Activations¶
-
namespace
paddle¶ -
class
ActivationFunction¶ Subclassed by paddle::IdentityActivation
Public Functions
-
ActivationFunction()¶
-
virtual
~ActivationFunction()¶
-
virtual const std::string &
getName() const = 0¶
Public Static Functions
-
ActivationFunction *
create(const std::string &type)¶
-
-
class
Defines
-
ACTIVATION_CLASS_NAME(ACTIVATION_NAME)¶
-
BEGIN_DEFINE_ACTIVATION(ACTIVATION_NAME)¶
-
END_DEFINE_ACTIVATION(ACTIVATION_NAME)¶
-
namespace
paddle¶ Functions
-
void
forward(Argument &act)¶ SigmoidActivation
f(z) = {1}{1+exp(-z)}
Relu Activation.
forward. y = max(0, z)
derivative of relu is:
1 if z > 0
0 otherwise.
BRelu Activation.
forward. y = min(24, max(0, z))
derivative of brelu is:
1 if 0 < z < 24
0 otherwise.
TODO(yuyang18): Remove magic number 24 or make it configuable.
tanh activation.
f(z) = tanh(z)={e^z-e^{-z}}{e^z+e^{-z}}
Soft relu activation.
f(z) = ln(1+e^z)
Abs Activation.
Forward: f(z) = abs(z)
Derivative:
1 if z>0
-1 if z<0
0 if z=0
Square Activation.
f(z) = z^2.
-
ACTIVATION_CLASS_NAME(softmax)¶ Softmax on all frames of one sequence. Width of frame must be one.
-
ACTIVATION_CLASS_NAME() paddle::stanh()
Variables
-
ClassRegistrar<ActivationFunction>
gActivationRegistrar¶
-
InitFunction paddle::__reg_activation__identity([]{gActivationRegistrar.registerClass< IdentityActivation >("");gActivationRegistrar.registerClass< IdentityActivation >("linear");})
-
MatrixPtr
sftMaxSum_¶ Do Softmax activation for all sample. P(y=j|x) = {e^{x^Tw_j}}{^K_{k=1}e^{x^Tw_k}}
-
real
a¶ Scaled Tanh Activation
f(z) = 1.7159 * tanh(2/3*z)
-
real
b¶
-
class
IdentityActivation¶ The IdentityActivation class.
Do nothing when forward/backward.
Inherits from paddle::ActivationFunction
Public Functions
-
virtual const std::string &
getName() const¶
Public Static Attributes
-
const std::string
name¶
-
virtual const std::string &
-
void