#include <MatrixAffineTransformVariable.h>
Inheritance diagram for PLearn::MatrixAffineTransformVariable:
Public Member Functions | |
MatrixAffineTransformVariable () | |
Default constructor for persistence. | |
MatrixAffineTransformVariable (Variable *mat, Variable *transformation) | |
PLEARN_DECLARE_OBJECT (MatrixAffineTransformVariable) | |
virtual void | recomputeSize (int &l, int &w) const |
Recomputes the length l and width w that this variable should have, according to its parent variables. | |
virtual void | fprop () |
compute output given input | |
virtual void | bprop () |
virtual void | symbolicBprop () |
compute a piece of new Var graph that represents the symbolic derivative of this Var | |
Private Types | |
typedef BinaryVariable | inherited |
Should work for both column and row vectors: result vector will be of same kind (row or col) First row of transformation matrix contains bias b, following rows contain linear-transformation T Will compute b + x.T which is equivalent to b +
Definition at line 57 of file MatrixAffineTransformVariable.h.
|
Reimplemented from PLearn::BinaryVariable. Definition at line 59 of file MatrixAffineTransformVariable.h. |
|
Default constructor for persistence.
Definition at line 63 of file MatrixAffineTransformVariable.h. |
|
Definition at line 64 of file MatrixAffineTransformVariable.h. |
|
Implements PLearn::Variable. Definition at line 76 of file MatrixAffineTransformVariable.cc. References PLearn::TMat< T >::firstRow(), PLearn::Variable::length(), PLearn::TMat< T >::length(), PLearn::productAcc(), PLearn::productTransposeAcc(), PLearn::TMat< T >::subMatRows(), PLearn::Vec, and PLearn::Variable::width(). |
|
compute output given input
Implements PLearn::Variable. Definition at line 66 of file MatrixAffineTransformVariable.cc. References PLearn::Variable::length(), PLearn::Var::length(), PLearn::Mat, PLearn::transposeProductAcc(), and PLearn::Variable::width(). |
|
|
|
Recomputes the length l and width w that this variable should have, according to its parent variables. This is used for ex. by sizeprop() The default version stupidly returns the current dimensions, so make sure to overload it in subclasses if this is not appropriate. Reimplemented from PLearn::Variable. Definition at line 56 of file MatrixAffineTransformVariable.cc. References PLearn::Var::width(). |
|
compute a piece of new Var graph that represents the symbolic derivative of this Var
Reimplemented from PLearn::Variable. Definition at line 97 of file MatrixAffineTransformVariable.cc. References PLearn::Var::length(), and PLearn::Var::width(). |