diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec
index fb5f64b2ec48f711a9051fb8875c622d969c1e12..550aeafc4ca594100b7d3d0dbea4fd65ebfdf609 100644
--- a/paddle/fluid/API.spec
+++ b/paddle/fluid/API.spec
@@ -78,8 +78,8 @@ paddle.fluid.layers.dynamic_gru (ArgSpec(args=['input', 'size', 'param_attr', 'b
 paddle.fluid.layers.gru_unit (ArgSpec(args=['input', 'hidden', 'size', 'param_attr', 'bias_attr', 'activation', 'gate_activation', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, 'tanh', 'sigmoid', False)), ('document', 'e0e2439f7af069b57badca18a6ba60b8'))
 paddle.fluid.layers.linear_chain_crf (ArgSpec(args=['input', 'label', 'param_attr'], varargs=None, keywords=None, defaults=(None,)), ('document', '7c49ef4bbf0adfd4b9a1d98e2e5f3fea'))
 paddle.fluid.layers.crf_decoding (ArgSpec(args=['input', 'param_attr', 'label'], varargs=None, keywords=None, defaults=(None,)), ('document', '462ddf2435e3392334e0c05ae57a01c4'))
-paddle.fluid.layers.cos_sim (ArgSpec(args=['X', 'Y'], varargs=None, keywords=None, defaults=None), ('document', 'd740824aa7316b807c4b4a3c6c8c0bbe'))
-paddle.fluid.layers.cross_entropy (ArgSpec(args=['input', 'label', 'soft_label', 'ignore_index'], varargs=None, keywords=None, defaults=(False, -100)), ('document', '025b364dafb4b7975c801eb33e7831a1'))
+paddle.fluid.layers.cos_sim (ArgSpec(args=['X', 'Y'], varargs=None, keywords=None, defaults=None), ('document', 'cefab7c23ee5582727e8b22dffbafac8'))
+paddle.fluid.layers.cross_entropy (ArgSpec(args=['input', 'label', 'soft_label', 'ignore_index'], varargs=None, keywords=None, defaults=(False, -100)), ('document', '535f1f6213dd7ca0fe5ed7cb4718c0e3'))
 paddle.fluid.layers.bpr_loss (ArgSpec(args=['input', 'label', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '30add751a0f99347a6257634c03ff254'))
 paddle.fluid.layers.square_error_cost (ArgSpec(args=['input', 'label'], varargs=None, keywords=None, defaults=None), ('document', 'f273bb26833ee88b349c4b8083e1dc67'))
 paddle.fluid.layers.chunk_eval (ArgSpec(args=['input', 'label', 'chunk_scheme', 'num_chunk_types', 'excluded_chunk_types'], varargs=None, keywords=None, defaults=(None,)), ('document', 'ee152a7ba3036e7b9ede9184545179b4'))
@@ -93,7 +93,7 @@ paddle.fluid.layers.pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'po
 paddle.fluid.layers.pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True)), ('document', '043de7333b79ee0ac55053c14ed81625'))
 paddle.fluid.layers.adaptive_pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', '859b887174d06f361658f69cb7c06d95'))
 paddle.fluid.layers.adaptive_pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', '120f4323a3d7ed9c0916f15a59f0e497'))
-paddle.fluid.layers.batch_norm (ArgSpec(args=['input', 'act', 'is_test', 'momentum', 'epsilon', 'param_attr', 'bias_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var', 'fuse_with_relu', 'use_global_stats'], varargs=None, keywords=None, defaults=(None, False, 0.9, 1e-05, None, None, 'NCHW', False, None, None, None, False, False, False)), ('document', '320c6973b02ea179fa89fecc80796464'))
+paddle.fluid.layers.batch_norm (ArgSpec(args=['input', 'act', 'is_test', 'momentum', 'epsilon', 'param_attr', 'bias_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var', 'fuse_with_relu', 'use_global_stats'], varargs=None, keywords=None, defaults=(None, False, 0.9, 1e-05, None, None, 'NCHW', False, None, None, None, False, False, False)), ('document', '581f9f99cd7f4b0cab9e0aad5fa0ea24'))
 paddle.fluid.layers.data_norm (ArgSpec(args=['input', 'act', 'epsilon', 'param_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var'], varargs=None, keywords=None, defaults=(None, 1e-05, None, 'NCHW', False, None, None, None, False)), ('document', 'e45e09e65a2658e07cad987222f0d9ab'))
 paddle.fluid.layers.beam_search_decode (ArgSpec(args=['ids', 'scores', 'beam_size', 'end_id', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'b0b8d53821716cd50c42e09b593f3feb'))
 paddle.fluid.layers.conv2d_transpose (ArgSpec(args=['input', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None)), ('document', '03993955ab1e6d3044c44e6f17fc85e9'))
@@ -434,7 +434,7 @@ paddle.fluid.nets.simple_img_conv_pool (ArgSpec(args=['input', 'num_filters', 'f
 paddle.fluid.nets.sequence_conv_pool (ArgSpec(args=['input', 'num_filters', 'filter_size', 'param_attr', 'act', 'pool_type', 'bias_attr'], varargs=None, keywords=None, defaults=(None, 'sigmoid', 'max', None)), ('document', '48c434dd7bb827f69d90e5135d77470f'))
 paddle.fluid.nets.glu (ArgSpec(args=['input', 'dim'], varargs=None, keywords=None, defaults=(-1,)), ('document', '6486b2595300fc3305b5a1f0ac363dce'))
 paddle.fluid.nets.scaled_dot_product_attention (ArgSpec(args=['queries', 'keys', 'values', 'num_heads', 'dropout_rate'], varargs=None, keywords=None, defaults=(1, 0.0)), ('document', '921714c9bfb351b41403418265393203'))
-paddle.fluid.nets.img_conv_group (ArgSpec(args=['input', 'conv_num_filter', 'pool_size', 'conv_padding', 'conv_filter_size', 'conv_act', 'param_attr', 'conv_with_batchnorm', 'conv_batchnorm_drop_rate', 'pool_stride', 'pool_type', 'use_cudnn'], varargs=None, keywords=None, defaults=(1, 3, None, None, False, 0.0, 1, 'max', True)), ('document', '3802be78fbfb206dae64a2d9f8480970'))
+paddle.fluid.nets.img_conv_group (ArgSpec(args=['input', 'conv_num_filter', 'pool_size', 'conv_padding', 'conv_filter_size', 'conv_act', 'param_attr', 'conv_with_batchnorm', 'conv_batchnorm_drop_rate', 'pool_stride', 'pool_type', 'use_cudnn'], varargs=None, keywords=None, defaults=(1, 3, None, None, False, 0.0, 1, 'max', True)), ('document', '5178bc1b4d302192597a5efbae13d902'))
 paddle.fluid.optimizer.SGDOptimizer.__init__ (ArgSpec(args=['self', 'learning_rate', 'regularization', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.optimizer.SGDOptimizer.apply_gradients (ArgSpec(args=['self', 'params_grads'], varargs=None, keywords=None, defaults=None), ('document', 'bfe7305918552aaecfdaa22411dbe871'))
 paddle.fluid.optimizer.SGDOptimizer.apply_optimize (ArgSpec(args=['self', 'loss', 'startup_program', 'params_grads'], varargs=None, keywords=None, defaults=None), ('document', '5c46d1926a40f1f873ffe9f37ac89dae'))
diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index 78cc4e9a1dff19ed3e345acb4a594506aa7ecc9b..69e260af1a7a8ab238f28fd6cf58526ae5c22eea 100644
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -1322,6 +1322,13 @@ def cos_sim(X, Y):
 
     Returns:
         Variable: the output of cosine(X, Y).
+
+    Examples:
+        .. code-block:: python
+
+            x = fluid.layers.data(name='x', shape=[3, 7], dtype='float32', append_batch_size=False)
+            y = fluid.layers.data(name='y', shape=[1, 7], dtype='float32', append_batch_size=False)
+            out = fluid.layers.cos_sim(x, y)
     """
     helper = LayerHelper('cos_sim', **locals())
     out = helper.create_variable_for_type_inference(dtype=X.dtype)
@@ -1482,7 +1489,10 @@ def cross_entropy(input, label, soft_label=False, ignore_index=kIgnoreIndex):
     Examples:
         .. code-block:: python
 
-          predict = fluid.layers.fc(input=net, size=classdim, act='softmax')
+          classdim = 7
+          x = fluid.layers.data(name='x', shape=[3, 7], dtype='float32', append_batch_size=False)
+          label = fluid.layers.data(name='label', shape=[3, 1], dtype='float32', append_batch_size=False)
+          predict = fluid.layers.fc(input=x, size=classdim, act='softmax')
           cost = fluid.layers.cross_entropy(input=predict, label=label)
     """
     if not soft_label:
@@ -3033,6 +3043,7 @@ def batch_norm(input,
 
         .. code-block:: python
 
+            x = fluid.layers.data(name='x', shape=[3, 7, 3, 7], dtype='float32', append_batch_size=False)
             hidden1 = fluid.layers.fc(input=x, size=200, param_attr='fc1.w')
             hidden2 = fluid.layers.batch_norm(input=hidden1)
     """
diff --git a/python/paddle/fluid/nets.py b/python/paddle/fluid/nets.py
index c961a5c36ed164fe96bc8edb334cfc9099182156..2e38e3eea0545e0e87c19c344871cde97d1bd0c0 100644
--- a/python/paddle/fluid/nets.py
+++ b/python/paddle/fluid/nets.py
@@ -191,7 +191,6 @@ def img_conv_group(input,
 
             img = fluid.layers.data(name='img', shape=[1, 28, 28], dtype='float32')
             conv_pool = fluid.nets.img_conv_group(input=img,
-                                                  num_channels=3,
                                                   conv_padding=1,
                                                   conv_num_filter=[3, 3],
                                                   conv_filter_size=3,