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§
Structs§
- AbsLayer
- Accum
Layer - Acos
Layer - Acosh
Layer - Activation
Layer - Activation
Layer Int8 - ArgLayer
- ArgMax/ArgMin layer
- Asin
Layer - Asinh
Layer - Atan
Layer - Atanh
Layer - Attention
Layer - BNLL
Layer - Backend
Node - Derivatives of this class encapsulates functions of certain backends.
- Backend
Wrapper - Derivatives of this class wraps cv::Mat for different backends and targets.
- Base
Convolution Layer - Batch
Norm Layer - Batch
Norm Layer Int8 - Blank
Layer - Partial List of Implemented Layers
- Ceil
Layer - Celu
Layer - ChannelsP
ReLU Layer - Classification
Model - This class represents high-level API for classification models.
- Compare
Layer - Concat
Layer - Const
Layer - Constant layer produces the same data blob at an every forward pass.
- Convolution
Layer - Convolution
Layer Int8 - Correlation
Layer - CosLayer
- Cosh
Layer - Crop
AndResize Layer - Crop
Layer - CumSum
Layer - Data
Augmentation Layer - Deconvolution
Layer - Depth
ToSpace Layer - Dequantize
Layer - Detection
Model - This class represents high-level API for object detection networks.
- Detection
Output Layer - Detection output layer.
- Dict
- This class implements name-value dictionary, values are instances of DictValue.
- Dict
Value - 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
- Einsum
Layer - This function performs array summation based on the Einstein summation convention. The function allows for concise expressions of various mathematical operations using subscripts.
- Eltwise
Layer - Element wise operation on inputs
- Eltwise
Layer Int8 - ErfLayer
- ExpLayer
- Expand
Layer - Flatten
Layer - Floor
Layer - Flow
Warp Layer - GRULayer
- GRU recurrent one-layer
- Gather
Elements Layer - 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
- Gather
Layer - Gather layer
- Gelu
Approximation Layer - Gelu
Layer - Gemm
Layer - Group
Norm Layer - Hard
Sigmoid Layer - Hard
Swish Layer - Image2
Blob Params - Processing params of image to blob.
- Inner
Product Layer InnerProduct
,MatMul
andGemm
operations are all implemented by Fully Connected Layer. Parameteris_matmul
is used to distinguishMatMul
andGemm
fromInnerProduct
.- Inner
Product Layer Int8 - Instance
Norm Layer - Interp
Layer - Bilinear resize layer from https://github.com/cdmh/deeplab-public-ver2
- Keypoints
Model - This class represents high-level API for keypoints models
- LRNLayer
- LSTM
Layer - LSTM recurrent layer
- Layer
- This interface class allows to build new Layers - are building blocks of networks.
- Layer
Factory - %Layer factory allows to create instances of registered layers.
- Layer
Norm Layer - Layer
Params - This class provides all data needed to initialize layer.
- LogLayer
- MVNLayer
- MatMul
Layer - MaxUnpool
Layer - Mish
Layer - Model
- This class is presented high-level API for neural networks.
- Nary
Eltwise Layer - Net
- This class allows to create and manipulate comprehensive artificial neural networks.
- NormalizeB
BoxLayer - inline formula - normalization layer.
- NotLayer
- Padding
Layer - Adds extra values for specific axes.
- Permute
Layer - Pooling
Layer - Pooling
Layer Int8 - Power
Layer - Prior
BoxLayer - Proposal
Layer - Quantize
Layer - RNNLayer
- Classical recurrent layer
- ReLU6
Layer - ReLU
Layer - Reciprocal
Layer - Reduce
Layer - Region
Layer - Reorg
Layer - Requantize
Layer - Reshape
Layer - Resize
Layer - Resize input 4-dimensional blob by nearest neighbor or bilinear strategy.
- Round
Layer - Scale
Layer - Scale
Layer Int8 - Scatter
Layer - ScatterND
Layer - Segmentation
Model - This class represents high-level API for segmentation models
- Selu
Layer - Shift
Layer - Shift
Layer Int8 - Shrink
Layer - Shuffle
Channel Layer - Permute channels of 4-dimensional input blob.
