opencv

Commit Graph

Author	SHA1	Message	Date
Yuantao Feng	c2b7c1f13b	Merge pull request #23219 from fengyuentau:add_gelu Add GELU layer for vision transformers * add gelu and gelu approximation * drop setKernelParams	2 years ago
wanli	4718a4bf81	make GEMM can be supported with transA and transB in CUDA	2 years ago
Yuantao Feng	4d918ba40b	Merge pull request #23047 from fengyuentau:layer_norm dnn: add layer normalization for vision transformers * add layer norm onnx parser, impl and tests * add onnx graph simplifier for layer norm expanded * handle the case when constants are of type Initializer * add test case for layer norm expanded with initializers * use CV_Assert & CV_CheckType in place of CV_Assert_N; use forward_fallback for OCL_FP16 * use const ref / ref in parameters of invoker::run; extract inner const if from nested loop; use size_t in place of ull * template hasBias * remove trailing whitespace * use pointer parameter with null check; move normSize division & mean_square division outside of loop; use std::max to ensure positive value before std::sqrt * refactor implementation, optimize parallel_for * disable layer norm expanded * remove the removal of layer norm optional outputs	2 years ago
zoom	4891818114	make MatMul support 3D or 4D with broadcast	2 years ago
zihaomu	0d56524b72	gemm support transA and transB, and first input is constance.	2 years ago
fengyuentau	441624a5fb	tile impl	2 years ago
zoom	5044af69d1	let MatMul can work when both two inputs are const	2 years ago
zoom	ef2677b0a6	Make MatMul layer support 3d or 4d operation with const input	2 years ago
Zihao Mu	17f2b56291	remove never used code in onnximporter	2 years ago
Zihao Mu	903bf0147e	Merge pull request #22666 from zihaomu:support_onnx_qdq_model DNN: let Quant and Dequant of ONNX_importer support the Constant input. * let Quant and Dequant support the Constant input. * fix negative value of axis.	2 years ago
Smirnov Egor	dd14cf6a9c	address CUDA-related errors and enable cuda in elementwise ops	2 years ago
fengyuentau	d24d8f2abe	implementation of scatter and scatternd with conformance tests enabled	2 years ago
zoom	d816442e4d	Make Unsqueeze layer support negative axes.	2 years ago
Zihao Mu	d9eff7daeb	parse quantized nodes does not rely on name.	2 years ago
Zihao Mu	9821fae59d	add greater_or_equal and less_or_equal ONNX support	2 years ago
zoom	4557971481	enhance slice layer refactor the code for parsing Slice layer add test for Slice layer let 'begin' and 'end' resize to dims add opset message comment	2 years ago
Zihao Mu	15cfafb360	DNN: Remove unused code in onnx_importer.cpp	2 years ago
Egor Smirnov	65f71ce2eb	add Gather implementation	2 years ago
fengyuentau	4aef9b1c93	dnn: support yolov7 (not simplified)	2 years ago
Zihao Mu	2d837efba7	add qgemm and squeeze op13 supported on ONNXImporter	2 years ago
Zihao Mu	9638e34ab0	reuse WORDS_BIGENDIAN.	2 years ago
Zihao Mu	7eaec9dd22	load fp16 as fp32 and align fp16 and double in onnx_graph_simplifie	2 years ago
fengyuentau	e7e814fa8c	remove asymmetric padding checks	2 years ago
Zihao Mu	d4640f4647	support ReduceLayer without reshape layer.	2 years ago
Zihao Mu	57545653b1	replace new mish impl with softplus	2 years ago
Zihao Mu	3c5377ca1b	add another Mish graph simplifier.	2 years ago
Zihao Mu	98c33c605d	batchsize dynamic is set to index 0.	2 years ago
rogday	ed69bcae2d	Merge pull request #21865 from rogday:nary_eltwise_layers Reimplementation of Element-wise layers with broadcasting support * init * semi-working initial version * add small_vector * wip * remove smallvec * add nary function * replace auto with Mat in lambda expr used in transform * uncomment asserts * autobuffer shape_buf & step_buf * fix a missing bracket * fixed a missing addLayer in parseElementWise * solve one-dimensional broadcast * remove pre_broadcast_transform for the case of two constants; fix missing constBlobsExtraInfo when addConstant is called * one autobuffer for step & shape * temporal fix for the missing original dimension information * fix parseUnsqueeze when it gets a 1d tensor constant * support sum/mean/min/max with only one input * reuse old code to handle cases of two non-constant inputs * add condition to handle div & mul of two non-constant inputs * use \|\| instead of or * remove trainling spaces * enlarge buf in binary_forward to contain other buffer * use autobuffer in nary_forward * generate data randomly and add more cases for perf * add op and, or & xor * update perf_dnn * remove some comments * remove legacy; add two ONNX conformance tests in filter * move from cpu_denylist to all_denylist * adjust parsing for inputs>=2 Co-authored-by: fengyuentau <yuantao.feng@opencv.org.cn>	2 years ago
