Deep Neural Network module

Modules
	Partial List of Implemented Layers
	Utilities for New Layers Registration

Classes
class	cv::dnn::Blob
	This class provides methods for continuous n-dimensional CPU and GPU array processing. More...
struct	cv::dnn::BlobShape
	Lightweight class for storing and processing a shape of blob (or anything else). More...
class	cv::dnn::Dict
	This class implements name-value dictionary, values are instances of DictValue. More...
struct	cv::dnn::DictValue
	This struct stores the scalar value (or array) of one of the following type: double, cv::String or int64. More...
class	cv::dnn::Importer
	Small interface class for loading trained serialized models of different dnn-frameworks. More...
class	cv::dnn::Layer
	This interface class allows to build new Layers - are building blocks of networks. More...
class	cv::dnn::LayerParams
	This class provides all data needed to initialize layer. More...
class	cv::dnn::Net
	This class allows to create and manipulate comprehensive artificial neural networks. More...

Functions
Ptr< Importer >	cv::dnn::createCaffeImporter (const String &prototxt, const String &caffeModel=String())
	Creates the importer of Caffe framework network. More...
Ptr< Importer >	cv::dnn::createTorchImporter (const String &filename, bool isBinary=true)
	Creates the importer of Torch7 framework network. More...
void	cv::dnn::initModule ()
	Initialize dnn module and built-in layers. More...
Blob	cv::dnn::readTorchBlob (const String &filename, bool isBinary=true)
	Loads blob which was serialized as torch.Tensor object of Torch7 framework. More...

Detailed Description

This module contains:

• API for new layers creation, layers are building bricks of neural networks;
• set of built-in most-useful Layers;
• API to constuct and modify comprehensive neural networks from layers;
• functionality for loading serialized networks models from differnet frameworks.

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

Function Documentation

Ptr<Importer> cv::dnn::createCaffeImporter	(	const String &	prototxt,
		const String &	caffeModel = String()
	)

Creates the importer of Caffe framework network.

Parameters

prototxt	path to the .prototxt file with text description of the network architecture.
caffeModel	path to the .caffemodel file with learned network.

Returns

Pointer to the created importer, NULL in failure cases.

Ptr<Importer> cv::dnn::createTorchImporter	(	const String &	filename,
		bool	isBinary = true
	)

Creates the importer of Torch7 framework network.

Parameters

filename	path to the file, dumped from Torch by using torch.save() function.
isBinary	specifies whether the network was serialized in ascii mode or binary.

Returns

Pointer to the created importer, NULL in failure cases.

Warning

Torch7 importer is experimental now, you need explicitly set CMake opencv_dnn_BUILD_TORCH_IMPORTER flag to compile its.

Note

Ascii mode of Torch serializer is more preferable, because binary mode extensively use long type of C language, which has various bit-length on different systems.

The loading file must contain serialized nn.Module object with importing network. Try to eliminate a custom objects from serialazing data to avoid importing errors.

List of supported layers (i.e. object instances derived from Torch nn.Module class):

• nn.Sequential
• nn.Parallel
• nn.Concat
• nn.Linear
• nn.SpatialConvolution
• nn.SpatialMaxPooling, nn.SpatialAveragePooling
• nn.ReLU, nn.TanH, nn.Sigmoid
• nn.Reshape

Also some equivalents of these classes from cunn, cudnn, and fbcunn may be successfully imported.

void cv::dnn::initModule

(

)

Initialize dnn module and built-in layers.

This function automatically called on most of OpenCV builds, but you need to call it manually on some specific configurations (iOS for example).

Blob cv::dnn::readTorchBlob	(	const String &	filename,
		bool	isBinary = true
	)

Loads blob which was serialized as torch.Tensor object of Torch7 framework.

Warning

This function has the same limitations as createTorchImporter().