Module dnn

Expand description

§Deep Neural Network module

This module contains: - API for new layers creation, layers are building bricks of neural networks; - set of built-in most-useful Layers; - API to construct and modify comprehensive neural networks from layers; - functionality for loading serialized networks models from different frameworks.

Functionality of this module is designed only for forward pass computations (i.e. network testing). A network training is in principle not supported.

Modules§

prelude

Structs§

AbsLayer
AccumLayer
AcosLayer
AcoshLayer
ActivationLayer
ActivationLayerInt8
ArgLayer: ArgMax/ArgMin layer
AsinLayer
AsinhLayer
AtanLayer
AtanhLayer
AttentionLayer
BNLLLayer
BackendNode: Derivatives of this class encapsulates functions of certain backends.
BackendWrapper: Derivatives of this class wraps cv::Mat for different backends and targets.
BaseConvolutionLayer
BatchNormLayer
BatchNormLayerInt8
BlankLayer: Partial List of Implemented Layers
CeilLayer
CeluLayer
ChannelsPReLULayer
ClassificationModel: This class represents high-level API for classification models.
CompareLayer
ConcatLayer
ConstLayer: Constant layer produces the same data blob at an every forward pass.
ConvolutionLayer
ConvolutionLayerInt8
CorrelationLayer
CosLayer
CoshLayer
CropAndResizeLayer
CropLayer
CumSumLayer
DataAugmentationLayer
DeconvolutionLayer
DepthToSpaceLayer
DequantizeLayer
DetectionModel: This class represents high-level API for object detection networks.
DetectionOutputLayer: Detection output layer.
Dict: This class implements name-value dictionary, values are instances of DictValue.
DictValue: This struct stores the scalar value (or array) of one of the following type: double, cv::String or int64. @todo Maybe int64 is useless because double type exactly stores at least 2^52 integers.
ELULayer
EinsumLayer: This function performs array summation based on the Einstein summation convention. The function allows for concise expressions of various mathematical operations using subscripts.
EltwiseLayer: Element wise operation on inputs
EltwiseLayerInt8
ErfLayer
ExpLayer
ExpandLayer
FlattenLayer
FloorLayer
FlowWarpLayer
GRULayer: GRU recurrent one-layer
GatherElementsLayer: GatherElements layer GatherElements takes two inputs data and indices of the same rank r >= 1 and an optional attribute axis and works such that: output[i][j][k] = data[index[i][j][k]][j][k] if axis = 0 and r = 3 output[i][j][k] = data[i][index[i][j][k]][k] if axis = 1 and r = 3 output[i][j][k] = data[i][j][index[i][j][k]] if axis = 2 and r = 3
GatherLayer: Gather layer
GeluApproximationLayer
GeluLayer
GemmLayer
GroupNormLayer
HardSigmoidLayer
HardSwishLayer
Image2BlobParams: Processing params of image to blob.
InnerProductLayer: InnerProduct, MatMul and Gemm operations are all implemented by Fully Connected Layer. Parameter is_matmul is used to distinguish MatMul and Gemm from InnerProduct.
InnerProductLayerInt8
InstanceNormLayer
InterpLayer: Bilinear resize layer from https://github.com/cdmh/deeplab-public-ver2
KeypointsModel: This class represents high-level API for keypoints models
LRNLayer
LSTMLayer: LSTM recurrent layer
Layer: This interface class allows to build new Layers - are building blocks of networks.
LayerFactory: %Layer factory allows to create instances of registered layers.
LayerNormLayer
LayerParams: This class provides all data needed to initialize layer.
LogLayer
MVNLayer
MatMulLayer
MaxUnpoolLayer
MishLayer
Model: This class is presented high-level API for neural networks.
NaryEltwiseLayer
Net: This class allows to create and manipulate comprehensive artificial neural networks.
NormalizeBBoxLayer: inline formula - normalization layer.
NotLayer
PaddingLayer: Adds extra values for specific axes.
PermuteLayer
PoolingLayer
PoolingLayerInt8
PowerLayer
PriorBoxLayer
ProposalLayer
QuantizeLayer
RNNLayer: Classical recurrent layer
ReLU6Layer
ReLULayer
ReciprocalLayer
ReduceLayer
RegionLayer
ReorgLayer
RequantizeLayer
ReshapeLayer
ResizeLayer: Resize input 4-dimensional blob by nearest neighbor or bilinear strategy.
RoundLayer
ScaleLayer
ScaleLayerInt8
ScatterLayer
ScatterNDLayer
SegmentationModel: This class represents high-level API for segmentation models
SeluLayer
ShiftLayer
ShiftLayerInt8
ShrinkLayer
ShuffleChannelLayer: Permute channels of 4-dimensional input blob.
SigmoidLayer
SignLayer
SinLayer
SinhLayer
SliceLayer: Slice layer has several modes:
SoftmaxLayer
SoftmaxLayerInt8
SoftplusLayer
SoftsignLayer
SpaceToDepthLayer
SplitLayer
SqrtLayer
SwishLayer
TanHLayer
TanLayer
TextDetectionModel: Base class for text detection networks
TextDetectionModel_DB: This class represents high-level API for text detection DL networks compatible with DB model.
TextDetectionModel_EAST: This class represents high-level API for text detection DL networks compatible with EAST model.
TextRecognitionModel: This class represents high-level API for text recognition networks.
ThresholdedReluLayer
TileLayer
TopKLayer
_Range