Zihao Mu	1b8fba8e26	support ReduceSum with two input and dynamic shape batch size in ReduceLayer.	2 years ago
Zihao Mu	45fbb67aba	fix scale layer can not handle 1x1 weight correctly.	2 years ago
Zihao Mu	a80fcacd90	Merge pull request #21372 from zihaomu:dnn_quantize_per_tensor Add per_tensor_quantize to int8 quantize * add per_tensor_quantize to dnn int8 module. * change api flag from perTensor to perChannel, and recognize quantize type and onnx importer. * change the default to hpp	2 years ago
Zihao Mu	ef94275eb6	bug fixed of GEMM node in ONNX_importer	3 years ago
Wanli	a6ca48a1c2	Merge pull request #22100 from WanliZhong:issue_22015 Fix issue 22015, let Clip layer support 1-3 inputs * Fix issue 22015. Let layer Clip support 1-3 inputs. * Resolve other problems caused by modifications * Update onnx_importer.cpp added extra checks to min/max handling in Clip * Add assertions to check the size of the input * Add test for clip with min and max initializers * Separate test for "clip_init_min_max". Change the check method for input_size to provide a clearer message in case of problem. * Add tests for clip with min or max initializers * Change the implementation of getting input Co-authored-by: Vadim Pisarevsky <vadim.pisarevsky@gmail.com>	3 years ago
Zihao Mu	2411b825b4	bug fixed of GEMM node in ONNX_importer	3 years ago
Namgoo Lee	24547f40ff	remove const from functions returning by value	3 years ago
rogday	93dc0679ec	Merge pull request #21818 from rogday:revert_renaming * add prefixes to layer names and layer output names * dnn: OPENCV_DNN_ONNX_USE_LEGACY_NAMES runtime parameter Co-authored-by: Alexander Alekhin <alexander.a.alekhin@gmail.com>	3 years ago
fengyuentau	ff88132620	support asymmetric paddings for qconv	3 years ago
Yulv-git	15ac54d5d6	Fix some typos in modules/.	3 years ago
Zihao Mu	64ded50bbf	parsing depth2space and space2depth of ONNX importer	3 years ago
zihaomu	e36948cfbc	add ONNX OP sign, shrink and reciprocal	3 years ago
Zihao Mu	7b582b71ba	Merge pull request #21036 from fengyuentau:timvx_backend_support dnn: TIM-VX NPU backend support * Add TimVX NPU backend for DNN module. * use official branch from tim-vx repo; fix detecting viv sdk Co-authored-by: fytao <yuantao.feng@outlook.com>	3 years ago
Smirnov Egor	abebbf04b1	Add CUDA support for LSTM. Co-authored-by: Julia Bareeva <jbareeva@gmail.com>	3 years ago
Zihao Mu	b6b5c27cec	Support for some reduce layers for onnx	3 years ago
rogday	93353aea70	Merge pull request #21522 from rogday:lstm Fix LSTM support in ONNX * fix LSTM and add peephole support * disable old tests * turn lambdas into functions * more hacks for c++98 * add assertions * slice fixes * backport of cuda-related fixes * address review comments	3 years ago
Egor Smirnov	375fe81311	fix slice and expand	3 years ago
Yuantao Feng	f77c3574af	Merge pull request #21607 from fengyuentau:fix_FaceDetectorYN_dynamic_shape Use YuNet of fixed input shape to fix not-supported-dynamic-zero-shape for FaceDetectorYN * use yunet with input of fixed shape * update yunet used in face recognition regression	3 years ago
Alexander Alekhin	85719a0a5d	dnn: support outputs registration under new names - fixed ONNX importer	3 years ago
Zihao Mu	9e3ba487fa	Merge pull request #21518 from zihaomu:resize_onnx_opset13 Add resize layer compatible with ONNX opset13 version	3 years ago
Alexander Alekhin	70b0274c8e	dnn: apply hint to ignore denormals processing	3 years ago
Smirnov Egor	17b2d92a3d	add optional outputs support and fix graph links	3 years ago

1 2 3 4 5 ...

286 Commits (c6e5f6052513b6b1fb07682371ec08a6d4c0584b)