Refine comment for CRF related headers. (#117)

paddle/gserver/layers/CRFLayer.h

@@ -25,7 +25,7 @@ namespace paddle {
 /**
  * A layer for calculating the cost of sequential conditional random field
  * model.
- * See LinearChainCRF.h for the detail of the CRF formulation.
+ * See class LinearChainCRF for the detail of the CRF formulation.
  */
 class CRFLayer : public Layer {
 public:

paddle/gserver/layers/LinearChainCRF.h

@@ -21,39 +21,39 @@ namespace paddle {
 
 class LinearChainCRF {
 public:
-  /*
-    The size of para and grad must be (numClasses + 2) * numClasses.
-    The first numClasses values of para are for starting weights (a).
-    The next numClasses values of para are for ending weights (b),
-    The remaning values are for transition weights (w).
-
-    The probability of a state sequence s of length L is defined as:
-    P(s) = (1/Z) exp(a_{s_1} + b_{s_L}
-                     + \sum_{l=1}^L x_{s_l}
-                     + \sum_{l=2}^L w_{s_{l-1},s_l})
-    where Z is a normalization value so that the sum of P(s) over all possible
-    sequences is 1, and x is the input feature to the CRF.
+  /**
+   * The size of para and grad must be \f$(numClasses + 2) * numClasses\f$.
+   * The first numClasses values of para are for starting weights (\f$a\f$).
+   * The next numClasses values of para are for ending weights (\f$b\f$),
+   * The remaning values are for transition weights (\f$w\f$).
+   *
+   * The probability of a state sequence s of length \f$L\f$ is defined as:
+   * \f$P(s) = (1/Z) exp(a_{s_1} + b_{s_L}
+   *                  + \sum_{l=1}^L x_{s_l}
+   *                  + \sum_{l=2}^L w_{s_{l-1},s_l})\f$
+   * where \f$Z\f$ is a normalization value so that the sum of \f$P(s)\f$ over all possible
+   * sequences is \f$1\f$, and \f$x\f$ is the input feature to the CRF.
    */
   LinearChainCRF(int numClasses, real* para, real* grad);
 
-  /*
-    Calculate the negative log likelihood of s given x.
-    The size of x must be length * numClasses. Each consecutive numClasses
-    values are the features for one time step.
+  /**
+   * Calculate the negative log likelihood of s given x.
+   * The size of x must be length * numClasses. Each consecutive numClasses
+   * values are the features for one time step.
    */
   real forward(real* x, int* s, int length);
 
-  /*
-    Calculate the gradient with respect to x, a, b, and w.
-    The gradient of x will be stored in dx.
-    backward() can only be called after a corresponding call to forward() with
-    the same x, s and length.
-    NOTE: The gradient is added to dx and grad (provided at constructor).
+  /**
+   * Calculate the gradient with respect to x, a, b, and w.
+   * The gradient of x will be stored in dx.
+   * backward() can only be called after a corresponding call to forward() with
+   * the same x, s and length.
+   * @note The gradient is added to dx and grad (provided at constructor).
    */
   void backward(real* x, real* dx, int* s, int length);
 
-  /*
-    Find the most probable sequence given x. The result will be stored in s.
+  /**
+   * Find the most probable sequence given x. The result will be stored in s.
    */
   void decode(real* x, int* s, int length);