- Sigmoid
Layer - Sign
Layer - SinLayer
- Sinh
Layer - Slice
Layer - Slice layer has several modes:
- Softmax
Layer - Softmax
Layer Int8 - Softplus
Layer - Softsign
Layer - Space
ToDepth Layer - Split
Layer - Sqrt
Layer - Swish
Layer - TanH
Layer - TanLayer
- Text
Detection Model - Base class for text detection networks
- Text
Detection Model_ DB - This class represents high-level API for text detection DL networks compatible with DB model.
- Text
Detection Model_ EAST - This class represents high-level API for text detection DL networks compatible with EAST model.
- Text
Recognition Model - This class represents high-level API for text recognition networks.
- Thresholded
Relu Layer - Tile
Layer - TopK
Layer - _Range
Enums§
- Backend
- Enum of computation backends supported by layers.
- Data
Layout - Enum of data layout for model inference.
- Image
Padding Mode - 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. - SoftNMS
Method - 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 - SoftNMS
Method_ SOFTNMS_ GAUSSIAN - SoftNMS
Method_ SOFTNMS_ LINEAR
Traits§
- AbsLayer
Trait - Mutable methods for crate::dnn::AbsLayer
- AbsLayer
Trait Const - Constant methods for crate::dnn::AbsLayer
- Accum
Layer Trait - Mutable methods for crate::dnn::AccumLayer
- Accum
Layer Trait Const - Constant methods for crate::dnn::AccumLayer
- Acos
Layer Trait - Mutable methods for crate::dnn::AcosLayer
- Acos
Layer Trait Const - Constant methods for crate::dnn::AcosLayer
- Acosh
Layer Trait - Mutable methods for crate::dnn::AcoshLayer
- Acosh
Layer Trait Const - Constant methods for crate::dnn::AcoshLayer
- Activation
Layer Int8 Trait - Mutable methods for crate::dnn::ActivationLayerInt8
- Activation
Layer Int8 Trait Const - Constant methods for crate::dnn::ActivationLayerInt8
- Activation
Layer Trait - Mutable methods for crate::dnn::ActivationLayer
- Activation
Layer Trait Const - Constant methods for crate::dnn::ActivationLayer
- ArgLayer
Trait - Mutable methods for crate::dnn::ArgLayer
- ArgLayer
Trait Const - Constant methods for crate::dnn::ArgLayer
- Asin
Layer Trait - Mutable methods for crate::dnn::AsinLayer
- Asin
Layer Trait Const - Constant methods for crate::dnn::AsinLayer
- Asinh
Layer Trait - Mutable methods for crate::dnn::AsinhLayer
- Asinh
Layer Trait Const - Constant methods for crate::dnn::AsinhLayer
- Atan
Layer Trait - Mutable methods for crate::dnn::AtanLayer
- Atan
Layer Trait Const - Constant methods for crate::dnn::AtanLayer
- Atanh
Layer Trait - Mutable methods for crate::dnn::AtanhLayer
- Atanh
Layer Trait Const - Constant methods for crate::dnn::AtanhLayer
- Attention
Layer Trait - Mutable methods for crate::dnn::AttentionLayer
- Attention
Layer Trait Const - Constant methods for crate::dnn::AttentionLayer
- BNLL
Layer Trait - Mutable methods for crate::dnn::BNLLLayer
- BNLL
Layer Trait Const - Constant methods for crate::dnn::BNLLLayer
- Backend
Node Trait - Mutable methods for crate::dnn::BackendNode
- Backend
Node Trait Const - Constant methods for crate::dnn::BackendNode
- Backend
Wrapper Trait - Mutable methods for crate::dnn::BackendWrapper
- Backend
Wrapper Trait Const - Constant methods for crate::dnn::BackendWrapper
- Base
Convolution Layer Trait - Mutable methods for crate::dnn::BaseConvolutionLayer
- Base
Convolution Layer Trait Const - Constant methods for crate::dnn::BaseConvolutionLayer
- Batch
Norm Layer Int8 Trait - Mutable methods for crate::dnn::BatchNormLayerInt8
- Batch
