diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec
index d0e5fbca5899d67d91ea2488c79d858f7603e488..7abe9f9d68a06a90858626f12e94dc2d8b0c3852 100755
--- a/paddle/fluid/API.spec
+++ b/paddle/fluid/API.spec
@@ -121,7 +121,7 @@ paddle.fluid.initializer.MSRAInitializer ('paddle.fluid.initializer.MSRAInitiali
 paddle.fluid.initializer.MSRAInitializer.__init__ (ArgSpec(args=['self', 'uniform', 'fan_in', 'seed'], varargs=None, keywords=None, defaults=(True, None, 0)), ('document', '53c757bed9345f2ad3361902531e7cf5'))
 paddle.fluid.initializer.force_init_on_cpu (ArgSpec(args=[], varargs=None, keywords=None, defaults=None), ('document', '5f55553caf939d270c7fe8dc418084b2'))
 paddle.fluid.initializer.init_on_cpu (ArgSpec(args=[], varargs=None, keywords=None, defaults=None), ('document', 'eaa04fd68661a3af59abd0e19b3b6eda'))
-paddle.fluid.initializer.NumpyArrayInitializer ('paddle.fluid.initializer.NumpyArrayInitializer', ('document', '064f134a27c16372967d450f499762ab'))
+paddle.fluid.initializer.NumpyArrayInitializer ('paddle.fluid.initializer.NumpyArrayInitializer', ('document', '7b0c371a233f9eb6feab75bbef8a74cc'))
 paddle.fluid.initializer.NumpyArrayInitializer.__init__ (ArgSpec(args=['self', 'value'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.embedding (ArgSpec(args=['input', 'size', 'is_sparse', 'is_distributed', 'padding_idx', 'param_attr', 'dtype'], varargs=None, keywords=None, defaults=(False, False, None, None, 'float32')), ('document', 'd4ac047e0d5e6b7b1c5ff6ef7d7cfff5'))
 paddle.fluid.one_hot (ArgSpec(args=['input', 'depth', 'allow_out_of_range'], varargs=None, keywords=None, defaults=(False,)), ('document', 'eef66730acc806088f9e8ba90252bda1'))
@@ -136,7 +136,7 @@ paddle.fluid.layers.linear_chain_crf (ArgSpec(args=['input', 'label', 'param_att
 paddle.fluid.layers.crf_decoding (ArgSpec(args=['input', 'param_attr', 'label', 'length'], varargs=None, keywords=None, defaults=(None, None)), ('document', '933b7e268c4ffa3d5c3ef953a5ee9f0b'))
 paddle.fluid.layers.cos_sim (ArgSpec(args=['X', 'Y'], varargs=None, keywords=None, defaults=None), ('document', '07bb25484c98d529fbe67338422724af'))
 paddle.fluid.layers.cross_entropy (ArgSpec(args=['input', 'label', 'soft_label', 'ignore_index'], varargs=None, keywords=None, defaults=(False, -100)), ('document', '789a141e97fd0b37241f630935936d08'))
-paddle.fluid.layers.bpr_loss (ArgSpec(args=['input', 'label', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '6263dfdeb6c670fa0922c9cbc8fb1bf4'))
+paddle.fluid.layers.bpr_loss (ArgSpec(args=['input', 'label', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'ae57e6e5136dade436f0df1f11770afa'))
 paddle.fluid.layers.square_error_cost (ArgSpec(args=['input', 'label'], varargs=None, keywords=None, defaults=None), ('document', 'bbb9e708bab250359864fefbdf48e9d9'))
 paddle.fluid.layers.chunk_eval (ArgSpec(args=['input', 'label', 'chunk_scheme', 'num_chunk_types', 'excluded_chunk_types', 'seq_length'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'b02844e0ad4bd713c5fe6802aa13219c'))
 paddle.fluid.layers.sequence_conv (ArgSpec(args=['input', 'num_filters', 'filter_size', 'filter_stride', 'padding', 'padding_start', 'bias_attr', 'param_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(3, 1, True, None, None, None, None, None)), ('document', 'ebddcc5a1073ef065d22b4673e36b1d2'))
@@ -151,7 +151,7 @@ paddle.fluid.layers.adaptive_pool2d (ArgSpec(args=['input', 'pool_size', 'pool_t
 paddle.fluid.layers.adaptive_pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', '55db6ae7275fb9678a6814aebab81a9c'))
 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', 'b88a2a2d5de3e6d845d134782fb54857'))
 paddle.fluid.layers.instance_norm (ArgSpec(args=['input', 'epsilon', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None)), ('document', '5e2d18e85599ede7e71b06ed64d0f69e'))
-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', '2460b30fb87037555208fa8ac6fc1787'))
+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', '5ba4cdb4ea5c03382da545335ffc05b7'))
 paddle.fluid.layers.beam_search_decode (ArgSpec(args=['ids', 'scores', 'beam_size', 'end_id', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '83e08f21af41ac8bac37aeab1f86fdd0'))
