diff --git a/doc/api/v2/config/layer.rst b/doc/api/v2/config/layer.rst
index db33a20487e579cda67a01c52ee646829df0f4e6..8a8774bd696d60945c87487acbd3c2dee5a0c0bd 100644
--- a/doc/api/v2/config/layer.rst
+++ b/doc/api/v2/config/layer.rst
@@ -109,6 +109,12 @@ sum_to_one_norm
     :members: sum_to_one_norm
     :noindex:
     
+cross_channel_norm
+---------------
+..  automodule:: paddle.v2.layer
+    :members: cross_channel_norm
+    :noindex:
+    
 Recurrent Layers
 ================
 
diff --git a/paddle/gserver/layers/CrossChannelNormLayer.cpp b/paddle/gserver/layers/CrossChannelNormLayer.cpp
index dd3612c49da2b922de28104360c5bdd67d9cbedc..0bc90966e2bfe03293175e69353b274d63718580 100644
--- a/paddle/gserver/layers/CrossChannelNormLayer.cpp
+++ b/paddle/gserver/layers/CrossChannelNormLayer.cpp
@@ -40,7 +40,6 @@ void CrossChannelNormLayer::forward(PassType passType) {
   normBuffer_->addScalar(*normBuffer_, 1e-6);
   inV->square2(*dataBuffer_);
   for (size_t i = 0; i < batchSize; i++) {
-    spatialBuffer_->zeroMem();
     MatrixPtr inTmp = Matrix::create(
         inV->getData() + i * dataDim, channels_, spatialDim, false, useGpu_);
     MatrixPtr dataTmp = Matrix::create(dataBuffer_->getData() + i * dataDim,
@@ -80,7 +79,6 @@ void CrossChannelNormLayer::backward(const UpdateCallback& callback) {
   scaleDiff_->zeroMem();
   for (size_t i = 0; i < batchSize; i++) {
     spatialBuffer_->zeroMem();
-    channelBuffer_->zeroMem();
     // propagate to param.
     MatrixPtr dataBufferTmp =
         Matrix::create(dataBuffer_->getData() + i * dataDim,
diff --git a/paddle/gserver/layers/NormLayer.h b/paddle/gserver/layers/NormLayer.h
index 59ba226dfe5f5f96ce0d5a97c05851c60cace287..d896abbd757b89694e0cd6ec25adaa100ce4443e 100644
--- a/paddle/gserver/layers/NormLayer.h
+++ b/paddle/gserver/layers/NormLayer.h
@@ -66,11 +66,10 @@ public:
 };
 
 /**
- * This layer applys normalize across the channels of each sample to a
- * conv layer's output and scale the output by a group of trainable factors
- * which dimensions equal to the channel's number.
- * - Input: One and only one input layer are accepted. The input layer must be
- *        be a data output layer.
+ * This layer applys normalization across the channels of each sample to a
+ * conv layer's output, and scales the output by a group of trainable factors
+ * whose equal to the number of channels.
+ * - Input: One and only one input layer are accepted.
  * - Output: The normalized data of the input data.
  * Reference:
  *    Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed,
diff --git a/python/paddle/trainer_config_helpers/layers.py b/python/paddle/trainer_config_helpers/layers.py
index cac71539f59f392e65ac6023da71999816d4d3bb..df91a6d8cf8a9d114a1fdce0f624c6a9c8ba22d0 100755
--- a/python/paddle/trainer_config_helpers/layers.py
+++ b/python/paddle/trainer_config_helpers/layers.py
@@ -1015,6 +1015,7 @@ def cross_channel_norm_layer(input, name=None, param_attr=None):
     This layer applys normalize across the channels of each sample to
     a conv layer's output and scale the output by a group of trainable
     factors which dimensions equal to the channel's number.
+
     :param name: The Layer Name.
     :type name: basestring
     :param input: The input layer.