Norm Layer Int8 Trait Const - Constant methods for crate::dnn::BatchNormLayerInt8
- Batch
Norm Layer Trait - Mutable methods for crate::dnn::BatchNormLayer
- Batch
Norm Layer Trait Const - Constant methods for crate::dnn::BatchNormLayer
- Blank
Layer Trait - Mutable methods for crate::dnn::BlankLayer
- Blank
Layer Trait Const - Constant methods for crate::dnn::BlankLayer
- Ceil
Layer Trait - Mutable methods for crate::dnn::CeilLayer
- Ceil
Layer Trait Const - Constant methods for crate::dnn::CeilLayer
- Celu
Layer Trait - Mutable methods for crate::dnn::CeluLayer
- Celu
Layer Trait Const - Constant methods for crate::dnn::CeluLayer
- ChannelsP
ReLU Layer Trait - Mutable methods for crate::dnn::ChannelsPReLULayer
- ChannelsP
ReLU Layer Trait Const - Constant methods for crate::dnn::ChannelsPReLULayer
- Classification
Model Trait - Mutable methods for crate::dnn::ClassificationModel
- Classification
Model Trait Const - Constant methods for crate::dnn::ClassificationModel
- Compare
Layer Trait - Mutable methods for crate::dnn::CompareLayer
- Compare
Layer Trait Const - Constant methods for crate::dnn::CompareLayer
- Concat
Layer Trait - Mutable methods for crate::dnn::ConcatLayer
- Concat
Layer Trait Const - Constant methods for crate::dnn::ConcatLayer
- Const
Layer Trait - Mutable methods for crate::dnn::ConstLayer
- Const
Layer Trait Const - Constant methods for crate::dnn::ConstLayer
- Convolution
Layer Int8 Trait - Mutable methods for crate::dnn::ConvolutionLayerInt8
- Convolution
Layer Int8 Trait Const - Constant methods for crate::dnn::ConvolutionLayerInt8
- Convolution
Layer Trait - Mutable methods for crate::dnn::ConvolutionLayer
- Convolution
Layer Trait Const - Constant methods for crate::dnn::ConvolutionLayer
- Correlation
Layer Trait - Mutable methods for crate::dnn::CorrelationLayer
- Correlation
Layer Trait Const - Constant methods for crate::dnn::CorrelationLayer
- CosLayer
Trait - Mutable methods for crate::dnn::CosLayer
- CosLayer
Trait Const - Constant methods for crate::dnn::CosLayer
- Cosh
Layer Trait - Mutable methods for crate::dnn::CoshLayer
- Cosh
Layer Trait Const - Constant methods for crate::dnn::CoshLayer
- Crop
AndResize Layer Trait - Mutable methods for crate::dnn::CropAndResizeLayer
- Crop
AndResize Layer Trait Const - Constant methods for crate::dnn::CropAndResizeLayer
- Crop
Layer Trait - Mutable methods for crate::dnn::CropLayer
- Crop
Layer Trait Const - Constant methods for crate::dnn::CropLayer
- CumSum
Layer Trait - Mutable methods for crate::dnn::CumSumLayer
- CumSum
Layer Trait Const - Constant methods for crate::dnn::CumSumLayer
- Data
Augmentation Layer Trait - Mutable methods for crate::dnn::DataAugmentationLayer
- Data
Augmentation Layer Trait Const - Constant methods for crate::dnn::DataAugmentationLayer
- Deconvolution
Layer Trait - Mutable methods for crate::dnn::DeconvolutionLayer
- Deconvolution
Layer Trait Const - Constant methods for crate::dnn::DeconvolutionLayer
- Depth
ToSpace Layer Trait - Mutable methods for crate::dnn::DepthToSpaceLayer
- Depth
ToSpace Layer Trait Const - Constant methods for crate::dnn::DepthToSpaceLayer
- Dequantize
Layer Trait - Mutable methods for crate::dnn::DequantizeLayer
- Dequantize
Layer Trait Const - Constant methods for crate::dnn::DequantizeLayer
- Detection
Model Trait - Mutable methods for crate::dnn::DetectionModel
- Detection
Model Trait Const - Constant methods for crate::dnn::DetectionModel
- Detection
Output Layer Trait - Mutable methods for crate::dnn::DetectionOutputLayer