 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', 'data_format'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None, 'NCHW')), ('document', '0ca6c549ac2b63096bdc7832a08b4431'))
 paddle.fluid.layers.conv3d_transpose (ArgSpec(args=['input', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name', 'data_format'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None, 'NCDHW')), ('document', '709d7ca3a94f52a253d15b06aafb1bd0'))
@@ -294,7 +294,7 @@ paddle.fluid.layers.temporal_shift (ArgSpec(args=['x', 'seg_num', 'shift_ratio',
 paddle.fluid.layers.py_func (ArgSpec(args=['func', 'x', 'out', 'backward_func', 'skip_vars_in_backward_input'], varargs=None, keywords=None, defaults=(None, None)), ('document', '8404e472ac12b4a30a505d3d3a3e5fdb'))
 paddle.fluid.layers.psroi_pool (ArgSpec(args=['input', 'rois', 'output_channels', 'spatial_scale', 'pooled_height', 'pooled_width', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '42d5155374f69786300d90d751956998'))
 paddle.fluid.layers.prroi_pool (ArgSpec(args=['input', 'rois', 'output_channels', 'spatial_scale', 'pooled_height', 'pooled_width', 'name'], varargs=None, keywords=None, defaults=(1.0, 1, 1, None)), ('document', '454c7ea8c73313dd41513929d7526303'))
-paddle.fluid.layers.teacher_student_sigmoid_loss (ArgSpec(args=['input', 'label', 'soft_max_up_bound', 'soft_max_lower_bound'], varargs=None, keywords=None, defaults=(15.0, -15.0)), ('document', '07cb0d95a646dba1b9cc7cdce89e59f0'))
+paddle.fluid.layers.teacher_student_sigmoid_loss (ArgSpec(args=['input', 'label', 'soft_max_up_bound', 'soft_max_lower_bound'], varargs=None, keywords=None, defaults=(15.0, -15.0)), ('document', 'b0e07aa41caae04b07a8e8217cc96020'))
 paddle.fluid.layers.huber_loss (ArgSpec(args=['input', 'label', 'delta'], varargs=None, keywords=None, defaults=None), ('document', '11bb8e62cc9256958eff3991fe4834da'))
 paddle.fluid.layers.kldiv_loss (ArgSpec(args=['x', 'target', 'reduction', 'name'], varargs=None, keywords=None, defaults=('mean', None)), ('document', '18bc95c62d3300456c3c7da5278b47bb'))
 paddle.fluid.layers.npair_loss (ArgSpec(args=['anchor', 'positive', 'labels', 'l2_reg'], varargs=None, keywords=None, defaults=(0.002,)), ('document', 'a41a93253c937697e900e19af172490d'))
@@ -316,7 +316,7 @@ paddle.fluid.layers.read_file (ArgSpec(args=['reader'], varargs=None, keywords=N
 paddle.fluid.layers.double_buffer (ArgSpec(args=['reader', 'place', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', '44724c493f41a124abc7531c2740e2e3'))
 paddle.fluid.layers.py_reader (ArgSpec(args=['capacity', 'shapes', 'dtypes', 'lod_levels', 'name', 'use_double_buffer'], varargs=None, keywords=None, defaults=(None, None, True)), ('document', 'd78a1c7344955c5caed8dc13adb7beb6'))
 paddle.fluid.layers.create_py_reader_by_data (ArgSpec(args=['capacity', 'feed_list', 'name', 'use_double_buffer'], varargs=None, keywords=None, defaults=(None, True)), ('document', '2edf37d57862b24a7a26aa19a3573f73'))
-paddle.fluid.layers.load (ArgSpec(args=['out', 'file_path', 'load_as_fp16'], varargs=None, keywords=None, defaults=(None,)), ('document', '9d1a4bc97bbce9fa1d4f7a4200a771ff'))
+paddle.fluid.layers.load (ArgSpec(args=['out', 'file_path', 'load_as_fp16'], varargs=None, keywords=None, defaults=(None,)), ('document', '309f9e5249463e1b207a7347b2a91134'))
 paddle.fluid.layers.create_tensor (ArgSpec(args=['dtype', 'name', 'persistable'], varargs=None, keywords=None, defaults=(None, False)), ('document', 'aaf0176c743c43e9bc684dd7dfac25c5'))
 paddle.fluid.layers.create_parameter (ArgSpec(args=['shape', 'dtype', 'name', 'attr', 'is_bias', 'default_initializer'], varargs=None, keywords=None, defaults=(None, None, False, None)), ('document', '021272f30e0cdf7503586815378abfb8'))
 paddle.fluid.layers.create_global_var (ArgSpec(args=['shape', 'value', 'dtype', 'persistable', 'force_cpu', 'name'], varargs=None, keywords=None, defaults=(False, False, None)), ('document', '47ea8b8c91879e50c9036e418b00ef4a'))
diff --git a/python/paddle/fluid/initializer.py b/python/paddle/fluid/initializer.py
index c73a0d925e2d79c81b16ae15c608fc46f81f28b9..181d1ec36722130cd93e9b07db0ba37d6f745921 100644
--- a/python/paddle/fluid/initializer.py
+++ b/python/paddle/fluid/initializer.py
@@ -861,15 +861,20 @@ class BilinearInitializer(Initializer):
 
