From 3305c8766e2df7e614bfb1d45ea5a7dddfda3ea9 Mon Sep 17 00:00:00 2001
From: yangyaming <mxscmxsc@gmail.com>
Date: Thu, 23 Nov 2017 13:12:07 +0800
Subject: [PATCH] Add more comment.

---
 paddle/operators/huber_loss_op.cc | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/paddle/operators/huber_loss_op.cc b/paddle/operators/huber_loss_op.cc
index 707ee60b6..938803d5b 100644
--- a/paddle/operators/huber_loss_op.cc
+++ b/paddle/operators/huber_loss_op.cc
@@ -71,15 +71,18 @@ 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:
 
 $$
-Out_{\delta}(i, x, y) =
+Out_{\delta}(X, Y)_i =
 \begin{cases}
-0.5 * (Input(i, y) - Input(i, x))^2,
-\quad |Input(i, y) - Input(i, x)| \leq \delta \\
-\delta * (|Input(i, y) - Input(i, x)| - 0.5 * \delta),
+0.5 * (Y_i - X_i)^2,
+\quad |Y_i - X_i| \leq \delta \\
+\delta * (|Y_i - X_i| - 0.5 * \delta),
 \quad otherwise
 \end{cases}
 $$
 
+In the above equation, $Out_\delta(X, Y)_i$, $X_i$ and $Y_i$ represent the ith
+element of Out, X and Y.
+
 )DOC");
   }
 };
-- 
GitLab