- Detection
Output Layer Trait Const - Constant methods for crate::dnn::DetectionOutputLayer
- Dict
Trait - Mutable methods for crate::dnn::Dict
- Dict
Trait Const - Constant methods for crate::dnn::Dict
- Dict
Value Trait - Mutable methods for crate::dnn::DictValue
- Dict
Value Trait Const - Constant methods for crate::dnn::DictValue
- ELULayer
Trait - Mutable methods for crate::dnn::ELULayer
- ELULayer
Trait Const - Constant methods for crate::dnn::ELULayer
- Einsum
Layer Trait - Mutable methods for crate::dnn::EinsumLayer
- Einsum
Layer Trait Const - Constant methods for crate::dnn::EinsumLayer
- Eltwise
Layer Int8 Trait - Mutable methods for crate::dnn::EltwiseLayerInt8
- Eltwise
Layer Int8 Trait Const - Constant methods for crate::dnn::EltwiseLayerInt8
- Eltwise
Layer Trait - Mutable methods for crate::dnn::EltwiseLayer
- Eltwise
Layer Trait Const - Constant methods for crate::dnn::EltwiseLayer
- ErfLayer
Trait - Mutable methods for crate::dnn::ErfLayer
- ErfLayer
Trait Const - Constant methods for crate::dnn::ErfLayer
- ExpLayer
Trait - Mutable methods for crate::dnn::ExpLayer
- ExpLayer
Trait Const - Constant methods for crate::dnn::ExpLayer
- Expand
Layer Trait - Mutable methods for crate::dnn::ExpandLayer
- Expand
Layer Trait Const - Constant methods for crate::dnn::ExpandLayer
- Flatten
Layer Trait - Mutable methods for crate::dnn::FlattenLayer
- Flatten
Layer Trait Const - Constant methods for crate::dnn::FlattenLayer
- Floor
Layer Trait - Mutable methods for crate::dnn::FloorLayer
- Floor
Layer Trait Const - Constant methods for crate::dnn::FloorLayer
- Flow
Warp Layer Trait - Mutable methods for crate::dnn::FlowWarpLayer
- Flow
Warp Layer Trait Const - Constant methods for crate::dnn::FlowWarpLayer
- GRULayer
Trait - Mutable methods for crate::dnn::GRULayer
- GRULayer
Trait Const - Constant methods for crate::dnn::GRULayer
- Gather
Elements Layer Trait - Mutable methods for crate::dnn::GatherElementsLayer
- Gather
Elements Layer Trait Const - Constant methods for crate::dnn::GatherElementsLayer
- Gather
Layer Trait - Mutable methods for crate::dnn::GatherLayer
- Gather
Layer Trait Const - Constant methods for crate::dnn::GatherLayer
- Gelu
Approximation Layer Trait - Mutable methods for crate::dnn::GeluApproximationLayer
- Gelu
Approximation Layer Trait Const - Constant methods for crate::dnn::GeluApproximationLayer
- Gelu
Layer Trait - Mutable methods for crate::dnn::GeluLayer
- Gelu
Layer Trait Const - Constant methods for crate::dnn::GeluLayer
- Gemm
Layer Trait - Mutable methods for crate::dnn::GemmLayer
- Gemm
Layer Trait Const - Constant methods for crate::dnn::GemmLayer
- Group
Norm Layer Trait - Mutable methods for crate::dnn::GroupNormLayer
- Group
Norm Layer Trait Const - Constant methods for crate::dnn::GroupNormLayer
- Hard
Sigmoid Layer Trait - Mutable methods for crate::dnn::HardSigmoidLayer
- Hard
Sigmoid Layer Trait Const - Constant methods for crate::dnn::HardSigmoidLayer
- Hard
Swish Layer Trait - Mutable methods for crate::dnn::HardSwishLayer
- Hard
Swish Layer Trait Const - Constant methods for crate::dnn::HardSwishLayer
- Inner
Product Layer Int8 Trait - Mutable methods for crate::dnn::InnerProductLayerInt8
- Inner
Product Layer Int8 Trait Const - Constant methods for crate::dnn::InnerProductLayerInt8
- Inner
Product Layer Trait - Mutable methods for crate::dnn::InnerProductLayer
- Inner
Product Layer Trait Const - Constant methods for crate::dnn::InnerProductLayer
