Collaboration diagram for CvConvNet:
Public Member Functions
|double||fprop (CvArr *input)|
|Forward-propagation of input image through the whole network. |
|const CvMat *||getplane (std::string id)|
|Provides access to individual planes inside the network. |
|Produces string representation of the convolutional net. |
|int||fromString (std::string xml)|
|Creates the convolutional net from a string representation. |
|std::vector< CvGenericPlane * >||m_plane|
|The container of the planes. |
|std::map< std::string, int >||m_idmap|
|Hash table mapping string ids into int ids. |
|Name of creator of the network. |
|Name of the network itself. |
|Any additional info about the network. |
|std::ostream &||operator<< (std::ostream &s, CvConvNet &n)|
|Output of the network into stream. |
|std::istream &||operator>> (std::istream &s, CvConvNet &n)|
|[Not implemented yet] |
The class is a container of individual feature maps (called planes) of the convolutional neural network. The class also defines basic methods to operate with the network such as saving the network as an XML string, loading the network from a string, accessing values of individual planes inside hidden layers etc.
testimg.cpp, and testmnist.cpp.
Definition at line 63 of file cvconvnet.h.
|double CvConvNet::fprop||(||CvArr *||input||)|
Forward-propagation of input image through the whole network.
The method propagates the input image through the whole network updating planes (feature maps) of each individual neuron. Each plane values can be accessed after fprop for further analysis.
|input||pointer to input image in CvMat or IplImage format|
Referenced by main().
|const CvMat * CvConvNet::getplane||(||std::string||id||)|
Provides access to individual planes inside the network.
The method returns a pointer to matrix of any individual feature map inside the network The plane is specified by its text id (it is the same id that is assigned to plane in XML file).
|id||String specifying the feature map to be accessed|
Produces string representation of the convolutional net.
Method produces an XML representation of the complete structure of the convolutional network including information about connections between planes, weights for specific connections. The representation does NOT include current state of the network such as propagated values at each plane (feature map).
Creates the convolutional net from a string representation.
The method creates Convolutional Net from its string XML representation
|xml||XML-string representing the network|
Referenced by main().
|std::ostream& operator<<||(||std::ostream &||s,|
|std::istream& operator>>||(||std::istream &||s,|
|std::map<std::string, int> CvConvNet::m_idmap