Enums§

Backend: Enum of computation backends supported by layers.
DataLayout: Enum of data layout for model inference.
ImagePaddingMode: Enum of image processing mode. To facilitate the specialization pre-processing requirements of the dnn model. For example, the letter box often used in the Yolo series of models.
SoftNMSMethod: Enum of Soft NMS methods.
Target: Enum of target devices for computations.

Constants§

CV_DNN_BACKEND_INFERENCE_ENGINE_NGRAPH
CV_DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_API
CV_DNN_INFERENCE_ENGINE_CPU_TYPE_ARM_COMPUTE
CV_DNN_INFERENCE_ENGINE_CPU_TYPE_X86
CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_2
CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X
CV_DNN_INFERENCE_ENGINE_VPU_TYPE_UNSPECIFIED
DNN_BACKEND_CANN
DNN_BACKEND_CUDA
DNN_BACKEND_DEFAULT: DNN_BACKEND_DEFAULT equals to OPENCV_DNN_BACKEND_DEFAULT, which can be defined using CMake or a configuration parameter
DNN_BACKEND_HALIDE: DNN_BACKEND_DEFAULT equals to OPENCV_DNN_BACKEND_DEFAULT, which can be defined using CMake or a configuration parameter
DNN_BACKEND_INFERENCE_ENGINE: Intel OpenVINO computational backend
DNN_BACKEND_OPENCV
DNN_BACKEND_TIMVX
DNN_BACKEND_VKCOM
DNN_BACKEND_WEBNN
DNN_LAYOUT_NCDHW: OpenCV data layout for 5D data.
DNN_LAYOUT_NCHW: OpenCV data layout for 4D data.
DNN_LAYOUT_ND: OpenCV data layout for 2D data.
DNN_LAYOUT_NDHWC: Tensorflow-like data layout for 5D data.
DNN_LAYOUT_NHWC: Tensorflow-like data layout for 4D data.
DNN_LAYOUT_PLANAR: Tensorflow-like data layout, it should only be used at tf or tflite model parsing.
DNN_LAYOUT_UNKNOWN
DNN_PMODE_CROP_CENTER
DNN_PMODE_LETTERBOX
DNN_PMODE_NULL
DNN_TARGET_CPU
DNN_TARGET_CPU_FP16
DNN_TARGET_CUDA
DNN_TARGET_CUDA_FP16
DNN_TARGET_FPGA: FPGA device with CPU fallbacks using Inference Engine’s Heterogeneous plugin.
DNN_TARGET_HDDL
DNN_TARGET_MYRIAD
DNN_TARGET_NPU
DNN_TARGET_OPENCL
DNN_TARGET_OPENCL_FP16
DNN_TARGET_VULKAN
OPENCV_DNN_API_VERSION
SoftNMSMethod_SOFTNMS_GAUSSIAN
SoftNMSMethod_SOFTNMS_LINEAR