 class NumpyArrayInitializer(Initializer):
     """Init an parameter with an numpy array
+    This op initialize the variable by numpy array.
 
     Args:
         value (numpy): numpy array to initialize the variable
 
+    Returns:
+        A Tensor variable initialized by numpy.
+
     Examples:
         .. code-block:: python
 
             import paddle.fluid as fluid
-            x = fluid.layers.data(name="x", shape=[5], dtype='float32')
+            import numpy
+            x = fluid.data(name="x", shape=[2, 1], dtype='float32')
             fc = fluid.layers.fc(input=x, size=10,
                 param_attr=fluid.initializer.NumpyArrayInitializer(numpy.array([1,2])))
     """
diff --git a/python/paddle/fluid/layers/io.py b/python/paddle/fluid/layers/io.py
index 39ce712081bc1ed275a0287b9bded90d2217b213..59c442bb5886f829b6e24fd51f587f990f342896 100644
--- a/python/paddle/fluid/layers/io.py
+++ b/python/paddle/fluid/layers/io.py
@@ -857,24 +857,25 @@ def read_file(reader):
         return out
 
 
-@templatedoc()
 def load(out, file_path, load_as_fp16=None):
     """
-    ${comment}
-
-    >>> import paddle.fluid as fluid
-    >>> tmp_tensor = fluid.layers.create_tensor(dtype='float32')
-    >>> fluid.layers.load(tmp_tensor, "./tmp_tensor.bin")
+    Load operator will load a LoDTensor / SelectedRows variable from disk file.
 
     Args:
-        out(${out_type}): ${out_comment}.
-
-        file_path(${file_path_type}): ${file_path_comment}.
+        out(Variable): The LoDTensor / SelectedRows need to be loaded..
 
-        load_as_fp16(${load_as_fp16_type}): ${load_as_fp16_comment}.
+        file_path(STRING): Variable will be loaded from "file_path".
 
