Classes
class	cv::dnn::AbsLayer

class	cv::dnn::BaseConvolutionLayer

class	cv::dnn::BNLLLayer

class	cv::dnn::ConcatLayer

class	cv::dnn::ConvolutionLayer

class	cv::dnn::CropLayer

class	cv::dnn::DeconvolutionLayer

class	cv::dnn::EltwiseLayer

class	cv::dnn::InnerProductLayer

class	cv::dnn::LRNLayer

class	cv::dnn::LSTMLayer
	LSTM recurrent layer. More...

class	cv::dnn::MVNLayer

class	cv::dnn::PoolingLayer

class	cv::dnn::PowerLayer

class	cv::dnn::ReLULayer

class	cv::dnn::ReshapeLayer

class	cv::dnn::RNNLayer
	Classical recurrent layer. More...

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 bult-in layers and their descriptions.

Classes listed here, in fact, provides C++ API for creating intances of bult-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 convinient for native C++ programming and basically designed for use inside importers (see Importer, createCaffeImporter(), createTorchImporter()).

Bult-in layers partially reproduce functionality of corresponding Caffe and Torch7 layers. In partuclar, the following layers and Caffe Importer were tested to reproduce Caffe functionality:

Convolution
Deconvolution
Pooling
InnerProduct
TanH, ReLU, Sigmoid, BNLL, Power, AbsVal
Softmax
Reshape, Flatten, Slice, Split
LRN
MVN
Dropout (since it does nothing on forward pass -))