Traits§

AbsLayerTrait: Mutable methods for crate::dnn::AbsLayer
AbsLayerTraitConst: Constant methods for crate::dnn::AbsLayer
AccumLayerTrait: Mutable methods for crate::dnn::AccumLayer
AccumLayerTraitConst: Constant methods for crate::dnn::AccumLayer
AcosLayerTrait: Mutable methods for crate::dnn::AcosLayer
AcosLayerTraitConst: Constant methods for crate::dnn::AcosLayer
AcoshLayerTrait: Mutable methods for crate::dnn::AcoshLayer
AcoshLayerTraitConst: Constant methods for crate::dnn::AcoshLayer
ActivationLayerInt8Trait: Mutable methods for crate::dnn::ActivationLayerInt8
ActivationLayerInt8TraitConst: Constant methods for crate::dnn::ActivationLayerInt8
ActivationLayerTrait: Mutable methods for crate::dnn::ActivationLayer
ActivationLayerTraitConst: Constant methods for crate::dnn::ActivationLayer
ArgLayerTrait: Mutable methods for crate::dnn::ArgLayer
ArgLayerTraitConst: Constant methods for crate::dnn::ArgLayer
AsinLayerTrait: Mutable methods for crate::dnn::AsinLayer
AsinLayerTraitConst: Constant methods for crate::dnn::AsinLayer
AsinhLayerTrait: Mutable methods for crate::dnn::AsinhLayer
AsinhLayerTraitConst: Constant methods for crate::dnn::AsinhLayer
AtanLayerTrait: Mutable methods for crate::dnn::AtanLayer
AtanLayerTraitConst: Constant methods for crate::dnn::AtanLayer
AtanhLayerTrait: Mutable methods for crate::dnn::AtanhLayer
AtanhLayerTraitConst: Constant methods for crate::dnn::AtanhLayer
AttentionLayerTrait: Mutable methods for crate::dnn::AttentionLayer
AttentionLayerTraitConst: Constant methods for crate::dnn::AttentionLayer
BNLLLayerTrait: Mutable methods for crate::dnn::BNLLLayer
BNLLLayerTraitConst: Constant methods for crate::dnn::BNLLLayer
BackendNodeTrait: Mutable methods for crate::dnn::BackendNode
BackendNodeTraitConst: Constant methods for crate::dnn::BackendNode
BackendWrapperTrait: Mutable methods for crate::dnn::BackendWrapper
BackendWrapperTraitConst: Constant methods for crate::dnn::BackendWrapper
BaseConvolutionLayerTrait: Mutable methods for crate::dnn::BaseConvolutionLayer
BaseConvolutionLayerTraitConst: Constant methods for crate::dnn::BaseConvolutionLayer
BatchNormLayerInt8Trait: Mutable methods for crate::dnn::BatchNormLayerInt8
BatchNormLayerInt8TraitConst: Constant methods for crate::dnn::BatchNormLayerInt8
BatchNormLayerTrait: Mutable methods for crate::dnn::BatchNormLayer
BatchNormLayerTraitConst: Constant methods for crate::dnn::BatchNormLayer
BlankLayerTrait: Mutable methods for crate::dnn::BlankLayer
BlankLayerTraitConst: Constant methods for crate::dnn::BlankLayer
CeilLayerTrait: Mutable methods for crate::dnn::CeilLayer
CeilLayerTraitConst: Constant methods for crate::dnn::CeilLayer
CeluLayerTrait: Mutable methods for crate::dnn::CeluLayer
CeluLayerTraitConst: Constant methods for crate::dnn::CeluLayer
ChannelsPReLULayerTrait: Mutable methods for crate::dnn::ChannelsPReLULayer
ChannelsPReLULayerTraitConst: Constant methods for crate::dnn::ChannelsPReLULayer
ClassificationModelTrait: Mutable methods for crate::dnn::ClassificationModel
ClassificationModelTraitConst: Constant methods for crate::dnn::ClassificationModel
CompareLayerTrait: Mutable methods for crate::dnn::CompareLayer
CompareLayerTraitConst: Constant methods for crate::dnn::CompareLayer
ConcatLayerTrait: Mutable methods for crate::dnn::ConcatLayer
ConcatLayerTraitConst: Constant methods for crate::dnn::ConcatLayer
ConstLayerTrait: Mutable methods for crate::dnn::ConstLayer
ConstLayerTraitConst: Constant methods for crate::dnn::ConstLayer
ConvolutionLayerInt8Trait: Mutable methods for crate::dnn::ConvolutionLayerInt8
ConvolutionLayerInt8TraitConst: Constant methods for crate::dnn::ConvolutionLayerInt8
