opencv

Commit Graph

Author	SHA1	Message	Date
YashasSamaga	3c35b563d7	add scale_x_y parameter to region	5 years ago
Yashas Samaga B L	d981d04c76	Merge pull request #17200 from YashasSamaga:cuda4dnn-general-opt1 cuda4dnn: optimizations for swish, mish, sigmoid, region, resize based ops, transpose, identity-conv fusion * bunch of optimizations * more accurate implementation for mish	5 years ago
Dmitry Kurtaev	8b13b85c5e	dnn: Slice with variable input shapes	5 years ago
Liubov Batanina	a5696da9ec	Merge pull request #17185 from l-bat:yolo_v4 * Support Yolov4 * Skip Mish on OpenVINO 2020.2 * Revert Mish * Refactoring	5 years ago
Alexander Alekhin	b805115c1a	dnn(test): update skip tests on Win32 configuration	5 years ago
Dmitry Kurtaev	25ec4ce6f1	PReLU from Tensorflow	5 years ago
Alexander Alekhin	9181ecfc7b	cmake: fix protobuf handling	5 years ago
Liubov Batanina	4bf94cb5d1	Fix test	5 years ago
Alexander Alekhin	288fa70ed9	dnn(protobuf): backport AllowUnknownField(), SetRecursionLimit() - limit recursion in SkipField*() calls	5 years ago
YashasSamaga	aff2c7c43c	handle redundant slice in SliceOp	5 years ago
Alexander Alekhin	f756923271	dnn(ie): avoid conversion to legacy CNNNetworkImpl	5 years ago
Alexander Alekhin	83c4378d5d	dnn(test): skip failed NGRAPH/MYRIAD tests	5 years ago
Liubov Batanina	1c1762d3f6	Skip myriad	5 years ago
ashishiva3@gmail.com	e0ac0cfbe2	add fused batchNorm Upsample	5 years ago
Liubov Batanina	aa08900ac8	Supported TF concat 3d	5 years ago
AshihsKrShrivastava	d37180a2c4	modification for upsample node fused from unfused Resize subgraph	5 years ago
Liubov Batanina	8badf7f354	Merge pull request #17112 from l-bat:ie_region * Support nGraph Region * Support region since OpenVINO 2020.2 * Skip myriad	5 years ago
Dmitry Kurtaev	908bf935f7	Flexible inputs for OpenVINO IR models	5 years ago
Dmitry Kurtaev	5e5385a814	Remove NodeVector for nGraph	5 years ago
Alexander Alekhin	ef68cc3d5f	dnn: use OpenVINO 2020.2 defines original commit: `45263d7642`	5 years ago
Ilya Lavrenov	91b0100287	Fixed compilation when NN builder is not built	5 years ago
Dmitry Kurtaev	870a775d7d	Align DLIE and nGraph average pooling layers	5 years ago
Dmitry Kurtaev	d3f9ad1145	Enable ONNX SSD from https://github.com/amdegroot/ssd.pytorch	5 years ago
AshihsKrShrivastava	bef6b6282c	ReflecitonPad2d and ZeroPad2d Subgraph fusion added	5 years ago
Dmitry Kurtaev	21ed892489	Fix Elu import from ONNX	5 years ago
Liubov Batanina	734771418e	Merge pull request #16840 from l-bat:matmul_inputs * Supported FullyConnected layer with two inputs * Skipped test * Fix conditions * Added OpenCL support * Supported ReduceMean3D * Supported Expand layer * Fix warning * Added Normalize subgraph * refactoring * Used addLayer * Fix check * Used addLayer * Skip failed test * Added normalize1 subgraph * Fix comments	5 years ago
Liubov Batanina	a448d3a6aa	Fix ENet test with OpenVINO 2020.2	5 years ago
Dmitry Kurtaev	b36eba7fab	Support FusedResizeAndPadConv2D from TensorFlow	5 years ago
Dmitry Kurtaev	8574a757f9	Case sensitive dnn layers types	5 years ago
Alexander Alekhin	e661ad2a67	eliminate build warnings	5 years ago
Alexander Alekhin	b4b4d21212	eliminate build warnings	5 years ago
Dmitry Kurtaev	7e4b2057f2	Import TF2.0 network from Keras	5 years ago
YashasSamaga	4e8cd4629c	fix CUDNN_STATUS_NOT_SUPPORTED, remove redundant fusion checks	5 years ago
Dmitry Kurtaev	467c3ef0ac	Add checks for LSTM initial h and c	5 years ago
YashasSamaga	2aeb32d2d1	fix segfaults, support bias in untrainable mode, support batches in untrainable mode	5 years ago
Dmitry Kurtaev	8433620295	Bidirectional LSTM	5 years ago
Pavel Rojtberg	66cf55ea1f	dnn: expose only float variant of NMSBoxes for bindings the float variant was always shadowed by the int version as Rect2d is implicitly convertible to Rect. This swaps things which is fine, as the vector of boxes was always copied and the computation was done in double.	5 years ago
Dmitry Kurtaev	11d565ca62	Fix LSTM from ONNX with batch==1	5 years ago
Dmitry Kurtaev	8d69dbdf49	LSTM from ONNX works	5 years ago
Dmitry Kurtaev	14da5ec311	LSTM scalar	5 years ago
Liubov Batanina	718d7e4b04	Merge pull request #16715 from l-bat:slice_onnx * Support Slice layer with multiple inputs * Add test * Supported Resize from PyTorch * Rewrite test * Remove Cast layer (supported in #16735) * Support ConstantOfShape * Fix tests * Fix coments * Remove useless condition * Fixed failed tests	5 years ago
YashasSamaga	034a43e7f7	release and relock on wrapper resize	5 years ago
Dmitry Kurtaev	7f0d90a525	Fix memory leak in Python custom dnn layers	5 years ago
Liubov Batanina	2645ee90ca	Merge pull request #16735 from l-bat:flatten_const_onnx * Supported Flatten for constant nodes * Added default axis * Refactoring * Refactoring * Added cast layer * Fix comments * Add Cast for layers	5 years ago
Alexander Alekhin	9b64eadcb6	dnn(ie): separate IECore for different devices - HETERO plugin doesn't switch well between devices	5 years ago
Alexander Alekhin	7d1c42afe1	dnn: fix merge mistake in scale_layer.cpp	5 years ago
Alexander Alekhin	db95aec4a7	dnn(ie): switch to nGraph backend by default	5 years ago
Yashas Samaga B L	490908f0ff	Merge pull request #16436 from YashasSamaga:feature-enetb0-yolo dnn(darknet-importer): add grouped convolutions, sigmoid, swish, scale_channels * update darknet importer to support enetb0-yolo * remove dropout (pr16438) and fix formatting * add test for scale_channels * disable batch testing for scale channels * do not set LayerParams::name * merge all activations into setActivation	5 years ago
NesQl	0bcdf7d03e	Merge pull request #16724 from liqi-c:3.4-tengine * Add Tengine support . * Modify printf to CV_LOG_WARNING * a few minor fixes in the code * Renew Tengine version * Add header file for CV_LOG_WARNING * Add #ifdef HAVE_TENGINE in tengine_graph_convolution.cpp * remove trailing whitespace * Remove trailing whitespace * Modify for compile problem * Modify some code style error * remove whitespace * Move some code style problem * test * add ios limit and build problem * Modified as alalek suggested * Add cmake 2.8 support * modify cmake 3.5.1 problem * test and set BUILD_ANDROID_PROJECTS OFF * remove some compile error * remove some extra code in tengine * close test. * Test again * disable android. * delete ndk version judgement * Remove setenv() call . and add License information * Set tengine default OFF. Close test . Co-authored-by: Vadim Pisarevsky <vadim.pisarevsky@gmail.com>	5 years ago
Dmitry Kurtaev	b927ce18b2	Support for MobileNetV3-SSD from TensorFlow	5 years ago

... 2 3 4 5 6 ...

1516 Commits (5ecf6937747e1b37c3d73c3f6fe46f9b2dc404ca)