gmail.com	f29bc22005	Convolutional padding parsing modified	5 years ago
Julien	886220b9be	Merge pull request #16273 from JulienMaille:wrapper_available_target * add a wrapper for getAvailableTargets * add java wrapper on Target enum	5 years ago
Alexander Alekhin	55d54b56bf	dnn(onnx): handle unaligned access in ONNX importer	5 years ago
Julien Maille	a696348ec5	FIX: disable dnn cuda input_shortcut on _half for CC<5.3	5 years ago
Yashas Samaga B L	d85e67d3ec	Merge pull request #16063 from YashasSamaga:cuda4dnn-shortcut-unequal support eltwise sum with different number of input channels in CUDA backend * add shortcut primitive * add offsets in shortcut kernel * skip tests involving more than two inputs * remove redundant modulus operation * support multiple inputs * remove whole file indentation * skip acc in0 trunc test if weighted * use shortcut iff channels are unequal	5 years ago
Dmitry Kurtaev	8b9e8a805d	MVN support through nGraph	5 years ago
Alexander Alekhin	2638c5e9b7	dnn: dump layer's blobs on getMemoryShapes() error	5 years ago
Julien	ced3df73da	Fix: rsqrt(float) was improperly put in the ifdef for half	5 years ago
YashasSamaga	fd369a5004	fix and optimize ROIPooling	5 years ago
Dmitry Kurtaev	d92a883de1	Different way to reset Myriad device	5 years ago
Julien	4e2ef8c8f5	Merge pull request #16218 from JulienMaille:cuda-dnn-for-older-gpus Enable cuda4dnn on hardware without support for __half * Enable cuda4dnn on hardware without support for half (ie. compute capability < 5.3) Update CMakeLists.txt Lowered minimum CC to 3.0 * UPD: added ifdef on new copy kernel * added fp16 support detection at runtime * Clarified #if condition on atomicAdd definition * More explicit CMake error message	5 years ago
Dmitry Kurtaev	7c741f54fa	Wrap custom OpenCV layers to try-catch	5 years ago
Dmitry Kurtaev	0d896af8ec	Fix uninitialized value	5 years ago
Liubov Batanina	be86338a79	Enable acrossSpatial normalizeL2 on Myriad	5 years ago
Dmitry Kurtaev	c1c84d2fd1	ONNX graphs simplifier	5 years ago
Dmitry Kurtaev	8f1e36f7c1	Disable some tests for Myriad target of nGraph Add lightweight IE hardware targets checks nGraph: Concat with paddings Enable more nGraph tests Restore FP32->FP16 for GPU plugin of IE try to fix buildbot Use lightweight IE targets check only starts from R4	5 years ago
Liubov Batanina	9ed372b297	Update get memory shapes	5 years ago
Liubov Batanina	4625337179	Add docs reduce mean	5 years ago
Liubov Batanina	e9e3af0aaa	Add global pool by axis test	5 years ago
Liubov Batanina	a33d50084d	Add global_pooling_dim flags	5 years ago
Liubov Batanina	7eba3a7c96	Add pack description	5 years ago
Dmitry Kurtaev	f954f0830c	Sort text TensorFlow graphs	5 years ago
YashasSamaga	48eecafc89	simplify code to help MSVC 19.10 and lower	5 years ago
Dmitry Kurtaev	76cfa65d55	AddV2 from TensorFlow	5 years ago
YashasSamaga	01f97f150c	perfor fp conversions on GPU	5 years ago
YashasSamaga	17a35587e1	use optimized cuDNN path for conv + bias + relu	5 years ago
Liubov Batanina	752653c70b	Update global pooling	5 years ago
Brian Wignall	f9c514b391	Fix spelling typos backport commit `659ffaddb4`	5 years ago
Brian Wignall	659ffaddb4	Fix spelling typos	5 years ago
Liubov Batanina	cf477f7e9f	Fix global axis	5 years ago
Liubov Batanina	543e0302d3	Support global pooling by axis	5 years ago
YashasSamaga	16bc505d26	improve reduction logic and add fast transpose kernel	5 years ago
Liubov Batanina	6e33769e56	Add human parsing demo	5 years ago
Yashas Samaga B L	1fac1421e5	Merge pull request #16010 from YashasSamaga:cuda4dnn-fp16-tests * enable tests for DNN_TARGET_CUDA_FP16 * disable deconvolution tests * disable shortcut tests * fix typos and some minor changes * dnn(test): skip CUDA FP16 test too (run_pool_max)	5 years ago
Alexander Alekhin	97b6068c46	dnn(test): don't require downloaded data	5 years ago
antalzsiroscandid	aa80f754f4	dnn: reading IR models from buffer	5 years ago
Alexander Alekhin	2c0d9fa81f	dnn(test): fix Test_Model.Keypoints* tests	5 years ago
YashasSamaga	cf93df41fc	enable tensor cores for fp16 convolutions	5 years ago
Yashas Samaga B L	17c485eb03	Merge pull request #16092 from YashasSamaga:cuda4dnn-conv-act-fuse cuda4dnn: fuse activations with convolutions * fuse ReLU, ReLU6, TanH, Sigmoid with conv * fix OpenCL errors * improve ReLU, add power, swish and mish * fix missing fusion entries * fix handling of unsetAttached * remove whole file indentation * optimize power = 1.0, use IDENTITY instead of NONE * handle edge case: change backend and then clear	5 years ago
Xuanda Yang	3d60a9b96c	Merge pull request #16156 from TH3CHARLie:3.4 * Eltwise::DIV support in Halide backend * fix typo * remove div from generated test suite to pass CI, switching to manual test... * ensure divisor not near to zero * use randu * dnn(test): update test data for Eltwise.Accuracy/DIV layer test	5 years ago
Diego	5b0b59ecfb	Merge pull request #15189 from dvd42:keypoints_module Keypoints module	5 years ago
Alexander Alekhin	5ee7abbe3c	Merge pull request #16088 from alalek:dnn_eltwise_layer_different_src_channels dnn(eltwise): fix handling of different number of channels * dnn(test): reproducer for Eltwise layer issue from PR16063 * dnn(eltwise): rework support for inputs with different channels * dnn(eltwise): get rid of finalize(), variableChannels * dnn(eltwise): update input sorting by number of channels - do not swap inputs if number of channels are same after truncation * dnn(test): skip "shortcut" with batch size 2 on MYRIAD targets	5 years ago
Dmitry Kurtaev	fe77223dee	Modify nGraph's ConvolutionBackpropData and GroupConvolution	5 years ago
Yashas Samaga B L	3fddd3bf93	Merge pull request #16069 from YashasSamaga:cuda4dnn-crop_and_resize add CropAndResize layer for CUDA backend * add CropAndResize layer * process multiple channels per iteration	5 years ago
Dmitry Kurtaev	c2ca3ee2fa	Fix weights fusion for Convolution and Deconvolution layers in nGraph	5 years ago
Yashas Samaga B L	476a02739e	Merge pull request #16097 from YashasSamaga:cuda4dnn-optimize-resize-bilinear cuda4dnn(resize): process multiple channels each iteration * resize bilinear: process multiple chans. per iter. * remove unused headers * correct dispatch logic * resize_nn: process multiple chans. per iter.	5 years ago
Dmitry Kurtaev	883c4c60c3	Remove Dummy layer	5 years ago
Alexander Alekhin	b1b505f783	dnn: clarify error message from getMemoryShapes()	5 years ago

1 2 3 4 5 ...

1204 Commits (198b5096aaf8f5d855b98337e9de2fc45485c5a7)