ConvolutionLayerTrait: Mutable methods for crate::dnn::ConvolutionLayer
ConvolutionLayerTraitConst: Constant methods for crate::dnn::ConvolutionLayer
CorrelationLayerTrait: Mutable methods for crate::dnn::CorrelationLayer
CorrelationLayerTraitConst: Constant methods for crate::dnn::CorrelationLayer
CosLayerTrait: Mutable methods for crate::dnn::CosLayer
CosLayerTraitConst: Constant methods for crate::dnn::CosLayer
CoshLayerTrait: Mutable methods for crate::dnn::CoshLayer
CoshLayerTraitConst: Constant methods for crate::dnn::CoshLayer
CropAndResizeLayerTrait: Mutable methods for crate::dnn::CropAndResizeLayer
CropAndResizeLayerTraitConst: Constant methods for crate::dnn::CropAndResizeLayer
CropLayerTrait: Mutable methods for crate::dnn::CropLayer
CropLayerTraitConst: Constant methods for crate::dnn::CropLayer
CumSumLayerTrait: Mutable methods for crate::dnn::CumSumLayer
CumSumLayerTraitConst: Constant methods for crate::dnn::CumSumLayer
DataAugmentationLayerTrait: Mutable methods for crate::dnn::DataAugmentationLayer
DataAugmentationLayerTraitConst: Constant methods for crate::dnn::DataAugmentationLayer
DeconvolutionLayerTrait: Mutable methods for crate::dnn::DeconvolutionLayer
DeconvolutionLayerTraitConst: Constant methods for crate::dnn::DeconvolutionLayer
DepthToSpaceLayerTrait: Mutable methods for crate::dnn::DepthToSpaceLayer
DepthToSpaceLayerTraitConst: Constant methods for crate::dnn::DepthToSpaceLayer
DequantizeLayerTrait: Mutable methods for crate::dnn::DequantizeLayer
DequantizeLayerTraitConst: Constant methods for crate::dnn::DequantizeLayer
DetectionModelTrait: Mutable methods for crate::dnn::DetectionModel
DetectionModelTraitConst: Constant methods for crate::dnn::DetectionModel
DetectionOutputLayerTrait: Mutable methods for crate::dnn::DetectionOutputLayer
DetectionOutputLayerTraitConst: Constant methods for crate::dnn::DetectionOutputLayer
DictTrait: Mutable methods for crate::dnn::Dict
DictTraitConst: Constant methods for crate::dnn::Dict
DictValueTrait: Mutable methods for crate::dnn::DictValue
DictValueTraitConst: Constant methods for crate::dnn::DictValue
ELULayerTrait: Mutable methods for crate::dnn::ELULayer
ELULayerTraitConst: Constant methods for crate::dnn::ELULayer
EinsumLayerTrait: Mutable methods for crate::dnn::EinsumLayer
EinsumLayerTraitConst: Constant methods for crate::dnn::EinsumLayer
EltwiseLayerInt8Trait: Mutable methods for crate::dnn::EltwiseLayerInt8
EltwiseLayerInt8TraitConst: Constant methods for crate::dnn::EltwiseLayerInt8
EltwiseLayerTrait: Mutable methods for crate::dnn::EltwiseLayer
EltwiseLayerTraitConst: Constant methods for crate::dnn::EltwiseLayer
ErfLayerTrait: Mutable methods for crate::dnn::ErfLayer
ErfLayerTraitConst: Constant methods for crate::dnn::ErfLayer
ExpLayerTrait: Mutable methods for crate::dnn::ExpLayer
ExpLayerTraitConst: Constant methods for crate::dnn::ExpLayer
ExpandLayerTrait: Mutable methods for crate::dnn::ExpandLayer
ExpandLayerTraitConst: Constant methods for crate::dnn::ExpandLayer
FlattenLayerTrait: Mutable methods for crate::dnn::FlattenLayer
FlattenLayerTraitConst: Constant methods for crate::dnn::FlattenLayer
FloorLayerTrait: Mutable methods for crate::dnn::FloorLayer
FloorLayerTraitConst: Constant methods for crate::dnn::FloorLayer
FlowWarpLayerTrait: Mutable methods for crate::dnn::FlowWarpLayer
FlowWarpLayerTraitConst: Constant methods for crate::dnn::FlowWarpLayer
GRULayerTrait: Mutable methods for crate::dnn::GRULayer
GRULayerTraitConst: Constant methods for crate::dnn::GRULayer
GatherElementsLayerTrait: Mutable methods for crate::dnn::GatherElementsLayer
GatherElementsLayerTraitConst: Constant methods for crate::dnn::GatherElementsLayer
GatherLayerTrait: Mutable methods for crate::dnn::GatherLayer
GatherLayerTraitConst: Constant methods for crate::dnn::GatherLayer
GeluApproximationLayerTrait: Mutable methods for crate::dnn::GeluApproximationLayer
GeluApproximationLayerTraitConst: Constant methods for crate::dnn::GeluApproximationLayer
GeluLayerTrait: Mutable methods for crate::dnn::GeluLayer
GeluLayerTraitConst: Constant methods for crate::dnn::GeluLayer
GemmLayerTrait: Mutable methods for crate::dnn::GemmLayer
GemmLayerTraitConst: Constant methods for crate::dnn::GemmLayer
GroupNormLayerTrait: Mutable methods for crate::dnn::GroupNormLayer
GroupNormLayerTraitConst: Constant methods for crate::dnn::GroupNormLayer
HardSigmoidLayerTrait: Mutable methods for crate::dnn::HardSigmoidLayer
HardSigmoidLayerTraitConst: Constant methods for crate::dnn::HardSigmoidLayer
HardSwishLayerTrait: Mutable methods for crate::dnn::HardSwishLayer
HardSwishLayerTraitConst: Constant methods for crate::dnn::HardSwishLayer
InnerProductLayerInt8Trait: Mutable methods for crate::dnn::InnerProductLayerInt8
InnerProductLayerInt8TraitConst: Constant methods for crate::dnn::InnerProductLayerInt8
InnerProductLayerTrait: Mutable methods for crate::dnn::InnerProductLayer
InnerProductLayerTraitConst: Constant methods for crate::dnn::InnerProductLayer
InstanceNormLayerTrait: Mutable methods for crate::dnn::InstanceNormLayer
InstanceNormLayerTraitConst: Constant methods for crate::dnn::InstanceNormLayer
InterpLayerTrait: Mutable methods for crate::dnn::InterpLayer
InterpLayerTraitConst: Constant methods for crate::dnn::InterpLayer
KeypointsModelTrait: Mutable methods for crate::dnn::KeypointsModel
KeypointsModelTraitConst: Constant methods for crate::dnn::KeypointsModel
LRNLayerTrait: Mutable methods for crate::dnn::LRNLayer
LRNLayerTraitConst: Constant methods for crate::dnn::LRNLayer
LSTMLayerTrait: Mutable methods for crate::dnn::LSTMLayer
LSTMLayerTraitConst: Constant methods for crate::dnn::LSTMLayer
LayerFactoryTrait: Mutable methods for crate::dnn::LayerFactory
LayerFactoryTraitConst: Constant methods for crate::dnn::LayerFactory
LayerNormLayerTrait: Mutable methods for crate::dnn::LayerNormLayer
LayerNormLayerTraitConst: Constant methods for crate::dnn::LayerNormLayer
LayerParamsTrait: Mutable methods for crate::dnn::LayerParams
LayerParamsTraitConst: Constant methods for crate::dnn::LayerParams
LayerTrait: Mutable methods for crate::dnn::Layer
LayerTraitConst: Constant methods for crate::dnn::Layer
LogLayerTrait: Mutable methods for crate::dnn::LogLayer
LogLayerTraitConst: Constant methods for crate::dnn::LogLayer
MVNLayerTrait: Mutable methods for crate::dnn::MVNLayer
MVNLayerTraitConst: Constant methods for crate::dnn::MVNLayer
MatMulLayerTrait: Mutable methods for crate::dnn::MatMulLayer
MatMulLayerTraitConst: Constant methods for crate::dnn::MatMulLayer
MaxUnpoolLayerTrait: Mutable methods for crate::dnn::MaxUnpoolLayer
MaxUnpoolLayerTraitConst: Constant methods for crate::dnn::MaxUnpoolLayer
MishLayerTrait: Mutable methods for crate::dnn::MishLayer
MishLayerTraitConst: Constant methods for crate::dnn::MishLayer
ModelTrait: Mutable methods for crate::dnn::Model
ModelTraitConst: Constant methods for crate::dnn::Model
NaryEltwiseLayerTrait: Mutable methods for crate::dnn::NaryEltwiseLayer
NaryEltwiseLayerTraitConst: Constant methods for crate::dnn::NaryEltwiseLayer
NetTrait: Mutable methods for crate::dnn::Net
NetTraitConst: Constant methods for crate::dnn::Net
NormalizeBBoxLayerTrait: Mutable methods for crate::dnn::NormalizeBBoxLayer