+        load_as_fp16(BOOLEAN): If true, the tensor will be first loaded and then converted to float16 data type. Otherwise, the tensor will be directly loaded without data type conversion. Default is false..
     Returns:
         None
+
+    Examples:
+        .. code-block:: python
+
+            import paddle.fluid as fluid
+            tmp_tensor = fluid.layers.create_tensor(dtype='float32')
+            fluid.layers.load(tmp_tensor, "./tmp_tensor.bin")
     """
     helper = LayerHelper("load", **locals())
     attrs = {"file_path": file_path}
diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index f9b943798bc5ee28762fcbad9cf9008752d1c684..0c9ea4d6b70616514cb30905627e347bc2226509 100755
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -1841,7 +1841,7 @@ def bpr_loss(input, label, name=None):
 
     Args:
         input (Variable|list):  a 2-D tensor with shape [N x D], where N is the
-                                batch size and D is the number of classes.
+                                batch size and D is the number of positive classes and negative classes
                                 This input is not probability but logits.
         label (Variable|list):  the ground truth which is a 2-D tensor.  `label`
                                 is a tensor<int64> with shape [N x 1].
@@ -1856,10 +1856,10 @@ def bpr_loss(input, label, name=None):
           import paddle.fluid as fluid
 
           neg_size = 10
-          label = fluid.layers.data(
-                    name="label", shape=[1], dtype="int64")
-          predict = fluid.layers.data(
-                    name="predict", shape=[neg_size + 1], dtype="float32")
+          label = fluid.data(
+                    name="label", shape=[3, 1], dtype="int64")
+          predict = fluid.data(
+                    name="predict", shape=[3, neg_size + 1], dtype="float32")
           cost = fluid.layers.bpr_loss(input=predict, label=label)
     """
     helper = LayerHelper('bpr_loss', **locals())
@@ -4068,7 +4068,7 @@ def data_norm(input,
     """
     **Data Normalization Layer**
 
-    Can be used as a normalizer function for conv2d and fully_connected operations.
+    This op can be used as a normalizer function for conv2d and fully_connected operations.
     The required data format for this layer is one of the following:
 
     1. NHWC `[batch, in_height, in_width, in_channels]`
@@ -4109,7 +4109,7 @@ def data_norm(input,
             
             import paddle.fluid as fluid
 
-            hidden1 = fluid.layers.data(name="hidden1", shape=[200])
+            hidden1 = fluid.data(name="hidden1", shape=[64, 200])
             hidden2 = fluid.layers.data_norm(name="hidden2", input=hidden1)
     """
     helper = LayerHelper('data_norm', **locals())
@@ -13840,7 +13840,9 @@ def teacher_student_sigmoid_loss(input,
     **Teacher Student Log Loss Layer**
 
     This layer accepts input predictions and target label and returns the
-    teacher_student loss.
+    teacher_student loss. Z is click or not, z' is value of teacher loss, label = {-2, -1, [0, 2]}
+    when z' is not exist, clk = 0 : label = -2; when z' is not exist, clk = 1 : label = -1;
+    when z' is exist    , clk = 0 : label = 0 + z'; when z' is exist    , clk = 1 : label = 1 + z'
 
     .. math::
         loss = max(x, 0) - x * z + log(1 + exp(-abs(x))) + max(x, 0) - x * z' + log(1 + exp(-abs(x)))
@@ -13863,10 +13865,10 @@ def teacher_student_sigmoid_loss(input,
           import paddle.fluid as fluid
 
           batch_size = 64
-          label = fluid.layers.data(
-                    name="label", shape=[batch_size, 1], dtype="int64", append_batch_size=False)
-          similarity = fluid.layers.data(
-                    name="similarity", shape=[batch_size, 1], dtype="float32", append_batch_size=False)
+          label = fluid.data(
+                    name="label", shape=[batch_size, 1], dtype="int64")
+          similarity = fluid.data(
+                    name="similarity", shape=[batch_size, 1], dtype="float32")
           cost = fluid.layers.teacher_student_sigmoid_loss(input=similarity, label=label)
 
     """