PLearn 0.1
|
Go to the source code of this file.
Classes | |
class | PLearn::OneHotSquaredLoss |
Computes sum(square_i(netout[i]-(i==classnum ?hotval :coldval)) This is used typically in a classification setting where netout is a Var of network outputs, and classnum is the target class number. More... | |
class | PLearn::DiffTemplate< ObjectType, OneHotSquaredLoss > |
class | PLearn::TypeTraits< OneHotSquaredLoss > |
Namespaces | |
namespace | PLearn |
< for swap | |
Functions | |
Object * | PLearn::toObjectPtr (const OneHotSquaredLoss &o) |
PStream & | PLearn::operator>> (PStream &in, OneHotSquaredLoss &o) |
PStream & | PLearn::operator>> (PStream &in, OneHotSquaredLoss *&o) |
PStream & | PLearn::operator<< (PStream &out, const OneHotSquaredLoss &o) |
PStream & | PLearn::operator>> (PStream &in, PP< OneHotSquaredLoss > &o) |
template<class ObjectType > | |
int | PLearn::diff (const string &refer, const string &other, const Option< ObjectType, OneHotSquaredLoss > *opt, PLearnDiff *diffs) |
Var | PLearn::onehot_squared_loss (Var network_output, Var classnum, real coldval=0., real hotval=1.) |