NormalizeBBoxLayerTraitConst: Constant methods for crate::dnn::NormalizeBBoxLayer
NotLayerTrait: Mutable methods for crate::dnn::NotLayer
NotLayerTraitConst: Constant methods for crate::dnn::NotLayer
PaddingLayerTrait: Mutable methods for crate::dnn::PaddingLayer
PaddingLayerTraitConst: Constant methods for crate::dnn::PaddingLayer
PermuteLayerTrait: Mutable methods for crate::dnn::PermuteLayer
PermuteLayerTraitConst: Constant methods for crate::dnn::PermuteLayer
PoolingLayerInt8Trait: Mutable methods for crate::dnn::PoolingLayerInt8
PoolingLayerInt8TraitConst: Constant methods for crate::dnn::PoolingLayerInt8
PoolingLayerTrait: Mutable methods for crate::dnn::PoolingLayer
PoolingLayerTraitConst: Constant methods for crate::dnn::PoolingLayer
PowerLayerTrait: Mutable methods for crate::dnn::PowerLayer
PowerLayerTraitConst: Constant methods for crate::dnn::PowerLayer
PriorBoxLayerTrait: Mutable methods for crate::dnn::PriorBoxLayer
PriorBoxLayerTraitConst: Constant methods for crate::dnn::PriorBoxLayer
ProposalLayerTrait: Mutable methods for crate::dnn::ProposalLayer
ProposalLayerTraitConst: Constant methods for crate::dnn::ProposalLayer
QuantizeLayerTrait: Mutable methods for crate::dnn::QuantizeLayer
QuantizeLayerTraitConst: Constant methods for crate::dnn::QuantizeLayer
RNNLayerTrait: Mutable methods for crate::dnn::RNNLayer
RNNLayerTraitConst: Constant methods for crate::dnn::RNNLayer
ReLU6LayerTrait: Mutable methods for crate::dnn::ReLU6Layer
ReLU6LayerTraitConst: Constant methods for crate::dnn::ReLU6Layer
ReLULayerTrait: Mutable methods for crate::dnn::ReLULayer
ReLULayerTraitConst: Constant methods for crate::dnn::ReLULayer
ReciprocalLayerTrait: Mutable methods for crate::dnn::ReciprocalLayer
ReciprocalLayerTraitConst: Constant methods for crate::dnn::ReciprocalLayer
ReduceLayerTrait: Mutable methods for crate::dnn::ReduceLayer
ReduceLayerTraitConst: Constant methods for crate::dnn::ReduceLayer
RegionLayerTrait: Mutable methods for crate::dnn::RegionLayer
RegionLayerTraitConst: Constant methods for crate::dnn::RegionLayer
ReorgLayerTrait: Mutable methods for crate::dnn::ReorgLayer
ReorgLayerTraitConst: Constant methods for crate::dnn::ReorgLayer
RequantizeLayerTrait: Mutable methods for crate::dnn::RequantizeLayer
RequantizeLayerTraitConst: Constant methods for crate::dnn::RequantizeLayer
ReshapeLayerTrait: Mutable methods for crate::dnn::ReshapeLayer
ReshapeLayerTraitConst: Constant methods for crate::dnn::ReshapeLayer
ResizeLayerTrait: Mutable methods for crate::dnn::ResizeLayer
ResizeLayerTraitConst: Constant methods for crate::dnn::ResizeLayer
RoundLayerTrait: Mutable methods for crate::dnn::RoundLayer
RoundLayerTraitConst: Constant methods for crate::dnn::RoundLayer
ScaleLayerInt8Trait: Mutable methods for crate::dnn::ScaleLayerInt8
ScaleLayerInt8TraitConst: Constant methods for crate::dnn::ScaleLayerInt8
ScaleLayerTrait: Mutable methods for crate::dnn::ScaleLayer
ScaleLayerTraitConst: Constant methods for crate::dnn::ScaleLayer
ScatterLayerTrait: Mutable methods for crate::dnn::ScatterLayer
ScatterLayerTraitConst: Constant methods for crate::dnn::ScatterLayer
ScatterNDLayerTrait: Mutable methods for crate::dnn::ScatterNDLayer
ScatterNDLayerTraitConst: Constant methods for crate::dnn::ScatterNDLayer
SegmentationModelTrait: Mutable methods for crate::dnn::SegmentationModel
SegmentationModelTraitConst: Constant methods for crate::dnn::SegmentationModel
SeluLayerTrait: Mutable methods for crate::dnn::SeluLayer
SeluLayerTraitConst: Constant methods for crate::dnn::SeluLayer
ShiftLayerInt8Trait: Mutable methods for crate::dnn::ShiftLayerInt8
