libeblearn
|
#include <ebl_machines.h>
Public Member Functions | |
lenet7_binocular (parameter< T, Tstate > &prm, intg image_height, intg image_width, intg output_size, bool norm=false, bool mirror=false, bool tanh=false, bool shrink=false, bool diag=false) |
Lenet7_binocular, similar to lenet5 with different neural connections. This network expects a 2-layer image containing each stereoscopic left and right images.
ebl::lenet7_binocular< T, Tstate >::lenet7_binocular | ( | parameter< T, Tstate > & | prm, |
intg | image_height, | ||
intg | image_width, | ||
intg | output_size, | ||
bool | norm = false , |
||
bool | mirror = false , |
||
bool | tanh = false , |
||
bool | shrink = false , |
||
bool | diag = false |
||
) |
output_size | the number of ouputs. For a 5 class classifier like NORB, this would be 5. |