Softmax converts a real vector to a vector of categorical probabilities.
The elements of the output vector are in range (0, 1) and sum to 1.
Each vector is handled independently. The axis
argument sets which axis of the
input the function is applied along.
Softmax is often used as the activation for the last layer of a classification network because the result could be interpreted as a probability distribution.
The softmax of each vector x is computed as: exp(x) / tf.sum(exp(x))
.
The input values in are the log-odds of the resulting probability.
Public Constructors
Softmax(Ops tf)
Creates a softmax activation where the default axis is
ERROR(/#AXIS_DEFAULT) which indicates
the last dimension. |
|
Softmax(Ops tf, int axis)
Creates a Softmax activation
|
Public Methods
Operand<T> |
Inherited Methods
Public Constructors
public Softmax (Ops tf)
Creates a softmax activation where the default axis is ERROR(/#AXIS_DEFAULT)
which indicates
the last dimension.
Parameters
tf | the TensorFlow Ops |
---|
public Softmax (Ops tf, int axis)
Creates a Softmax activation
Parameters
tf | the TensorFlow Ops |
---|---|
axis | The dimension softmax would be performed on. |