ShiftLayerInt8TraitConst: Constant methods for crate::dnn::ShiftLayerInt8
ShiftLayerTrait: Mutable methods for crate::dnn::ShiftLayer
ShiftLayerTraitConst: Constant methods for crate::dnn::ShiftLayer
ShrinkLayerTrait: Mutable methods for crate::dnn::ShrinkLayer
ShrinkLayerTraitConst: Constant methods for crate::dnn::ShrinkLayer
ShuffleChannelLayerTrait: Mutable methods for crate::dnn::ShuffleChannelLayer
ShuffleChannelLayerTraitConst: Constant methods for crate::dnn::ShuffleChannelLayer
SigmoidLayerTrait: Mutable methods for crate::dnn::SigmoidLayer
SigmoidLayerTraitConst: Constant methods for crate::dnn::SigmoidLayer
SignLayerTrait: Mutable methods for crate::dnn::SignLayer
SignLayerTraitConst: Constant methods for crate::dnn::SignLayer
SinLayerTrait: Mutable methods for crate::dnn::SinLayer
SinLayerTraitConst: Constant methods for crate::dnn::SinLayer
SinhLayerTrait: Mutable methods for crate::dnn::SinhLayer
SinhLayerTraitConst: Constant methods for crate::dnn::SinhLayer
SliceLayerTrait: Mutable methods for crate::dnn::SliceLayer
SliceLayerTraitConst: Constant methods for crate::dnn::SliceLayer
SoftmaxLayerInt8Trait: Mutable methods for crate::dnn::SoftmaxLayerInt8
SoftmaxLayerInt8TraitConst: Constant methods for crate::dnn::SoftmaxLayerInt8
SoftmaxLayerTrait: Mutable methods for crate::dnn::SoftmaxLayer
SoftmaxLayerTraitConst: Constant methods for crate::dnn::SoftmaxLayer
SoftplusLayerTrait: Mutable methods for crate::dnn::SoftplusLayer
SoftplusLayerTraitConst: Constant methods for crate::dnn::SoftplusLayer
SoftsignLayerTrait: Mutable methods for crate::dnn::SoftsignLayer
SoftsignLayerTraitConst: Constant methods for crate::dnn::SoftsignLayer
SpaceToDepthLayerTrait: Mutable methods for crate::dnn::SpaceToDepthLayer
SpaceToDepthLayerTraitConst: Constant methods for crate::dnn::SpaceToDepthLayer
SplitLayerTrait: Mutable methods for crate::dnn::SplitLayer
SplitLayerTraitConst: Constant methods for crate::dnn::SplitLayer
SqrtLayerTrait: Mutable methods for crate::dnn::SqrtLayer
SqrtLayerTraitConst: Constant methods for crate::dnn::SqrtLayer
SwishLayerTrait: Mutable methods for crate::dnn::SwishLayer
SwishLayerTraitConst: Constant methods for crate::dnn::SwishLayer
TanHLayerTrait: Mutable methods for crate::dnn::TanHLayer
TanHLayerTraitConst: Constant methods for crate::dnn::TanHLayer
TanLayerTrait: Mutable methods for crate::dnn::TanLayer
TanLayerTraitConst: Constant methods for crate::dnn::TanLayer
TextDetectionModelTrait: Mutable methods for crate::dnn::TextDetectionModel
TextDetectionModelTraitConst: Constant methods for crate::dnn::TextDetectionModel
TextDetectionModel_DBTrait: Mutable methods for crate::dnn::TextDetectionModel_DB
TextDetectionModel_DBTraitConst: Constant methods for crate::dnn::TextDetectionModel_DB
TextDetectionModel_EASTTrait: Mutable methods for crate::dnn::TextDetectionModel_EAST
TextDetectionModel_EASTTraitConst: Constant methods for crate::dnn::TextDetectionModel_EAST
TextRecognitionModelTrait: Mutable methods for crate::dnn::TextRecognitionModel
TextRecognitionModelTraitConst: Constant methods for crate::dnn::TextRecognitionModel
ThresholdedReluLayerTrait: Mutable methods for crate::dnn::ThresholdedReluLayer
ThresholdedReluLayerTraitConst: Constant methods for crate::dnn::ThresholdedReluLayer
TileLayerTrait: Mutable methods for crate::dnn::TileLayer
TileLayerTraitConst: Constant methods for crate::dnn::TileLayer
TopKLayerTrait: Mutable methods for crate::dnn::TopKLayer
TopKLayerTraitConst: Constant methods for crate::dnn::TopKLayer
_RangeTrait: Mutable methods for crate::dnn::_Range
_RangeTraitConst: Constant methods for crate::dnn::_Range