- Instance
Norm Layer Trait - Mutable methods for crate::dnn::InstanceNormLayer
- Instance
Norm Layer Trait Const - Constant methods for crate::dnn::InstanceNormLayer
- Interp
Layer Trait - Mutable methods for crate::dnn::InterpLayer
- Interp
Layer Trait Const - Constant methods for crate::dnn::InterpLayer
- Keypoints
Model Trait - Mutable methods for crate::dnn::KeypointsModel
- Keypoints
Model Trait Const - Constant methods for crate::dnn::KeypointsModel
- LRNLayer
Trait - Mutable methods for crate::dnn::LRNLayer
- LRNLayer
Trait Const - Constant methods for crate::dnn::LRNLayer
- LSTM
Layer Trait - Mutable methods for crate::dnn::LSTMLayer
- LSTM
Layer Trait Const - Constant methods for crate::dnn::LSTMLayer
- Layer
Factory Trait - Mutable methods for crate::dnn::LayerFactory
- Layer
Factory Trait Const - Constant methods for crate::dnn::LayerFactory
- Layer
Norm Layer Trait - Mutable methods for crate::dnn::LayerNormLayer
- Layer
Norm Layer Trait Const - Constant methods for crate::dnn::LayerNormLayer
- Layer
Params Trait - Mutable methods for crate::dnn::LayerParams
- Layer
Params Trait Const - Constant methods for crate::dnn::LayerParams
- Layer
Trait - Mutable methods for crate::dnn::Layer
- Layer
Trait Const - Constant methods for crate::dnn::Layer
- LogLayer
Trait - Mutable methods for crate::dnn::LogLayer
- LogLayer
Trait Const - Constant methods for crate::dnn::LogLayer
- MVNLayer
Trait - Mutable methods for crate::dnn::MVNLayer
- MVNLayer
Trait Const - Constant methods for crate::dnn::MVNLayer
- MatMul
Layer Trait - Mutable methods for crate::dnn::MatMulLayer
- MatMul
Layer Trait Const - Constant methods for crate::dnn::MatMulLayer
- MaxUnpool
Layer Trait - Mutable methods for crate::dnn::MaxUnpoolLayer
- MaxUnpool
Layer Trait Const - Constant methods for crate::dnn::MaxUnpoolLayer
- Mish
Layer Trait - Mutable methods for crate::dnn::MishLayer
- Mish
Layer Trait Const - Constant methods for crate::dnn::MishLayer
- Model
Trait - Mutable methods for crate::dnn::Model
- Model
Trait Const - Constant methods for crate::dnn::Model
- Nary
Eltwise Layer Trait - Mutable methods for crate::dnn::NaryEltwiseLayer
- Nary
Eltwise Layer Trait Const - Constant methods for crate::dnn::NaryEltwiseLayer
- NetTrait
- Mutable methods for crate::dnn::Net
- NetTrait
Const - Constant methods for crate::dnn::Net
- NormalizeB
BoxLayer Trait - Mutable methods for crate::dnn::NormalizeBBoxLayer
- NormalizeB
BoxLayer Trait Const - Constant methods for crate::dnn::NormalizeBBoxLayer
- NotLayer
Trait - Mutable methods for crate::dnn::NotLayer
- NotLayer
Trait Const - Constant methods for crate::dnn::NotLayer
- Padding
Layer Trait - Mutable methods for crate::dnn::PaddingLayer
- Padding
Layer Trait Const - Constant methods for crate::dnn::PaddingLayer
- Permute
Layer Trait - Mutable methods for crate::dnn::PermuteLayer
- Permute
Layer Trait Const - Constant methods for crate::dnn::PermuteLayer
- Pooling
Layer Int8 Trait - Mutable methods for crate::dnn::PoolingLayerInt8
- Pooling
Layer Int8 Trait Const - Constant methods for crate::dnn::PoolingLayerInt8
- Pooling
Layer Trait - Mutable methods for crate::dnn::PoolingLayer
- Pooling
Layer Trait Const - Constant methods for crate::dnn::PoolingLayer
- Power
Layer Trait - Mutable methods for crate::dnn::PowerLayer
- Power
Layer Trait Const - Constant methods for crate::dnn::PowerLayer
- Prior
BoxLayer Trait - Mutable methods for crate::dnn::PriorBoxLayer
- Prior
