opencv

Commit Graph

Author	SHA1	Message	Date
Smirnov Egor	238dbffb48	change asserts for Sum	3 years ago
Smirnov Egor	a9d7b6eab7	fix const - input and remove unimplemented function	3 years ago
Smirnov Egor	9c84749e2c	backport YOLOv4x-mish new_coords CUDA implementation	3 years ago
Alexander Alekhin	8c2dd5fb9a	dnn(ocl4dnn): cleanup dead code, improve logging	3 years ago
Alexander Alekhin	724e04e979	dnn(ocl4dnn): add extra checks to convolution layer - prevent running code over unsupported/non-tested configurations - prevent integer div by zero	3 years ago
Alexander Alekhin	94e92cd6c0	dnn(ocl): skip int8 tests due to memory access issues	3 years ago
Smirnov Egor	2221dcc9f2	add SoftNMS implementation	3 years ago
Oliver Kuckertz	a3d7811f24	Merge pull request #20725 from mologie:fix-dnn-tf-on-arm * dnn: fix unaligned memory access crash on armv7 The getTensorContent function would return a Mat pointing to some member of a Protobuf-encoded message. Protobuf does not make any alignment guarantees, which results in a crash on armv7 when loading models while bit 2 is set in /proc/cpu/alignment (or the relevant kernel feature for alignment compatibility is disabled). Any read attempt from the previously unaligned data member would send SIGBUS. As workaround, this commit makes an aligned copy via existing clone functionality in getTensorContent. The unsafe copy=false option is removed. Unfortunately, a rather crude hack in PReLUSubgraph in fact writes(!) to the Protobuf message. We limit ourselves to fixing the alignment issues in this commit, and add getTensorContentRefUnaligned to cover the write case with a safe memcpy. A FIXME marks the issue. * dnn: reduce amount of .clone() calls * dnn: update FIXME comment Co-authored-by: Alexander Alekhin <alexander.a.alekhin@gmail.com>	3 years ago
Alexander Alekhin	646924fce8	dnn(pytest/test_input_3d): reload model between switching targets	3 years ago
HAN Liutong	e5fb50476c	Merge pull request #20521 from hanliutong:dev-rvv-multiVLEN Make the implementation of optimization in DNN adjustable to different vector sizes with RVV intrinsics. * Update fastGEMM for multi VLEN. * Update fastGEMM1T for multi VLEN. * Update fastDepthwiseConv for multi VLEN. * Update fastConv for multi VLEN. * Replace malloc with cv::AutoBuffer.	3 years ago
Alexander Alekhin	3e6f27522b	pre: OpenCV 4.5.4 (version++)	3 years ago
Alexander Alekhin	ebef84e9ea	pre: OpenCV 3.4.16 (version++)	3 years ago
Jebastin Nadar	cce78cc5e2	Merge pull request #20535 from SamFC10:onnx-q dnn : int8 quantized layers support in onnx importer * added quantized layers support in onnx importer * added more cases in eltwise node, some more checks * added tests for quantized nodes * relax thresholds for failed tests, address review comments * refactoring based on review comments * added support for unsupported cases and pre-quantized resnet50 test * relax thresholds due to int8 resize layer	3 years ago
Zihao Mu	9085b933d8	Merge pull request #20702 from zihaomu:tf_expand_dim_layer Add ExpandDims layer of tf_importer.cpp * Add ExpandDims to tf_importer. * add -1 expand test case. * Support different dimensions of input. * Compatible with 5-dimensional NDHWC data * Code align * support 3-dim input. * 3-dim bug fixed. * fixing error of code format.	3 years ago
YashasSamaga	505dde09de	support broadcasting in eltwise ops	3 years ago
SamFC10	87ebf2e50b	fix illegal memory access in int8 convolution	3 years ago
Alexander Alekhin	f977d10a19	dnn(ocl): fix conv DWCONV workgroup	3 years ago
Alexander Alekhin	846317ef37	dnn(ocl): fix conv BASIC workgroup	3 years ago
rogday	38b9ec7a18	Merge pull request #20682 from rogday:min * Add Min layer to CPU, OpenCL, Halide, Inference Engine, NGraph and CUDA * fix indentation * add min to fusion and halide tests; fix doc	3 years ago
SamFC10	9c5d7716e2	fix for unsqueeze opset version 13	3 years ago
rogday	c410d7a97d	Merge pull request #20671 from rogday:yolov4x-mish Add support for YOLOv4x-mish * backport to 3.4 for supporting yolov4x-mish * add YOLOv4x-mish test * address review comments Co-authored-by: Guo Xu <guoxu@1school.com.cn>	3 years ago
YashasSamaga	50462dcdc6	fix effrank assert to allow input effrank <= output effrank	3 years ago
Alexander Alekhin	6e66a9222a	dnn(onnx): fix format specifier	3 years ago
Zihao Mu	51b03b87e6	BiasAdd could load Const from second place.	3 years ago
Alexander Alekhin	1aacb9bb15	dnn(perf): update convolution tests	3 years ago
rogday	d31b93b513	Merge pull request #20674 from rogday:prelu_slope Fix PReLU negative slope access pattern * fix prelu negative slope access pattern * change begin() to ptr()	3 years ago
