diff --git a/paddle/operators/huber_loss_op.cc b/paddle/operators/huber_loss_op.cc
index 3435e74b0afb470fcbd1c0f4e06ad363352cac00..938803d5b36177c782fe40bc34fd92504e5bbf7b 100644
--- a/paddle/operators/huber_loss_op.cc
+++ b/paddle/operators/huber_loss_op.cc
@@ -70,11 +70,18 @@ input value and Y as the target value. Huber loss can evaluate the fitness of
 X to Y. Different from MSE loss, Huber loss is more robust for outliers. The
 shape of X and Y are [batch_size, 1]. The equation is:
 
-L_{\delta}(y, f(x)) =
+$$
+Out_{\delta}(X, Y)_i =
 \begin{cases}
-0.5 * (y - f(x))^2, \quad |y - f(x)| \leq \delta \\
-\delta * (|y - f(x)| - 0.5 * \delta),   \quad otherwise
+0.5 * (Y_i - X_i)^2,
+\quad |Y_i - X_i| \leq \delta \\
+\delta * (|Y_i - X_i| - 0.5 * \delta),
+\quad otherwise
 \end{cases}
+$$
+
+In the above equation, $Out_\delta(X, Y)_i$, $X_i$ and $Y_i$ represent the ith
+element of Out, X and Y.
 
 )DOC");
   }