BoxLayer Trait Const - Constant methods for crate::dnn::PriorBoxLayer
- Proposal
Layer Trait - Mutable methods for crate::dnn::ProposalLayer
- Proposal
Layer Trait Const - Constant methods for crate::dnn::ProposalLayer
- Quantize
Layer Trait - Mutable methods for crate::dnn::QuantizeLayer
- Quantize
Layer Trait Const - Constant methods for crate::dnn::QuantizeLayer
- RNNLayer
Trait - Mutable methods for crate::dnn::RNNLayer
- RNNLayer
Trait Const - Constant methods for crate::dnn::RNNLayer
- ReLU6
Layer Trait - Mutable methods for crate::dnn::ReLU6Layer
- ReLU6
Layer Trait Const - Constant methods for crate::dnn::ReLU6Layer
- ReLU
Layer Trait - Mutable methods for crate::dnn::ReLULayer
- ReLU
Layer Trait Const - Constant methods for crate::dnn::ReLULayer
- Reciprocal
Layer Trait - Mutable methods for crate::dnn::ReciprocalLayer
- Reciprocal
Layer Trait Const - Constant methods for crate::dnn::ReciprocalLayer
- Reduce
Layer Trait - Mutable methods for crate::dnn::ReduceLayer
- Reduce
Layer Trait Const - Constant methods for crate::dnn::ReduceLayer
- Region
Layer Trait - Mutable methods for crate::dnn::RegionLayer
- Region
Layer Trait Const - Constant methods for crate::dnn::RegionLayer
- Reorg
Layer Trait - Mutable methods for crate::dnn::ReorgLayer
- Reorg
Layer Trait Const - Constant methods for crate::dnn::ReorgLayer
- Requantize
Layer Trait - Mutable methods for crate::dnn::RequantizeLayer
- Requantize
Layer Trait Const - Constant methods for crate::dnn::RequantizeLayer
- Reshape
Layer Trait - Mutable methods for crate::dnn::ReshapeLayer
- Reshape
Layer Trait Const - Constant methods for crate::dnn::ReshapeLayer
- Resize
Layer Trait - Mutable methods for crate::dnn::ResizeLayer
- Resize
Layer Trait Const - Constant methods for crate::dnn::ResizeLayer
- Round
Layer Trait - Mutable methods for crate::dnn::RoundLayer
- Round
Layer Trait Const - Constant methods for crate::dnn::RoundLayer
- Scale
Layer Int8 Trait - Mutable methods for crate::dnn::ScaleLayerInt8
- Scale
Layer Int8 Trait Const - Constant methods for crate::dnn::ScaleLayerInt8
- Scale
Layer Trait - Mutable methods for crate::dnn::ScaleLayer
- Scale
Layer Trait Const - Constant methods for crate::dnn::ScaleLayer
- Scatter
Layer Trait - Mutable methods for crate::dnn::ScatterLayer
- Scatter
Layer Trait Const - Constant methods for crate::dnn::ScatterLayer
- ScatterND
Layer Trait - Mutable methods for crate::dnn::ScatterNDLayer
- ScatterND
Layer Trait Const - Constant methods for crate::dnn::ScatterNDLayer
- Segmentation
Model Trait - Mutable methods for crate::dnn::SegmentationModel
- Segmentation
Model Trait Const - Constant methods for crate::dnn::SegmentationModel
- Selu
Layer Trait - Mutable methods for crate::dnn::SeluLayer
- Selu
Layer Trait Const - Constant methods for crate::dnn::SeluLayer
- Shift
Layer Int8 Trait - Mutable methods for crate::dnn::ShiftLayerInt8
- Shift
Layer Int8 Trait Const - Constant methods for crate::dnn::ShiftLayerInt8
- Shift
Layer Trait - Mutable methods for crate::dnn::ShiftLayer
- Shift
Layer Trait Const - Constant methods for crate::dnn::ShiftLayer
- Shrink
Layer Trait - Mutable methods for crate::dnn::ShrinkLayer
- Shrink
Layer Trait Const - Constant methods for crate::dnn::ShrinkLayer
- Shuffle
Channel Layer Trait - Mutable methods for crate::dnn::ShuffleChannelLayer
- Shuffle
Channel Layer Trait Const - Constant methods for crate::dnn::ShuffleChannelLayer
- Sigmoid
Layer Trait - Mutable methods for crate::dnn::SigmoidLayer
- Sigmoid
Layer Trait Const - Constant methods for crate::dnn::SigmoidLayer
- Sign
Layer Trait - Mutable methods for crate::dnn::SignLayer
- Sign
Layer Trait Const - Constant methods for crate::dnn::SignLayer
- SinLayer
Trait - Mutable methods for crate::dnn::SinLayer
- SinLayer
Trait Const - Constant methods for crate::dnn::SinLayer
- Sinh
Layer Trait - Mutable methods for crate::dnn::SinhLayer
- Sinh
Layer Trait Const - Constant methods for crate::dnn::SinhLayer
- Slice
Layer Trait - Mutable methods for crate::dnn::SliceLayer
- Slice
Layer Trait Const - Constant methods for crate::dnn::SliceLayer
- Softmax
Layer Int8 Trait - Mutable methods for crate::dnn::SoftmaxLayerInt8
- Softmax
Layer Int8 Trait Const - Constant methods for crate::dnn::SoftmaxLayerInt8
- Softmax
Layer Trait - Mutable methods for crate::dnn::SoftmaxLayer
- Softmax
Layer Trait Const - Constant methods for crate::dnn::SoftmaxLayer
- Softplus
Layer Trait - Mutable methods for crate::dnn::SoftplusLayer
- Softplus
Layer Trait Const - Constant methods for crate::dnn::SoftplusLayer
- Softsign
Layer Trait - Mutable methods for crate::dnn::SoftsignLayer
- Softsign
Layer Trait Const - Constant methods for crate::dnn::SoftsignLayer
- Space
ToDepth Layer Trait - Mutable methods for crate::dnn::SpaceToDepthLayer
- Space
ToDepth Layer Trait Const - Constant methods for crate::dnn::SpaceToDepthLayer
- Split
Layer Trait - Mutable methods for crate::dnn::SplitLayer
- Split
Layer Trait Const - Constant methods for crate::dnn::SplitLayer
- Sqrt
Layer Trait - Mutable methods for crate::dnn::SqrtLayer
- Sqrt
Layer Trait Const - Constant methods for crate::dnn::SqrtLayer
- Swish
Layer Trait - Mutable methods for crate::dnn::SwishLayer
- Swish
Layer Trait Const - Constant methods for crate::dnn::SwishLayer
- TanH
Layer Trait - Mutable methods for crate::dnn::TanHLayer
- TanH
Layer Trait Const - Constant methods for crate::dnn::TanHLayer
- TanLayer
Trait - Mutable methods for crate::dnn::TanLayer
- TanLayer
Trait Const - Constant methods for crate::dnn::TanLayer
- Text
Detection Model Trait - Mutable methods for crate::dnn::TextDetectionModel
- Text
Detection Model Trait Const - Constant methods for crate::dnn::TextDetectionModel
- Text
Detection Model_ DBTrait - Mutable methods for crate::dnn::TextDetectionModel_DB
- Text
Detection Model_ DBTrait Const - Constant methods for crate::dnn::TextDetectionModel_DB
- Text
Detection Model_ EAST Trait - Mutable methods for crate::dnn::TextDetectionModel_EAST
- Text
Detection Model_ EAST Trait Const - Constant methods for crate::dnn::TextDetectionModel_EAST
- Text
Recognition Model Trait - Mutable methods for crate::dnn::TextRecognitionModel
- Text
Recognition Model Trait Const - Constant methods for crate::dnn::TextRecognitionModel
- Thresholded
Relu Layer Trait - Mutable methods for crate::dnn::ThresholdedReluLayer
- Thresholded
Relu Layer Trait Const - Constant methods for crate::dnn::ThresholdedReluLayer
- Tile
Layer Trait - Mutable methods for crate::dnn::TileLayer
- Tile
Layer Trait Const - Constant methods for crate::dnn::TileLayer
- TopK
Layer Trait - Mutable methods for crate::dnn::TopKLayer
- TopK
Layer Trait Const - Constant methods for crate::dnn::TopKLayer
- _Range
Trait - Mutable methods for crate::dnn::_Range
- _Range
Trait Const - 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§
- Layer
Factory_ Constructor - Each Layer class must provide this function to the factory
- MatShape
- Net_
Layer Id Deprecated - Container for strings and integers.