rogday	4807cd8a6e	Merge pull request #20605 from rogday:split_slice_shenanigans Add Normalize subgraph, fix Slice, Mul and Expand * Add Normalize subgraph, support for starts<0 and axis<0 in Slice, Mul broadcasting in the middle and fix Expand's unsqueeze * remove todos * remove range-based for loop * address review comments * change >> to > > in template * fix indexation * fix expand that does nothing	3 years ago
Alexander Alekhin	35e824c287	dnn(ocl): fix out of bound access in GEMM-like kernels - dropped usage of CreateSubBuffer() - buffers lifetime management issue - fixed elementwise offset - avoid out of bounds read access	3 years ago
Alexander Alekhin	5578ad5e14	dnn(ocl): fix automatic globalsize adjusting - if kernel code doesn't support that	3 years ago
Alexander Alekhin	5b2c016834	dnn(ocl): avoid out of buffer access in copyWeightsSwizzled	3 years ago
Alexander Alekhin	407adc7061	dnn(ocl): fix buffer offsets in IDLF kernel - drop CreateSubBuffer - fix FUSED_CONV_ELTWISE mode	3 years ago
rogday	d0e612dc36	Merge pull request #20647 from rogday:resize_concat_optimization Fix resize+concat optimization * fix resize+concat optimization * add comment and fix indentation	3 years ago
WJJ1995	edc442afdb	Merge pull request #20511 from wjj19950828:add_humanseg_support_0806 * support PPSeg model for dnn module * fixed README for CI * add test case * fixed bug * deal with comments * rm dnn_model_runner * update test case * fixed bug for testcase * update testcase	3 years ago
Alexander Alekhin	ae6fabc6fe	dnn(ocl): drop CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE check - it is a hint and it should not block kernel execution	3 years ago
Vincent Rabaud	38d0063c36	Do not use deprecated ReleaseCleared in protobuf library. This is to make code work with protobuf arenas for memory management (ReleaseCleared is incompatible). The cleaning of the memory is also simpler.	3 years ago
Alexander Alekhin	f28e4b86fb	dnn(ocl): fix top initialization in verifyResult	3 years ago
rogday	6801dd043d	Merge pull request #20494 from rogday:onnx_diagnostic_fix fix ONNXImporter diagnostic mode layer registration issue * fix layer registration, thread unsafe access and align the behavior of DNN_DIAGNOSTICS_RUN between onnx and tf importers * move skipModelInput * print all missing layers * address TF issue	3 years ago
Vincent Rabaud	9cfa84313c	Use the one argument version of SetTotalBytesLimit. The two argument versions has been deprecated, cf https://developers.google.com/protocol-buffers/docs/reference/cpp/google.protobuf.io.coded_stream	3 years ago
SamFC10	fa90e14b06	int8 layers and 8-bit quantization support	3 years ago
Smirnov Egor	fe625a558e	fix hasDynamicShapes for batch_size and fix axis selection in Scale layer	3 years ago
thezane	210bfaf8d6	Merge pull request #20483 from thezane:support-cumsum-layer-for-onnx * Support cumsum layer for onnx * Add unit tests * Address review comments	3 years ago
Smirnov Egor	9ef41f68fb	fix Split partial sum	3 years ago
Julia Bareeva	cfb36443fb	Merge pull request #20506 from JulieBar:lstm_activations * Support activations(Sigmoid, Tanh) for LSTM * fix warning	3 years ago
JIANG Yichen	955cf35d5f	Implement ctc prefix beam search decode for TextRecognitionModel. The algorithm is based on Hannun's paper: First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs	3 years ago
HAN Liutong	aaca4987c9	Merge pull request #20287 from hanliutong:dev-rvv-0.10 Optimization of DNN using native RISC-V vector intrinsics. * Use RVV to optimize fastGEMM (FP32) in DNN. * Use RVV to optimize fastGEMM1T in DNN. * Use RVV to optimize fastConv in DNN. * Use RVV to optimize fastDepthwiseConv in DNN. * Vectorize tails using vl. * Use "vl" instead of scalar to handle small block in fastConv. * Fix memory access out of bound in "fastGEMM1T". * Remove setvl. * Remove useless initialization. * Use loop unrolling to handle tail part instead of switch.	3 years ago
Smirnov Egor	739ff84732	add Max layer to TFImporter	3 years ago
SamFC10	2a177052de	fix bug in prior-box variances	3 years ago
Julia Bareeva	e1cafa3834	Merge pull request #20442 from JulieBar:gru_layer * Add initialization and inference for GRU layer * fix issues found on review	3 years ago
Julia Bareeva	633fedaa96	Merge pull request #20480 from JulieBar:lstm_pytest Add Python's test for LSTM layer * Add Python's test for LSTM layer * Set different test threshold for FP16 target * rename test to test_input_3d Co-authored-by: Julie Bareeva <julia.bareeva@xperience.ai>	3 years ago
Smirnov Egor	27392f832d	reimplement onnx refactor for master	3 years ago

1 2 3 4 5 ...

1726 Commits (b5a9a6793b3622b01fe6c7b025f85074fec99491)