libeblearn
|
This module applies a gain per unit (like a diagonal linear module). More...
#include <ebl_basic.h>
Public Member Functions | |
diag_module (parameter< T, Tstate > *p, intg thickness, const char *name="diag") | |
virtual | ~diag_module () |
Destructor. | |
virtual void | fprop (Tstate &in, Tstate &out) |
forward propagation from in to out | |
virtual void | bprop (Tstate &in, Tstate &out) |
backward propagation from out to in | |
virtual void | bbprop (Tstate &in, Tstate &out) |
second-derivative backward propagation from out to in | |
virtual bool | resize_output (Tstate &in, Tstate &out) |
virtual void | load_x (idx< T > &weights) |
Copy passed weights into x component of internal weights. | |
virtual std::string | describe () |
Returns a string describing this module and its parameters. | |
virtual diag_module< T, Tstate > * | copy (parameter< T, Tstate > *p=NULL) |
Protected Attributes | |
Tstate | coeff |
This module applies a gain per unit (like a diagonal linear module).
ebl::diag_module< T, Tstate >::diag_module | ( | parameter< T, Tstate > * | p, |
intg | thickness, | ||
const char * | name = "diag" |
||
) |
Constructor.
p | is used to store all parametric variables in a single place. If p is null, a local buffer will be used. |
thickness | The number of feature maps. |
diag_module< T, Tstate > * ebl::diag_module< T, Tstate >::copy | ( | parameter< T, Tstate > * | p = NULL | ) | [virtual] |
Returns a deep copy of this module.
p | If NULL, reuse current parameter space, otherwise allocate new weights on parameter 'p'. |
Reimplemented from ebl::module_1_1< T, Tstate >.
bool ebl::diag_module< T, Tstate >::resize_output | ( | Tstate & | in, |
Tstate & | out | ||
) | [virtual] |
resize the output based on input dimensions This returns true if output was resized/reallocated, false otherwise.