OpenCV  4.0.0-beta
Open Source Computer Vision
Classes
Partial List of Implemented Layers

Classes

class  cv::dnn::AbsLayer
 
class  cv::dnn::ActivationLayer
 
class  cv::dnn::BaseConvolutionLayer
 
class  cv::dnn::BatchNormLayer
 
class  cv::dnn::BlankLayer
 
class  cv::dnn::BNLLLayer
 
class  cv::dnn::ChannelsPReLULayer
 
class  cv::dnn::ConcatLayer
 
class  cv::dnn::ConvolutionLayer
 
class  cv::dnn::CropAndResizeLayer
 
class  cv::dnn::CropLayer
 
class  cv::dnn::DeconvolutionLayer
 
class  cv::dnn::DetectionOutputLayer
 
class  cv::dnn::EltwiseLayer
 
class  cv::dnn::ELULayer
 
class  cv::dnn::FlattenLayer
 
class  cv::dnn::InnerProductLayer
 
class  cv::dnn::InterpLayer
 Bilinear resize layer from https://github.com/cdmh/deeplab-public. More...
 
class  cv::dnn::LRNLayer
 
class  cv::dnn::LSTMLayer
 LSTM recurrent layer. More...
 
class  cv::dnn::MaxUnpoolLayer
 
class  cv::dnn::MVNLayer
 
class  cv::dnn::NormalizeBBoxLayer
 \( L_p \) - normalization layer. More...
 
class  cv::dnn::PaddingLayer
 Adds extra values for specific axes. More...
 
class  cv::dnn::PermuteLayer
 
class  cv::dnn::PoolingLayer
 
class  cv::dnn::PowerLayer
 
class  cv::dnn::PriorBoxLayer
 
class  cv::dnn::ProposalLayer
 
class  cv::dnn::RegionLayer
 
class  cv::dnn::ReLU6Layer
 
class  cv::dnn::ReLULayer
 
class  cv::dnn::ReorgLayer
 
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::ScaleLayer
 
class  cv::dnn::ShiftLayer
 
class  cv::dnn::ShuffleChannelLayer
 
class  cv::dnn::SigmoidLayer
 
class  cv::dnn::SliceLayer
 
class  cv::dnn::SoftmaxLayer
 
class  cv::dnn::SplitLayer
 
class  cv::dnn::TanHLayer
 

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: