fix API doc, solve conflict, test=develop, test=document_fix (#20196)

* fix APIs,test=develop,test=document_fix

* fix conflict, test=develop, test=document_fix

* fix confict, test=develop, test=document_fix

* fix confict, test=develop, test=document_fix

* fix API.spec, test=develop, test=document_fix

* change fluid.layers.data to fluid.data,test=develop, test=document_fix

* fix bug on example code, test=develop, test=document_fix

* fix API.spec,  test=develop, test=document_fix

paddle/fluid/API.spec

@@ -132,7 +132,7 @@ paddle.fluid.layers.dynamic_lstm (ArgSpec(args=['input', 'size', 'h_0', 'c_0', '
 paddle.fluid.layers.dynamic_lstmp (ArgSpec(args=['input', 'size', 'proj_size', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'proj_activation', 'dtype', 'name', 'h_0', 'c_0', 'cell_clip', 'proj_clip'], varargs=None, keywords=None, defaults=(None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'tanh', 'float32', None, None, None, None, None)), ('document', 'c37d51aad655c8a9f9b045c64717320a'))
 paddle.fluid.layers.dynamic_gru (ArgSpec(args=['input', 'size', 'param_attr', 'bias_attr', 'is_reverse', 'gate_activation', 'candidate_activation', 'h_0', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, False, 'sigmoid', 'tanh', None, False)), ('document', '83617c165827e030636c80486d5de6f3'))
 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', '33974b9bfa69f2f1eb85e6f956dff04e'))
-paddle.fluid.layers.linear_chain_crf (ArgSpec(args=['input', 'label', 'param_attr', 'length'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'bc7a0fd2bb2b35dfd2f54947320e78fa'))
+paddle.fluid.layers.linear_chain_crf (ArgSpec(args=['input', 'label', 'param_attr', 'length'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'b28bdb43160e9667be2a3457d19d9f5b'))
 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'))
@@ -144,7 +144,7 @@ paddle.fluid.layers.conv2d (ArgSpec(args=['input', 'num_filters', 'filter_size',
 paddle.fluid.layers.conv3d (ArgSpec(args=['input', 'num_filters', 'filter_size', 'stride', 'padding', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name', 'data_format'], varargs=None, keywords=None, defaults=(1, 0, 1, None, None, None, True, None, None, 'NCDHW')), ('document', 'a7e4573745c40b8b1d726709f209b6e4'))
 paddle.fluid.layers.sequence_pool (ArgSpec(args=['input', 'pool_type', 'is_test', 'pad_value'], varargs=None, keywords=None, defaults=(False, 0.0)), ('document', 'e90a93251c52dc4e6fb34fb3991b3f82'))
 paddle.fluid.layers.sequence_softmax (ArgSpec(args=['input', 'use_cudnn', 'name'], varargs=None, keywords=None, defaults=(False, None)), ('document', 'eaa9d0bbd3d4e017c8bc4ecdac483711'))
-paddle.fluid.layers.softmax (ArgSpec(args=['input', 'use_cudnn', 'name', 'axis'], varargs=None, keywords=None, defaults=(False, None, -1)), ('document', 'cee673c79e3ff4582656a24e04f841e5'))
+paddle.fluid.layers.softmax (ArgSpec(args=['input', 'use_cudnn', 'name', 'axis'], varargs=None, keywords=None, defaults=(False, None, -1)), ('document', '7ccaea1b93fe4f7387a6036692986c6b'))
 paddle.fluid.layers.pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive', 'data_format'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True, 'NCHW')), ('document', '630cae697d46b4b575b15d56cf8be25a'))
 paddle.fluid.layers.pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive', 'data_format'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True, 'NCDHW')), ('document', 'db0035a3132b1dfb12e53c57591fb9f6'))
 paddle.fluid.layers.adaptive_pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', '52343203de40afe29607397e13aaf0d2'))
@@ -191,7 +191,7 @@ paddle.fluid.layers.layer_norm (ArgSpec(args=['input', 'scale', 'shift', 'begin_
 paddle.fluid.layers.group_norm (ArgSpec(args=['input', 'groups', 'epsilon', 'param_attr', 'bias_attr', 'act', 'data_layout', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None, 'NCHW', None)), ('document', '65231cc8281815124934b1439fbb750c'))
 paddle.fluid.layers.spectral_norm (ArgSpec(args=['weight', 'dim', 'power_iters', 'eps', 'name'], varargs=None, keywords=None, defaults=(0, 1, 1e-12, None)), ('document', '9461e67095a6fc5d568fb2ce8fef66ff'))
 paddle.fluid.layers.softmax_with_cross_entropy (ArgSpec(args=['logits', 'label', 'soft_label', 'ignore_index', 'numeric_stable_mode', 'return_softmax', 'axis'], varargs=None, keywords=None, defaults=(False, -100, True, False, -1)), ('document', '54e1675aa0364f4a78fa72804ec0f413'))
-paddle.fluid.layers.smooth_l1 (ArgSpec(args=['x', 'y', 'inside_weight', 'outside_weight', 'sigma'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', 'ecb75c1b00c4c76c98b482f633b7a10c'))
+paddle.fluid.layers.smooth_l1 (ArgSpec(args=['x', 'y', 'inside_weight', 'outside_weight', 'sigma'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', 'cbe8940643ac80ef75e1abdfbdb09e88'))
 paddle.fluid.layers.one_hot (ArgSpec(args=['input', 'depth', 'allow_out_of_range'], varargs=None, keywords=None, defaults=(False,)), ('document', 'ec4115591be842868c86b2e5334245c6'))
 paddle.fluid.layers.autoincreased_step_counter (ArgSpec(args=['counter_name', 'begin', 'step'], varargs=None, keywords=None, defaults=(None, 1, 1)), ('document', '98e7927f09ee2270535b29f048e481ec'))
 paddle.fluid.layers.reshape (ArgSpec(args=['x', 'shape', 'actual_shape', 'act', 'inplace', 'name'], varargs=None, keywords=None, defaults=(None, None, False, None)), ('document', 'ca73fdc4551c5765c92eb00f24874289'))
@@ -229,7 +229,7 @@ paddle.fluid.layers.margin_rank_loss (ArgSpec(args=['label', 'left', 'right', 'm
 paddle.fluid.layers.elu (ArgSpec(args=['x', 'alpha', 'name'], varargs=None, keywords=None, defaults=(1.0, None)), ('document', '9af1926c06711eacef9e82d7a9e4d308'))
 paddle.fluid.layers.relu6 (ArgSpec(args=['x', 'threshold', 'name'], varargs=None, keywords=None, defaults=(6.0, None)), ('document', '538fc860b2a1734e118b94e4a1a3ee67'))
 paddle.fluid.layers.pow (ArgSpec(args=['x', 'factor', 'name'], varargs=None, keywords=None, defaults=(1.0, None)), ('document', 'ca34f88ff61cf2a7f4c97a493d6000d0'))
-paddle.fluid.layers.stanh (ArgSpec(args=['x', 'scale_a', 'scale_b', 'name'], varargs=None, keywords=None, defaults=(0.6666666666666666, 1.7159, None)), ('document', '1e1efad868714425da15c785dfb533a1'))
+paddle.fluid.layers.stanh (ArgSpec(args=['x', 'scale_a', 'scale_b', 'name'], varargs=None, keywords=None, defaults=(0.67, 1.7159, None)), ('document', 'd3f742178a7263adf5929153d104883d'))
 paddle.fluid.layers.hard_sigmoid (ArgSpec(args=['x', 'slope', 'offset', 'name'], varargs=None, keywords=None, defaults=(0.2, 0.5, None)), ('document', '607d79ca873bee40eed1c79a96611591'))
 paddle.fluid.layers.swish (ArgSpec(args=['x', 'beta', 'name'], varargs=None, keywords=None, defaults=(1.0, None)), ('document', 'e0dc7bc66cba939033bc028d7a62c5f4'))
 paddle.fluid.layers.prelu (ArgSpec(args=['x', 'mode', 'param_attr', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', '1fadca6622c70bd33cc260817f4ff191'))
@@ -436,8 +436,8 @@ paddle.fluid.layers.retinanet_detection_output (ArgSpec(args=['bboxes', 'scores'
 paddle.fluid.layers.distribute_fpn_proposals (ArgSpec(args=['fpn_rois', 'min_level', 'max_level', 'refer_level', 'refer_scale', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'be432c9b5f19ccba7aca38789ead29e4'))
 paddle.fluid.layers.box_decoder_and_assign (ArgSpec(args=['prior_box', 'prior_box_var', 'target_box', 'box_score', 'box_clip', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '5203935538d06a6d47b8630ad80cb2b0'))
 paddle.fluid.layers.collect_fpn_proposals (ArgSpec(args=['multi_rois', 'multi_scores', 'min_level', 'max_level', 'post_nms_top_n', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '808fcca082e0040e2b77dbc53a0cf9d5'))
-paddle.fluid.layers.accuracy (ArgSpec(args=['input', 'label', 'k', 'correct', 'total'], varargs=None, keywords=None, defaults=(1, None, None)), ('document', 'ef799022a6040597462ae2b3d2f1c407'))
-paddle.fluid.layers.auc (ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1)), ('document', '34b4575807f955f7e8698b8dead23858'))
+paddle.fluid.layers.accuracy (ArgSpec(args=['input', 'label', 'k', 'correct', 'total'], varargs=None, keywords=None, defaults=(1, None, None)), ('document', 'b691b7be425e281bd36897b514b2b064'))
+paddle.fluid.layers.auc (ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1)), ('document', 'c36ac7125da977c2bd1b192bee301f75'))
 paddle.fluid.layers.exponential_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', 'eaf430c5a0380fb11bfe9a8922cd6295'))
 paddle.fluid.layers.natural_exp_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', 'aa3146f64d5d508e4e50687603aa7b15'))
 paddle.fluid.layers.inverse_time_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', 'ea37a3a8a0b3ce2254e7bc49a0951dbe'))

paddle/fluid/operators/activation_op.cc

@@ -502,10 +502,12 @@ $out = x^{factor}$
 class STanhOpMaker : public framework::OpProtoAndCheckerMaker {
  public:
   void Make() override {
-    AddInput("X", "Input of STanh operator");
-    AddOutput("Out", "Output of STanh operator");
-    AddAttr<float>("scale_a", "The scale parameter of a for the input")
-        .SetDefault(2.0f / 3.0f);
+    AddInput("X",
+             "Input of STanh operator."
+             " A LoDTensor or Tensor with type float32, float64.");
+    AddOutput("Out", "Output of STanh operator. A Tensor with type float32.");
+    AddAttr<float>("scale_a", "The scale parameter of a for the input. ")
+        .SetDefault(0.67f);
     AddAttr<float>("scale_b", "The scale parameter of b for the input")
         .SetDefault(1.7159f);
     AddComment(R"DOC(

paddle/fluid/operators/linear_chain_crf_op.cc

@@ -22,14 +22,14 @@ namespace operators {
 class LinearChainCRFOpMaker : public framework::OpProtoAndCheckerMaker {
  public:
   void Make() override {
-    AddInput(
-        "Emission",
-        "(LoDTensor/Tensor<float>). When a LoDTensor input, A 2-D LoDTensor"
-        " with shape [N x D], where N is the size of the "
-        "mini-batch and D is the total tag number. The unscaled emission "
-        "weight matrix for the linear chain CRF. When a Tensor input,"
-        "A Tensor with shape [N x S x D], where N is batch size,"
-        "S is max length of sequences, D is the total tag number.");
+    AddInput("Emission",
+             "(LoDTensor/Tensor<float>). When a LoDTensor input,A 2-D LoDTensor"
+             " with shape [N x D], where N is the size of the "
+             "mini-batch and D is the total tag number. The unscaled emission "
+             "weight matrix for the linear chain CRF. When a Tensor input,"
+             "A Tensor with shape [N x S x D], where N is batch number,"
+             "S is max length of sequences, D is the total tag number."
+             "A LoDTensor or Tensor with type float32, float64.");
     AddInput("Transition",
              "(Tensor, default Tensor<float>) A 2-D Tensor with shape "
              "[(D + 2) x D]. The learnable parameter for the linear_chain_crf "
@@ -38,10 +38,12 @@ class LinearChainCRFOpMaker : public framework::OpProtoAndCheckerMaker {
              "(LoDTensor/Tensor<int64_t>), when a LoDTensor input,  "
              "[N x 1], where N is the total element number in a mini-batch. "
              "when a Tensor input, [N x S], where N is batch number. "
-             "S is max length of sequences. The ground truth.");
+             "S is max length of sequences. The ground truth."
+             "A  LoDTensor or Tensor with int64.");
     AddInput("Length",
              "(Tensor, default Tensor<int64_t>) A Tensor with shape "
-             "[M x 1], where M is the sequence number in a mini-batch.")
+             "[M x 1], where M is the sequence number in a mini-batch."
+             "A Tensor with type int64.")
         .AsDispensable();
     AddOutput(
         "Alpha",
@@ -60,14 +62,16 @@ class LinearChainCRFOpMaker : public framework::OpProtoAndCheckerMaker {
         "(Tensor, default Tensor<float>), the same shape with Emission. "
         "The exponentials of Input(Emission). This is an intermediate "
         "computational result in forward computation, and will be reused in "
-        "backward computation.")
+        "backward computation."
+        "A LoDTensor or Tensor with type float32, float64.")
         .AsIntermediate();
     AddOutput(
         "TransitionExps",
         "(Tensor, default Tensor<float>) A 2-D Tensor with shape "
         "[(D + 2) x D]. The exponentials of Input(Transition). This is an "
         "intermediate computational result in forward computation, and "
-        "will be reused in backward computation.")
+        "will be reused in backward computation."
+        "A LoDTensor or Tensor with type float32, float64.")
         .AsIntermediate();
     AddOutput(
         "LogLikelihood",
@@ -75,7 +79,7 @@ class LinearChainCRFOpMaker : public framework::OpProtoAndCheckerMaker {
         "likelihood of each training sample in a mini-batch. This is a 2-D "
         "tensor with shape [S x 1], where S is the sequence number in a "
         "mini-batch. Note: S is equal to the sequence number in a mini-batch. "
-        "The output is no longer a LoDTensor.");
+        "A Tensor with type float32, float64.");
     AddComment(R"DOC(
 Conditional Random Field defines an undirected probabilistic graph with nodes
 denoting random variables and edges denoting dependencies between these

python/paddle/fluid/layers/metric_op.py

@@ -37,25 +37,38 @@ def accuracy(input, label, k=1, correct=None, total=None):
     Note: the dtype of accuracy is determined by input. the input and label dtype can be different.
 
     Args:
-        input(Variable): The input of accuracy layer, which is the predictions of network.
-          Carry LoD information is supported.
-        label(Variable): The label of dataset.
-        k(int): The top k predictions for each class will be checked.
-        correct(Variable): The correct predictions count.
-        total(Variable): The total entries count.
+        input(Variable): The input of accuracy layer, which is the predictions of network. A LoDTensor or Tensor with type float32,float64.
+        label(Variable): The label of dataset.  LoDTensor or Tensor with type int32,int64.
+        k(int): The top k predictions for each class will be checked. Data type is int64 or int32.
+        correct(Variable): The correct predictions count. A Tensor with type int64 or int32.
+        total(Variable): The total entries count. A tensor with type int64 or int32.
 
     Returns:
-        Variable: The correct rate.
+        Variable: The correct rate. A Tensor with type float32.
 
     Examples:
         .. code-block:: python
 
-           import paddle.fluid as fluid
-           data = fluid.layers.data(name="data", shape=[-1, 32, 32], dtype="float32")
-           label = fluid.layers.data(name="label", shape=[-1,1], dtype="int32")
-           predict = fluid.layers.fc(input=data, size=10)
-           accuracy_out = fluid.layers.accuracy(input=predict, label=label, k=5)
+            import paddle.fluid as fluid
+            import numpy as np
+
+            data = fluid.data(name="input", shape=[-1, 32, 32], dtype="float32")
+            label = fluid.data(name="label", shape=[-1,1], dtype="int")
+            fc_out = fluid.layers.fc(input=data, size=10)
+            predict = fluid.layers.softmax(input=fc_out)
+            result = fluid.layers.accuracy(input=predict, label=label, k=5)
+
+            place = fluid.CPUPlace()
+            exe = fluid.Executor(place)
+
+            exe.run(fluid.default_startup_program())
+            x = np.random.rand(3, 32, 32).astype("float32")
+            y = np.array([[1],[0],[1]])
+            output= exe.run(feed={"input": x,"label": y},
+                             fetch_list=[result[0]])
+            print(output)
 
+            #[array([0.6666667], dtype=float32)]
     """
     helper = LayerHelper("accuracy", **locals())
     topk_out, topk_indices = nn.topk(input, k=k)
@@ -105,8 +118,10 @@ def auc(input,
                          [0, 1]. Each row is sorted in descending order. This
                          input should be the output of topk. Typically, this
                          Variable indicates the probability of each label.
+                         A LoDTensor or Tensor with type float32,float64.
         label(Variable): A 2D int Variable indicating the label of the training
                          data. The height is batch size and width is always 1.
+                         A LoDTensor or Tensor with type int32,int64.
         curve(str): Curve type, can be 'ROC' or 'PR'. Default 'ROC'.
         num_thresholds(int): The number of thresholds to use when discretizing
                              the roc curve. Default 200.
@@ -118,15 +133,30 @@ def auc(input,
         Variable: A tuple representing the current AUC.
         The return tuple is auc_out, batch_auc_out, [
         batch_stat_pos, batch_stat_neg, stat_pos, stat_neg ]
+        Data type is Tensor, supporting float32, float64.
 
     Examples:
         .. code-block:: python
 
             import paddle.fluid as fluid
-            data = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
-            label = fluid.layers.data(name="label", shape=[1], dtype="int32")
-            predict = fluid.layers.fc(input=data, size=2)
-            auc_out = fluid.layers.auc(input=predict, label=label)
+            import numpy as np
+
+            data = fluid.data(name="input", shape=[-1, 32,32], dtype="float32")
+            label = fluid.data(name="label", shape=[-1], dtype="int")
+            fc_out = fluid.layers.fc(input=data, size=2)
+            predict = fluid.layers.softmax(input=fc_out)
+            result=fluid.layers.auc(input=predict, label=label)
+
+            place = fluid.CPUPlace()
+            exe = fluid.Executor(place)
+
+            exe.run(fluid.default_startup_program())
+            x = np.random.rand(3,32,32).astype("float32")
+            y = np.array([1,0,1])
+            output= exe.run(feed={"input": x,"label": y},
+                             fetch_list=[result[0]])
+            print(output)
+            #[array([0.5])]
     """
     helper = LayerHelper("auc", **locals())
     auc_out = helper.create_variable_for_type_inference(dtype="float64")

python/paddle/fluid/layers/nn.py

@@ -1432,7 +1432,7 @@ def linear_chain_crf(input, label, param_attr=None, length=None):
     ${comment}
 
     Args:
-        input(${emission_type}): ${emission_comment}
+        input(${emission_type}): ${emission_comment} 
         label(${label_type}): ${label_comment}
         Length(${length_type}): ${length_comment}
         param_attr(ParamAttr): The attribute of the learnable parameter for transition parameter.
@@ -1440,7 +1440,7 @@ def linear_chain_crf(input, label, param_attr=None, length=None):
     Returns:
         output(${emission_exps_type}): ${emission_exps_comment} \n
         output(${transition_exps_type}): ${transition_exps_comment} \n
-        output(${log_likelihood_type}): ${log_likelihood_comment}
+        output(${log_likelihood_type}): ${log_likelihood_comment} \n
 
     Examples:
         .. code-block:: python
@@ -1452,8 +1452,8 @@ def linear_chain_crf(input, label, param_attr=None, length=None):
             train_program = fluid.Program()
             startup_program = fluid.Program()
             with fluid.program_guard(train_program, startup_program):
-                input_data = fluid.layers.data(name='input_data', shape=[10], dtype='float32', lod_level=1)
-                label = fluid.layers.data(name='label', shape=[1], dtype='int', lod_level=1)
+                input_data = fluid.data(name='input_data', shape=[-1,10], dtype='float32')
+                label = fluid.data(name='label', shape=[-1,1], dtype='int')
                 emission= fluid.layers.fc(input=input_data, size=10, act="tanh")
                 crf_cost = fluid.layers.linear_chain_crf(
                     input=emission,
@@ -1476,9 +1476,9 @@ def linear_chain_crf(input, label, param_attr=None, length=None):
             train_program = fluid.Program()
             startup_program = fluid.Program()
             with fluid.program_guard(train_program, startup_program):
-                input_data2 = fluid.layers.data(name='input_data2', shape=[10,10], dtype='float32')
-                label2 = fluid.layers.data(name='label2', shape=[10,1], dtype='int')
-                label_length = fluid.layers.data(name='length', shape=[1], dtype='int')
+                input_data2 = fluid.data(name='input_data2', shape=[-1,10,10], dtype='float32')
+                label2 = fluid.data(name='label2', shape=[-1,10,1], dtype='int')
+                label_length = fluid.data(name='length', shape=[-1,1], dtype='int')
                 emission2= fluid.layers.fc(input=input_data2, size=10, act="tanh", num_flatten_dims=2)
                 crf_cost2 = fluid.layers.linear_chain_crf(
                     input=emission2,
@@ -1496,15 +1496,19 @@ def linear_chain_crf(input, label, param_attr=None, length=None):
             #define data, using padding
             cc=np.random.rand(4,10,10).astype('float32')
             dd=np.random.rand(4,10,1).astype('int64')
-            ll=np.array([[3,3,4,2]])
+            ll=np.array([[3],[3],[4],[2]])
             feed2 = {'input_data2':cc,'label2':dd,'length':ll}
-
             loss2= exe.run(train_program,feed=feed2, fetch_list=[crf_cost2])
             print(loss2) 
-            
+            #[array([[ 7.8902354],
+            #        [ 7.3602567],
+            #        [ 10.004011],
+            #        [ 5.86721  ]], dtype=float32)]
+
             #you can use find_var to get transition parameter.
             transition=np.array(fluid.global_scope().find_var('crfw').get_tensor())
             print(transition)
+            
     """
     helper = LayerHelper('linear_chain_crf', **locals())
     size = input.shape[2] if length else input.shape[1]
@@ -2271,7 +2275,8 @@ def softmax(input, use_cudnn=False, name=None, axis=-1):
         Out[i, j] = \\frac{\exp(X[i, j])}{\sum_j(exp(X[i, j])}
 
     Args:
-        input (Variable): The input variable.
+        input (Variable): The input variable. A LoDTensor or Tensor with type 
+        float32, float64.
         use_cudnn (bool): Use cudnn kernel or not, it is valid only when the cudnn \
             library is installed. To improve numerical stablity, set use_cudnn to \
             False by default. Default: False
@@ -2279,23 +2284,28 @@ def softmax(input, use_cudnn=False, name=None, axis=-1):
             will be named automatically. Default: None.
         axis (int): The index of dimension to perform softmax calculations, it should
             be in range :math:`[-1, rank - 1]`, while :math:`rank` is the rank of
-            input variable. Default: -1.
+            input variable. Default: -1. -1 means the last dimension.
 
     Returns:
-        Variable: output of softmax
+        Variable: output of softmax. A Tensor with type float32, float64.
 
     Examples:
 
         .. code-block:: python
 
-             import paddle.fluid as fluid
-             x = fluid.layers.data(name='x', shape=[2], dtype='float32')
-             fc = fluid.layers.fc(input=x, size=10)
-             # perform softmax in the second dimension
-             softmax = fluid.layers.softmax(input=fc, axis=1)
-             # perform softmax in the last dimension
-             softmax = fluid.layers.softmax(input=fc, axis=-1)
+            import paddle.fluid as fluid
+            import numpy as np
 
+            data = fluid.data(name="input", shape=[-1, 3],dtype="float32")
+            result = fluid.layers.softmax(data,axis=1)
+            place = fluid.CPUPlace()
+            exe = fluid.Executor(place)
+            exe.run(fluid.default_startup_program())
+            x = np.random.rand(3, 3).astype("float32")
+            output= exe.run(feed={"input": x},
+                             fetch_list=[result[0]])
+            print(output)
+            #array([0.22595254, 0.39276356, 0.38128382], dtype=float32)]
     """
     helper = LayerHelper('softmax', **locals())
     if not isinstance(input, Variable):
@@ -7701,31 +7711,47 @@ def smooth_l1(x, y, inside_weight=None, outside_weight=None, sigma=None):
     Args:
         x (Variable): A tensor with rank at least 2. The input value of smooth
             L1 loss op with shape [batch_size, dim1, ..., dimN].
+            A LoDTensor or Tensor with type float32.
         y (Variable): A tensor with rank at least 2. The target value of smooth
             L1 loss op with same shape as :attr:`x`.
+            A LoDTensor or Tensor with type float32.
         inside_weight (Variable|None):  A tensor with rank at least 2. This
             input is optional and should have same shape with :attr:`x`. If
             provided, the result of (:attr:`x` - :attr:`y`) will be multiplied
             by this tensor element by element.
+            A Tensor with type float32.
         outside_weight (Variable|None): A tensor with rank at least 2. This
             input is optional and should have same shape with :attr:`x`. If
             provided, the out smooth L1 loss will be multiplied by this tensor
             element by element.
+            A Tensor with type float32.
         sigma (float|None): Hyper parameter of smooth L1 loss layer. A float
            scalar with default value 1.0.
 
     Returns:
-        Variable: The output smooth L1 loss with shape [batch_size, 1].
+        Variable: The output smooth L1 loss with shape [batch_size, 1].  A Tensor with type float32.
 
     Examples:
         .. code-block:: python
 
             import paddle.fluid as fluid
-            data = fluid.layers.data(name='data', shape=[128], dtype='float32')
-            label = fluid.layers.data(
-                name='label', shape=[100], dtype='float32')
-            fc = fluid.layers.fc(input=data, size=100)
-            out = fluid.layers.smooth_l1(x=fc, y=label)
+            import numpy as np
+            data = fluid.data(name="x", shape=[-1, 3], dtype="float32")
+            label = fluid.data(name="y", shape=[-1, 3], dtype="float32")
+            result = fluid.layers.smooth_l1(data,label)
+            place = fluid.CPUPlace()
+            exe = fluid.Executor(place)
+            exe.run(fluid.default_startup_program())
+            x = np.random.rand(3,3).astype("float32")
+            y = np.random.rand(3,3).astype("float32")
+            output= exe.run(feed={"x":x, "y":y},
+                             fetch_list=[result])
+            print(output)
+        
+            #[array([[0.08220536],
+            #       [0.36652038],
+            #      [0.20541131]], dtype=float32)]
+
     """
 
     helper = LayerHelper('smooth_l1_loss', **locals())
@@ -10852,7 +10878,7 @@ def pow(x, factor=1.0, name=None):
 
 
 @templatedoc()
-def stanh(x, scale_a=2.0 / 3.0, scale_b=1.7159, name=None):
+def stanh(x, scale_a=0.67, scale_b=1.7159, name=None):
     """
     ${comment}
     Args:
@@ -10863,15 +10889,28 @@ def stanh(x, scale_a=2.0 / 3.0, scale_b=1.7159, name=None):
                         will be named automatically.
 
     Returns:
-        output(${out_type}): ${out_comment}
+        output(${out_type}): ${out_comment}. 
 
     Examples:
 
         .. code-block:: python
 
             import paddle.fluid as fluid
-            x = fluid.layers.data(name="x", shape=[3,10,32,32], dtype="float32")
-            y = fluid.layers.stanh(x, scale_a=0.67, scale_b=1.72)
+            import numpy as np
+            data = fluid.data(name="input", shape=[-1, 3])
+            result = fluid.layers.stanh(data,scale_a=0.67, scale_b=1.72)
+            place = fluid.CPUPlace()
+            exe = fluid.Executor(place)
+            exe.run(fluid.default_startup_program())
+            x = np.random.random(size=(3, 3)).astype('float32')
+            output= exe.run(feed={"input": x},
+                         fetch_list=[result])
+            print(output)
+
+            #[array([[0.626466  , 0.89842904, 0.7501062 ],
+            #       [0.25147712, 0.7484996 , 0.22902708],
+            #       [0.62705994, 0.23110689, 0.56902856]], dtype=float32)]
+
     """
     helper = LayerHelper('stanh', **locals())
     out = helper.create_variable_for_type_inference(dtype=x.dtype)