Functions§

blob_from_image: Creates 4-dimensional blob from image. Optionally resizes and crops @p image from center, subtract @p mean values, scales values by @p scalefactor, swap Blue and Red channels.
blob_from_image_def: Creates 4-dimensional blob from image. Optionally resizes and crops @p image from center, subtract @p mean values, scales values by @p scalefactor, swap Blue and Red channels.
blob_from_image_to: Creates 4-dimensional blob from image. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
blob_from_image_to_def: Creates 4-dimensional blob from image. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
blob_from_image_with_params: Creates 4-dimensional blob from image with given params.
blob_from_image_with_params_1: Creates 4-dimensional blob from image with given params.
blob_from_image_with_params_1_def: @overload
blob_from_image_with_params_def: Creates 4-dimensional blob from image with given params.
blob_from_images: Creates 4-dimensional blob from series of images. Optionally resizes and crops @p images from center, subtract @p mean values, scales values by @p scalefactor, swap Blue and Red channels.
blob_from_images_def: Creates 4-dimensional blob from series of images. Optionally resizes and crops @p images from center, subtract @p mean values, scales values by @p scalefactor, swap Blue and Red channels.
blob_from_images_to: Creates 4-dimensional blob from series of images. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
blob_from_images_to_def: Creates 4-dimensional blob from series of images. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
blob_from_images_with_params: Creates 4-dimensional blob from series of images with given params.
blob_from_images_with_params_1: Creates 4-dimensional blob from series of images with given params.
blob_from_images_with_params_1_def: @overload
blob_from_images_with_params_def: Creates 4-dimensional blob from series of images with given params.
concat
enable_model_diagnostics: Enables detailed logging of the DNN model loading with CV DNN API.
get_available_backends
get_available_targets
get_inference_engine_backend_type: Returns Inference Engine internal backend API.
get_inference_engine_cpu_type: Returns Inference Engine CPU type.
get_inference_engine_vpu_type: Returns Inference Engine VPU type.
get_plane
images_from_blob: Parse a 4D blob and output the images it contains as 2D arrays through a simpler data structure (std::vectorcv::Mat).
nms_boxes: Performs non maximum suppression given boxes and corresponding scores.
nms_boxes_batched: Performs batched non maximum suppression on given boxes and corresponding scores across different classes.
nms_boxes_batched_1: C++ default parameters
nms_boxes_batched_1_def: Note
nms_boxes_batched_def: Performs batched non maximum suppression on given boxes and corresponding scores across different classes.
nms_boxes_def: Performs non maximum suppression given boxes and corresponding scores.
nms_boxes_f64: C++ default parameters
nms_boxes_f64_def: Note
nms_boxes_rotated: C++ default parameters
nms_boxes_rotated_def: Note
read_net: Read deep learning network represented in one of the supported formats.
read_net_1: Read deep learning network represented in one of the supported formats. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
read_net_1_def: Read deep learning network represented in one of the supported formats. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
read_net_def: Read deep learning network represented in one of the supported formats.
read_net_from_caffe: Reads a network model stored in Caffe framework’s format.
read_net_from_caffe_buffer: Reads a network model stored in Caffe model in memory.
read_net_from_caffe_buffer_def: Reads a network model stored in Caffe model in memory.
read_net_from_caffe_def: Reads a network model stored in Caffe framework’s format.
read_net_from_caffe_str: Reads a network model stored in Caffe model in memory. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
read_net_from_caffe_str_def: Reads a network model stored in Caffe model in memory. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
read_net_from_darknet: Reads a network model stored in Darknet model files.
read_net_from_darknet_buffer: Reads a network model stored in Darknet model files.
read_net_from_darknet_buffer_def: Reads a network model stored in Darknet model files.
read_net_from_darknet_def: Reads a network model stored in Darknet model files.
read_net_from_darknet_str: Reads a network model stored in Darknet model files.
read_net_from_darknet_str_def: Reads a network model stored in Darknet model files.
read_net_from_model_optimizer: Load a network from Intel’s Model Optimizer intermediate representation.
read_net_from_model_optimizer_1: Load a network from Intel’s Model Optimizer intermediate representation.
read_net_from_model_optimizer_2: Load a network from Intel’s Model Optimizer intermediate representation.
read_net_from_model_optimizer_def: Load a network from Intel’s Model Optimizer intermediate representation.
read_net_from_onnx: Reads a network model ONNX.
read_net_from_onnx_buffer: Reads a network model from ONNX in-memory buffer.
read_net_from_onnx_str: Reads a network model from ONNX in-memory buffer.
read_net_from_tensorflow: Reads a network model stored in TensorFlow framework’s format.
read_net_from_tensorflow_buffer: Reads a network model stored in TensorFlow framework’s format.
read_net_from_tensorflow_buffer_def: Reads a network model stored in TensorFlow framework’s format.
read_net_from_tensorflow_def: Reads a network model stored in TensorFlow framework’s format.
read_net_from_tensorflow_str: Reads a network model stored in TensorFlow framework’s format. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
read_net_from_tensorflow_str_def: Reads a network model stored in TensorFlow framework’s format. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
read_net_from_tf_lite: Reads a network model stored in TFLite framework’s format.
read_net_from_tf_lite_1: Reads a network model stored in TFLite framework’s format.
read_net_from_tf_lite_2: Reads a network model stored in TFLite framework’s format. @details This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
read_net_from_torch: Reads a network model stored in Torch7 framework’s format.
read_net_from_torch_def: Reads a network model stored in Torch7 framework’s format.
read_tensor_from_onnx: Creates blob from .pb file.
read_torch_blob: Loads blob which was serialized as torch.Tensor object of Torch7 framework. @warning This function has the same limitations as readNetFromTorch().
read_torch_blob_def: Loads blob which was serialized as torch.Tensor object of Torch7 framework. @warning This function has the same limitations as readNetFromTorch().
release_hddl_plugin: Release a HDDL plugin.
reset_myriad_device: Release a Myriad device (binded by OpenCV).
set_inference_engine_backend_type: Specify Inference Engine internal backend API.
shape
shape_1
shape_2
shape_3
shape_4: C++ default parameters
shape_4_def: Note
shrink_caffe_model: Convert all weights of Caffe network to half precision floating point.
shrink_caffe_model_def: Convert all weights of Caffe network to half precision floating point.
slice
slice_1
slice_2
slice_3
soft_nms_boxes: Performs soft non maximum suppression given boxes and corresponding scores. Reference: https://arxiv.org/abs/1704.04503
soft_nms_boxes_def: Performs soft non maximum suppression given boxes and corresponding scores. Reference: https://arxiv.org/abs/1704.04503
total: C++ default parameters
total_1: C++ default parameters
total_1_def: Note
total_def: Note
write_text_graph: Create a text representation for a binary network stored in protocol buffer format.

Type Aliases§

LayerFactory_Constructor: Each Layer class must provide this function to the factory
MatShape
Net_LayerIdDeprecated: Container for strings and integers.

Module dnnCopy item path