Activation¶
Abs¶
-
class
paddle.v2.activation.Abs Abs Activation.
Forward: \(f(z) = abs(z)\)
Derivative:
\[\begin{split}1 &\quad if \quad z > 0 \\ -1 &\quad if \quad z < 0 \\ 0 &\quad if \quad z = 0\end{split}\]
Exp¶
-
class
paddle.v2.activation.Exp Exponential Activation.
\[f(z) = e^z.\]
Identity¶
-
paddle.v2.activation.Identity Linear的别名
Linear¶
-
class
paddle.v2.activation.Linear Identity Activation.
Just do nothing for output both forward/backward.
Log¶
-
class
paddle.v2.activation.Log Logarithm Activation.
\[f(z) = log(z)\]
Square¶
-
class
paddle.v2.activation.Square Square Activation.
\[f(z) = z^2.\]
Sigmoid¶
-
class
paddle.v2.activation.Sigmoid Sigmoid activation.
\[f(z) = \frac{1}{1+exp(-z)}\]
Softmax¶
-
class
paddle.v2.activation.Softmax Softmax activation for simple input
\[P(y=j|x) = \frac{e^{x_j}} {\sum^K_{k=1} e^{x_j} }\]
SequenceSoftmax¶
-
class
paddle.v2.activation.SequenceSoftmax Softmax activation for one sequence. The dimension of input feature must be 1 and a sequence.
result = softmax(for each_feature_vector[0] in input_feature) for i, each_time_step_output in enumerate(output): each_time_step_output = result[i]
Relu¶
-
class
paddle.v2.activation.Relu Relu activation.
forward. \(y = max(0, z)\)
derivative:
\[\begin{split}1 &\quad if z > 0 \\ 0 &\quad\mathrm{otherwize}\end{split}\]
BRelu¶
-
class
paddle.v2.activation.BRelu BRelu Activation.
forward. \(y = min(24, max(0, z))\)
derivative:
\[\begin{split}1 &\quad if 0 < z < 24 \\ 0 &\quad \mathrm{otherwise}\end{split}\]
SoftRelu¶
-
class
paddle.v2.activation.SoftRelu SoftRelu Activation.
Tanh¶
-
class
paddle.v2.activation.Tanh Tanh activation.
\[f(z)=tanh(z)=\frac{e^z-e^{-z}}{e^z+e^{-z}}\]
STanh¶
-
class
paddle.v2.activation.STanh Scaled Tanh Activation.
\[f(z) = 1.7159 * tanh(2/3*z)\]
SoftSign¶
-
class
paddle.v2.activation.SoftSign SoftSign Activation.
\[f(z)=\frac{z}{1 + |z|}\]