OpenCV  4.10.0-dev
Open Source Computer Vision
Classes
Partial List of Implemented Layers

Detailed Description

This subsection of dnn module contains information about built-in layers and their descriptions.

Classes listed here, in fact, provides C++ API for creating instances of built-in layers. In addition to this way of layers instantiation, there is a more common factory API (see Utilities for New Layers Registration), it allows to create layers dynamically (by name) and register new ones. You can use both API, but factory API is less convenient for native C++ programming and basically designed for use inside importers (see readNetFromCaffe(), readNetFromTorch(), readNetFromTensorflow()).

Built-in layers partially reproduce functionality of corresponding Caffe and Torch7 layers. In particular, the following layers and Caffe importer were tested to reproduce Caffe functionality:

Classes

class  cv::dnn::AbsLayer
 
class  cv::dnn::AccumLayer
 
class  cv::dnn::AcoshLayer
 
class  cv::dnn::AcosLayer
 
class  cv::dnn::ActivationLayer
 
class  cv::dnn::ActivationLayerInt8
 
class  cv::dnn::ArgLayer
 ArgMax/ArgMin layer. More...
 
class  cv::dnn::AsinhLayer
 
class  cv::dnn::AsinLayer
 
class  cv::dnn::AtanhLayer
 
class  cv::dnn::AtanLayer
 
class  cv::dnn::AttentionLayer
 
class  cv::dnn::BaseConvolutionLayer
 
class  cv::dnn::BatchNormLayer
 
class  cv::dnn::BatchNormLayerInt8
 
class  cv::dnn::BlankLayer
 
class  cv::dnn::BNLLLayer
 
class  cv::dnn::CeilLayer
 
class  cv::dnn::CeluLayer
 
class  cv::dnn::ChannelsPReLULayer
 
class  cv::dnn::CompareLayer
 
class  cv::dnn::ConcatLayer
 
class  cv::dnn::ConstLayer
 
class  cv::dnn::ConvolutionLayer
 
class  cv::dnn::ConvolutionLayerInt8
 
class  cv::dnn::CorrelationLayer
 
class  cv::dnn::CoshLayer
 
class  cv::dnn::CosLayer
 
class  cv::dnn::CropAndResizeLayer
 
class  cv::dnn::CropLayer
 
class  cv::dnn::CumSumLayer
 
class  cv::dnn::DataAugmentationLayer
 
class  cv::dnn::DeconvolutionLayer
 
class  cv::dnn::DepthToSpaceLayer
 
class  cv::dnn::DequantizeLayer
 
class  cv::dnn::DetectionOutputLayer
 Detection output layer. More...
 
class  cv::dnn::EinsumLayer
 This function performs array summation based on the Einstein summation convention. The function allows for concise expressions of various mathematical operations using subscripts. More...
 
class  cv::dnn::EltwiseLayer
 Element wise operation on inputs. More...
 
class  cv::dnn::EltwiseLayerInt8
 
class  cv::dnn::ELULayer
 
class  cv::dnn::ErfLayer
 
class  cv::dnn::ExpandLayer
 
class  cv::dnn::ExpLayer
 
class  cv::dnn::FlattenLayer
 
class  cv::dnn::FloorLayer
 
class  cv::dnn::FlowWarpLayer
 
class  cv::dnn::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. More...
 
class  cv::dnn::GatherLayer
 Gather layer. More...
 
class  cv::dnn::GeluApproximationLayer
 
class  cv::dnn::GeluLayer
 
class  cv::dnn::GemmLayer
 
class  cv::dnn::GroupNormLayer
 
class  cv::dnn::GRULayer
 GRU recurrent one-layer. More...
 
class  cv::dnn::HardSigmoidLayer
 
class  cv::dnn::HardSwishLayer
 
class  cv::dnn::InnerProductLayer
 
class  cv::dnn::InnerProductLayerInt8
 
class  cv::dnn::InstanceNormLayer
 
class  cv::dnn::InterpLayer
 Bilinear resize layer from https://github.com/cdmh/deeplab-public-ver2. More...
 
class  cv::dnn::LayerNormLayer
 
class  cv::dnn::LogLayer
 
class  cv::dnn::LRNLayer
 
class  cv::dnn::LSTMLayer
 LSTM recurrent layer. More...
 
class  cv::dnn::MatMulLayer
 
class  cv::dnn::MaxUnpoolLayer
 
class  cv::dnn::MishLayer
 
class  cv::dnn::MVNLayer
 
class  cv::dnn::NaryEltwiseLayer
 
class  cv::dnn::NormalizeBBoxLayer
 \( L_p \) - normalization layer. More...
 
class  cv::dnn::NotLayer
 
class  cv::dnn::PaddingLayer
 Adds extra values for specific axes. More...
 
class  cv::dnn::PermuteLayer
 
class  cv::dnn::PoolingLayer
 
class  cv::dnn::PoolingLayerInt8
 
class  cv::dnn::PowerLayer
 
class  cv::dnn::PriorBoxLayer
 
class  cv::dnn::ProposalLayer
 
class  cv::dnn::QuantizeLayer
 
class  cv::dnn::ReciprocalLayer
 
class  cv::dnn::ReduceLayer
 
class  cv::dnn::RegionLayer
 
class  cv::dnn::ReLU6Layer
 
class  cv::dnn::ReLULayer
 
class  cv::dnn::ReorgLayer
 
class  cv::dnn::RequantizeLayer
 
class  cv::dnn::ReshapeLayer
 
class  cv::dnn::ResizeLayer
 Resize input 4-dimensional blob by nearest neighbor or bilinear strategy. More...
 
class  cv::dnn::RNNLayer
 Classical recurrent layer. More...
 
class  cv::dnn::RoundLayer
 
class  cv::dnn::ScaleLayer
 
class  cv::dnn::ScaleLayerInt8
 
class  cv::dnn::ScatterLayer
 
class  cv::dnn::ScatterNDLayer
 
class  cv::dnn::SeluLayer
 
class  cv::dnn::ShiftLayer
 
class  cv::dnn::ShiftLayerInt8
 
class  cv::dnn::ShrinkLayer
 
class  cv::dnn::ShuffleChannelLayer
 
class  cv::dnn::SigmoidLayer
 
class  cv::dnn::SignLayer
 
class  cv::dnn::SinhLayer
 
class  cv::dnn::SinLayer
 
class  cv::dnn::SliceLayer
 
class  cv::dnn::SoftmaxLayer
 
class  cv::dnn::SoftmaxLayerInt8
 
class  cv::dnn::SoftplusLayer
 
class  cv::dnn::SoftsignLayer
 
class  cv::dnn::SpaceToDepthLayer
 
class  cv::dnn::SplitLayer
 
class  cv::dnn::SqrtLayer
 
class  cv::dnn::SwishLayer
 
class  cv::dnn::TanHLayer
 
class  cv::dnn::TanLayer
 
class  cv::dnn::ThresholdedReluLayer
 
class  cv::dnn::TileLayer
 
class  cv::dnn::TopKLayer