fix bpr_loss data_norm teacher_student_sigmoid_loss api & fix continuous_value_model (#17331)

* fix bpr data_norm teacher_student_sigmoid , test=develop test=document_preview

修复了bpr_loss data_norm teacher_student_sigmoid_loss三个api, 同时修复了continuous_value_model文档英文拼写错误

paddle/fluid/API.spec

@@ -81,7 +81,7 @@ paddle.fluid.layers.linear_chain_crf (ArgSpec(args=['input', 'label', 'param_att
 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', '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.bpr_loss (ArgSpec(args=['input', 'label', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '6263dfdeb6c670fa0922c9cbc8fb1bf4'))
 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'))
 paddle.fluid.layers.sequence_conv (ArgSpec(args=['input', 'num_filters', 'filter_size', 'filter_stride', 'padding', 'bias_attr', 'param_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(3, 1, None, None, None, None, None)), ('document', 'b6543768e1afaa2ecb869709d6e9c7e2'))
@@ -95,7 +95,7 @@ paddle.fluid.layers.pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'po
 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', '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.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.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'))
 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'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None)), ('document', 'ec113c6a3686ac94f8fccd1a7953d445'))
@@ -227,14 +227,14 @@ paddle.fluid.layers.shuffle_channel (ArgSpec(args=['x', 'group', 'name'], vararg
 paddle.fluid.layers.temporal_shift (ArgSpec(args=['x', 'seg_num', 'shift_ratio', 'name'], varargs=None, keywords=None, defaults=(0.25, None)), ('document', 'fe4481fb31363b09cfdd228fc6776ddf'))
 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.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', '2f6ff96864054a31aa4bb659c6722c99'))
+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.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', '776d536cac47c89073abc7ee524d5aec'))
 paddle.fluid.layers.tree_conv (ArgSpec(args=['nodes_vector', 'edge_set', 'output_size', 'num_filters', 'max_depth', 'act', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1, 2, 'tanh', None, None, None)), ('document', '2985a372ac897ea4e13aced7f930d6f8'))
 paddle.fluid.layers.npair_loss (ArgSpec(args=['anchor', 'positive', 'labels', 'l2_reg'], varargs=None, keywords=None, defaults=(0.002,)), ('document', '46994d10276dd4cb803b4062b5d14329'))
 paddle.fluid.layers.pixel_shuffle (ArgSpec(args=['x', 'upscale_factor'], varargs=None, keywords=None, defaults=None), ('document', '132b6e74ff642a392bd6b14c10aedc65'))
 paddle.fluid.layers.fsp_matrix (ArgSpec(args=['x', 'y'], varargs=None, keywords=None, defaults=None), ('document', 'b76ccca3735bea4a58a0dbf0d77c5393'))
-paddle.fluid.layers.continuous_value_model (ArgSpec(args=['input', 'cvm', 'use_cvm'], varargs=None, keywords=None, defaults=(True,)), ('document', 'a07a44c2bacdcd09c1f5f35a96a0514e'))
+paddle.fluid.layers.continuous_value_model (ArgSpec(args=['input', 'cvm', 'use_cvm'], varargs=None, keywords=None, defaults=(True,)), ('document', '94e2819b7c9715ea71b62e9c78f36b29'))
 paddle.fluid.layers.where (ArgSpec(args=['condition'], varargs=None, keywords=None, defaults=None), ('document', '3126e3039e752ce26077f1efaca355c6'))
 paddle.fluid.layers.sign (ArgSpec(args=['x'], varargs=None, keywords=None, defaults=None), ('document', 'ccf6bb7912afd2818d24bc45461e807a'))
 paddle.fluid.layers.data (ArgSpec(args=['name', 'shape', 'append_batch_size', 'dtype', 'lod_level', 'type', 'stop_gradient'], varargs=None, keywords=None, defaults=(True, 'float32', 0, VarType.LOD_TENSOR, True)), ('document', 'adf285346e23316097f7789b572491e9'))

python/paddle/fluid/layers/nn.py

@@ -1544,14 +1544,16 @@ def cross_entropy2(input, label, ignore_index=kIgnoreIndex):
 
 def bpr_loss(input, label, name=None):
     """
-    Bayesian Personalized Ranking Loss Operator.
+    **Bayesian Personalized Ranking Loss Operator**
 
     This operator belongs to pairwise ranking loss. Label is the desired item.
     The loss at a given point in one session is defined as:
-    $Y[i] = -\frac{1}{N_{i}-1} * \sum_{0\le j<N_{i},~ j\neq Label[i]}\log(\sigma(X[i, Label[i]]-X[i, j]))$
+
+    .. math::
+        Y[i] = 1/(N[i] - 1) * \sum_j{\log(\sigma(X[i, Label[i]]-X[i, j]))}
 
     Learn more details by reading paper <session-based recommendations with recurrent
-    neural networks>(https://arxiv.org/abs/1511.06939)
+    neural networks>.
 
     Args:
         input (Variable|list):  a 2-D tensor with shape [N x D], where N is the
@@ -1567,9 +1569,15 @@ def bpr_loss(input, label, name=None):
     Examples:
         .. code-block:: python
 
+          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")
           cost = fluid.layers.bpr_loss(input=predict, label=label)
     """
-
     helper = LayerHelper('bpr_loss', **locals())
     out = helper.create_variable_for_type_inference(dtype=input.dtype)
     helper.append_op(
@@ -3208,8 +3216,10 @@ def data_norm(input,
 
         .. code-block:: python
             
-            data = fluid.layers.data(input=x, size=200, param_attr='fc1.w')
-            hidden2 = fluid.layers.data_norm(input=hidden1)
+            import paddle.fluid as fluid
+
+            hidden1 = fluid.layers.data(name="hidden1", shape=[200])
+            hidden2 = fluid.layers.data_norm(name="hidden2", input=hidden1)
     """
     helper = LayerHelper('data_norm', **locals())
     dtype = helper.input_dtype()
@@ -10485,7 +10495,15 @@ def teacher_student_sigmoid_loss(input,
     Examples:
         .. code-block:: python
           
+          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)
           cost = fluid.layers.teacher_student_sigmoid_loss(input=similarity, label=label)
+
     """
     helper = LayerHelper('teacher_student_sigmoid_loss', **locals())
     out = helper.create_variable(dtype=input.dtype)
@@ -11370,7 +11388,7 @@ def continuous_value_model(input, cvm, use_cvm=True):
         cvm (Variable):   a 2-D Tensor with shape [N x 2], where N is the batch size, 2 is show and click.
         use_cvm  (bool):  use cvm or not. if use cvm, the output dim is the same as input
                           if don't use cvm, the output dim is input dim - 2(remove show and click)
-                          (cvm op is a customized op, which input is a sequence has embedd_with_cvm default, so we need an op named cvm to decided whever use it or not.)
+                          (cvm op is a customized op, which input is a sequence has embed_with_cvm default, so we need an op named cvm to decided whever use it or not.)
 
     Returns: