[cherry-pick] refine en doc (#20360)

* refine en doc. test=develop. test=document_fix

paddle/fluid/API.spec

@@ -145,10 +145,10 @@ paddle.fluid.layers.conv3d (ArgSpec(args=['input', 'num_filters', 'filter_size',
 paddle.fluid.layers.sequence_pool (ArgSpec(args=['input', 'pool_type', 'is_test', 'pad_value'], varargs=None, keywords=None, defaults=(False, 0.0)), ('document', '5a709f7ef3fdb8fc819d09dc4fbada9a'))
 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', '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'))
-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.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', 'daf9ae55b2d54bd5f35acb397fd1e1b5'))
+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', 'df8edcb8dd020fdddf778c9f613dc650'))
+paddle.fluid.layers.adaptive_pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', 'd873fdd73bcd74f9203d347cfb90de75'))
+paddle.fluid.layers.adaptive_pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', 'a94ed07bf4828e318aaaedb8b037579a'))
 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', '1400433bae7876d0407ae205be39b7a1'))
 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', '23d6fba8ad8495f67a66d8878be5b0be'))
 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'))
@@ -189,7 +189,7 @@ paddle.fluid.layers.row_conv (ArgSpec(args=['input', 'future_context_size', 'par
 paddle.fluid.layers.multiplex (ArgSpec(args=['inputs', 'index'], varargs=None, keywords=None, defaults=None), ('document', '2c4d1ae83da6ed35e3b36ba1b3b51d23'))
 paddle.fluid.layers.layer_norm (ArgSpec(args=['input', 'scale', 'shift', 'begin_norm_axis', 'epsilon', 'param_attr', 'bias_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(True, True, 1, 1e-05, None, None, None, None)), ('document', '79797f827d89ae72c77960e9696883a9'))
 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', '87dd4b818f102bc1a780e1804c28bd38'))
-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.spectral_norm (ArgSpec(args=['weight', 'dim', 'power_iters', 'eps', 'name'], varargs=None, keywords=None, defaults=(0, 1, 1e-12, None)), ('document', '7b3d14d6707d878923847ec617d7d521'))
 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.one_hot (ArgSpec(args=['input', 'depth', 'allow_out_of_range'], varargs=None, keywords=None, defaults=(False,)), ('document', 'cdf5dc2078f1e20dc61dd0bec7e28a29'))
@@ -282,7 +282,7 @@ paddle.fluid.layers.sequence_reverse (ArgSpec(args=['x', 'name'], varargs=None,
 paddle.fluid.layers.affine_channel (ArgSpec(args=['x', 'scale', 'bias', 'data_layout', 'name', 'act'], varargs=None, keywords=None, defaults=(None, None, 'NCHW', None, None)), ('document', 'ecc4b1323028bde0518d666882d03515'))
 paddle.fluid.layers.similarity_focus (ArgSpec(args=['input', 'axis', 'indexes', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '18ec2e3afeb90e70c8b73d2b71c40fdb'))
 paddle.fluid.layers.hash (ArgSpec(args=['input', 'hash_size', 'num_hash', 'name'], varargs=None, keywords=None, defaults=(1, None)), ('document', 'a0b73c21be618cec0281e7903039e5e3'))
-paddle.fluid.layers.grid_sampler (ArgSpec(args=['x', 'grid', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '5d16663e096d7f04954c70ce1cc5e195'))
+paddle.fluid.layers.grid_sampler (ArgSpec(args=['x', 'grid', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '90c74742f48c70b103f1fbb9eb129066'))
 paddle.fluid.layers.log_loss (ArgSpec(args=['input', 'label', 'epsilon', 'name'], varargs=None, keywords=None, defaults=(0.0001, None)), ('document', 'e3993a477c94729526040ff65d95728e'))
 paddle.fluid.layers.add_position_encoding (ArgSpec(args=['input', 'alpha', 'beta', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'e399f9436fed5f7ff480d8532e42c937'))
 paddle.fluid.layers.bilinear_tensor_product (ArgSpec(args=['x', 'y', 'size', 'act', 'name', 'param_attr', 'bias_attr'], varargs=None, keywords=None, defaults=(None, None, None, None)), ('document', '45fc3652a8e1aeffbe4eba371c54f756'))
@@ -290,13 +290,13 @@ paddle.fluid.layers.merge_selected_rows (ArgSpec(args=['x', 'name'], varargs=Non
 paddle.fluid.layers.get_tensor_from_selected_rows (ArgSpec(args=['x', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '2c568321feb4d16c41a83df43f95089d'))
 paddle.fluid.layers.lstm (ArgSpec(args=['input', 'init_h', 'init_c', 'max_len', 'hidden_size', 'num_layers', 'dropout_prob', 'is_bidirec', 'is_test', 'name', 'default_initializer', 'seed'], varargs=None, keywords=None, defaults=(0.0, False, False, None, None, -1)), ('document', 'baa7327ed89df6b7bdd32f9ffdb62f63'))
 paddle.fluid.layers.shuffle_channel (ArgSpec(args=['x', 'group', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '276a1213dd431228cefa33c3146df34a'))
-paddle.fluid.layers.temporal_shift (ArgSpec(args=['x', 'seg_num', 'shift_ratio', 'name'], varargs=None, keywords=None, defaults=(0.25, None)), ('document', '13b1cdcb01f5ffdc26591ff9a2ec4669'))
+paddle.fluid.layers.temporal_shift (ArgSpec(args=['x', 'seg_num', 'shift_ratio', 'name'], varargs=None, keywords=None, defaults=(0.25, None)), ('document', 'd5945431cdcae3cda21914db5bbf383e'))
 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', 'b0e07aa41caae04b07a8e8217cc96020'))
 paddle.fluid.layers.huber_loss (ArgSpec(args=['input', 'label', 'delta'], varargs=None, keywords=None, defaults=None), ('document', '9d93ee81f7a3e526d68bb280bc695d6c'))
-paddle.fluid.layers.kldiv_loss (ArgSpec(args=['x', 'target', 'reduction', 'name'], varargs=None, keywords=None, defaults=('mean', None)), ('document', '18bc95c62d3300456c3c7da5278b47bb'))
+paddle.fluid.layers.kldiv_loss (ArgSpec(args=['x', 'target', 'reduction', 'name'], varargs=None, keywords=None, defaults=('mean', None)), ('document', '45f3ebbcb766fca84cb2fe6307086573'))
 paddle.fluid.layers.npair_loss (ArgSpec(args=['anchor', 'positive', 'labels', 'l2_reg'], varargs=None, keywords=None, defaults=(0.002,)), ('document', '3828c4bd81c25af0ab955f52d453c587'))
 paddle.fluid.layers.pixel_shuffle (ArgSpec(args=['x', 'upscale_factor'], varargs=None, keywords=None, defaults=None), ('document', '7e5cac851fd9bad344230e1044b6a565'))
 paddle.fluid.layers.fsp_matrix (ArgSpec(args=['x', 'y'], varargs=None, keywords=None, defaults=None), ('document', '3a4eb7cce366f5fd8bc38b42b6af5ba1'))
@@ -438,9 +438,9 @@ paddle.fluid.layers.box_decoder_and_assign (ArgSpec(args=['prior_box', 'prior_bo
 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', 'ff4a651d65a9a9f9da71349ba6a2dc1f'))
 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.layers.exponential_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', '48c7b2563a6fc11f23030cde8d7a5c80'))
+paddle.fluid.layers.natural_exp_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', '63edb712ab4ca837049f24a9421dfe30'))
+paddle.fluid.layers.inverse_time_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', 'ff553aa6546eeb1bc692fadb3df78370'))
 paddle.fluid.layers.polynomial_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'end_learning_rate', 'power', 'cycle'], varargs=None, keywords=None, defaults=(0.0001, 1.0, False)), ('document', 'a343254c36c2e89512cd8cd8a1960ead'))
 paddle.fluid.layers.piecewise_decay (ArgSpec(args=['boundaries', 'values'], varargs=None, keywords=None, defaults=None), ('document', 'd9f654117542c6b702963dda107a247f'))
 paddle.fluid.layers.noam_decay (ArgSpec(args=['d_model', 'warmup_steps'], varargs=None, keywords=None, defaults=None), ('document', 'fd57228fb76195e66bbcc8d8e42c494d'))

paddle/fluid/operators/kldiv_loss_op.cc

@@ -69,10 +69,12 @@ class KLDivLossOpMaker : public framework::OpProtoAndCheckerMaker {
     AddInput("X",
              "The input tensor of KL divergence loss operator. "
              "This is a tensor with shape of [N, *], where N is the "
-             "batch size, * means any number of additional dimensions.");
+             "batch size, * means any number of additional dimensions. "
+             "The data type is float32 or flaot64");
     AddInput("Target",
              "The  tensor of KL divergence loss operator. "
-             "This is a tensor with shape of Input(X).");
+             "This is a tensor with shape of Input(X). "
+             "The data type is same as Input(X)");
     AddOutput(
         "Loss",
         "The output KL divergence loss tensor. if Attr(reduction) is "
@@ -90,7 +92,8 @@ class KLDivLossOpMaker : public framework::OpProtoAndCheckerMaker {
 
     AddComment(R"DOC(
          This operator calculates the Kullback-Leibler divergence loss
-         between Input(X) and Input(Target).
+         between Input(X) and Input(Target). Notes that Input(X) is the
+         log-probability and Input(Target) is the probability.
 
          KL divergence loss is calculated as follows:
 

paddle/fluid/operators/pool_op.cc

@@ -200,8 +200,9 @@ void Pool2dOpMaker::Make() {
   // TypedAttrChecker don't support vector type.)
   AddAttr<bool>(
       "global_pooling",
-      "(bool, default false) Whether to use the global pooling. "
-      "If global_pooling = true, kernel size and paddings will be ignored.")
+      "(bool) Whether to use the global pooling. "
+      "If global_pooling = true, kernel size and paddings will be ignored. "
+      "Default False.")
       .SetDefault(false);
   AddAttr<std::vector<int>>("strides",
                             "(vector<int>, default {1, 1}), strides(height, "
@@ -217,36 +218,38 @@ void Pool2dOpMaker::Make() {
       .SetDefault({0, 0});
   AddAttr<bool>(
       "exclusive",
-      "(bool, default True) When true, will exclude the zero-padding in the "
+      "(bool) When true, will exclude the zero-padding in the "
       "averaging calculating, otherwise, include the zero-padding. Note, it "
-      "is only used when pooling_type is avg. The default is True.")
+      "is only used when pooling_type is avg. The default is True. "
+      "Default True.")
       .SetDefault(true);
   AddAttr<bool>(
       "adaptive",
-      "(bool, default False) When true, will perform adaptive pooling instead, "
+      "(bool) When true, will perform adaptive pooling instead, "
       "output shape in H and W dimensions will be same as ksize, input data "
       "will be divided into grids specify by ksize averagely and perform "
-      "pooling in each grid area to get output pooling value.")
+      "pooling in each grid area to get output pooling value. "
+      "Default False.")
       .SetDefault(false);
 
   AddAttr<bool>(
       "use_cudnn",
-      "(bool, default false) Only used in cudnn kernel, need install cudnn.")
+      "(bool) Only used in cudnn kernel, need install cudnn. Default False")
       .SetDefault(false);
   AddAttr<bool>(
       "ceil_mode",
-      "(bool, default false) Whether to use the ceil function to calculate "
+      "(bool) Whether to use the ceil function to calculate "
       "output height and width. False is the default. If it is set to False, "
-      "the floor function will be used.")
+      "the floor function will be used. Default False")
       .SetDefault(false);
   AddAttr<bool>("use_mkldnn",
-                "(bool, default false) Only used in mkldnn kernel.")
+                "(bool) Only used in mkldnn kernel. Default False")
       .SetDefault(false);
   AddAttr<bool>("use_quantizer",
-                "(bool, default false) "
+                "(bool) "
                 "Set to true for operators that should be quantized and use "
                 "int8 kernel. "
-                "Only used on CPU.")
+                "Only used on CPU. Default False")
       .SetDefault(false);
   AddAttr<std::string>(
       "data_format",
@@ -269,11 +272,11 @@ void Pool2dOpMaker::Make() {
   // TODO(dzhwinter): need to registered layout transform function
 
   AddComment(R"DOC(
-The pooling2d operation calculates the output based on
-the input, pooling_type and ksize, strides, paddings parameters.
-Input(X) and output(Out) are in NCHW or NHWC format, where N is batch size, C is the
+This operation calculates the pooling output based on
+the input, pooling_type and pool_size, pool_stride, pool_padding parameters.
+Input(X) and Output(Out) are in NCHW or NHWC format, where N is batch size, C is the
 number of channels, H is the height of the feature, and W is the width of the feature.
-Parameters(ksize, strides, paddings) are two elements.
+Parameters(pool_size, pool_stride, pool_padding) hold two integer elements.
 These two elements represent height and width, respectively.
 The input(X) size and output(Out) size may be different.
 
@@ -393,8 +396,9 @@ void Pool3dOpMaker::Make() {
   // TypedAttrChecker don't support vector type.)
   AddAttr<bool>(
       "global_pooling",
-      "(bool, default false) Whether to use the global pooling. "
-      "If global_pooling = true, kernel size and paddings will be ignored.")
+      "(bool) Whether to use the global pooling. "
+      "If global_pooling = true, kernel size and paddings will be ignored. "
+      "Default False")
       .SetDefault(false);
   AddAttr<std::vector<int>>(
       "strides",
@@ -413,30 +417,32 @@ void Pool3dOpMaker::Make() {
                                // TypedAttrChecker don't support vector type.)
   AddAttr<bool>(
       "exclusive",
-      "(bool, default True) When true, will exclude the zero-padding in the "
+      "(bool) When true, will exclude the zero-padding in the "
       "averaging calculating, otherwise, include the zero-padding. Note, it "
-      "is only used when pooling_type is avg. The default is True.")
+      "is only used when pooling_type is avg. The default is True. "
+      "Default True")
       .SetDefault(true);
   AddAttr<bool>(
       "adaptive",
-      "(bool, default False) When true, will perform adaptive pooling instead, "
+      "(bool) When true, will perform adaptive pooling instead, "
       "output shape in H and W dimensions will be same as ksize, input data "
       "will be divided into grids specify by ksize averagely and perform "
-      "pooling in each grid area to get output pooling value.")
+      "pooling in each grid area to get output pooling value. "
+      "Default False")
       .SetDefault(false);
 
   AddAttr<bool>(
       "use_cudnn",
-      "(bool, default false) Only used in cudnn kernel, need install cudnn.")
+      "(bool) Only used in cudnn kernel, need install cudnn. Default False")
       .SetDefault(false);
   AddAttr<bool>(
       "ceil_mode",
-      "(bool, default false) Whether to use the ceil function to calculate "
+      "(bool) Whether to use the ceil function to calculate "
       "output height and width. False is the default. If it is set to False, "
-      "the floor function will be used.")
+      "the floor function will be used. Default False")
       .SetDefault(false);
   AddAttr<bool>("use_mkldnn",
-                "(bool, default false) Only used in mkldnn kernel")
+                "(bool) Only used in mkldnn kernel. Default False")
       .SetDefault(false);
   AddAttr<std::string>(
       "data_format",
@@ -454,14 +460,12 @@ void Pool3dOpMaker::Make() {
   // TODO(dzhwinter): need to registered layout transform function
 
   AddComment(R"DOC(
-Pool3d Operator.
-
-The pooling3d operation calculates the output based on
-the input, pooling_type, ksize, strides, and paddings parameters.
+This operation calculates the output based on
+the input, pooling_type, pool_size, pool_stride, and pool_padding parameters.
 Input(X) and output(Out) are in NCDHW or NDHWC format, where N is batch
 size, C is the number of channels, and D, H and W are the depth, height and
-width of the feature, respectively. Parameters(ksize, strides, paddings)
-are three elements. These three elements represent depth, height and
+width of the feature, respectively. Parameters(pool_size, pool_stride, pool_padding)
+hold three integer elements. These three elements represent depth, height and
 width, respectively. The input(X) size and output(Out) size may be different.
 
 Example:

paddle/fluid/operators/spectral_norm_op.cc

@@ -88,7 +88,8 @@ class SpectralNormOpMaker : public framework::OpProtoAndCheckerMaker {
     AddInput("Weight",
              "The input weight tensor of spectral_norm operator, "
              "This can be a 2-D, 3-D, 4-D, 5-D tensor which is the "
-             "weights of fc, conv1d, conv2d, conv3d layer.");
+             "weights of fc, conv1d, conv2d, conv3d layer. "
+             "The data type is float32 or float64.");
     AddInput("U",
              "The weight_u tensor of spectral_norm operator, "
              "This can be a 1-D tensor in shape [H, 1],"
@@ -123,7 +124,9 @@ class SpectralNormOpMaker : public framework::OpProtoAndCheckerMaker {
         .SetDefault(1);
     AddAttr<float>("eps",
                    "epsilon for numerical stability in "
-                   "calculating norms")
+                   "calculating norms, it will be added to "
+                   "the denominator to aviod divide zero. "
+                   "Default 1e-12.")
         .SetDefault(1e-12);
 
     AddComment(R"DOC(

paddle/fluid/operators/temporal_shift_op.cc

@@ -69,7 +69,8 @@ class TemporalShiftOpMaker : public framework::OpProtoAndCheckerMaker {
              "This is a 4-D tensor with shape of [N*T,  C, H, W]. "
              "While N is the batch size, T is the temporal segment "
              "number, C is the channel number, H is the height of "
-             "features and W is the width of features.");
+             "features and W is the width of features. "
+             "The data type is float32 and float64");
     AddOutput("Out",
               "The output tensor of temporal shift operator. "
               "This is a 4-D tensor in the same shape with Input(X).");
@@ -82,7 +83,8 @@ class TemporalShiftOpMaker : public framework::OpProtoAndCheckerMaker {
         "The shift ratio of the channels, the first :attr:`shift_ratio` part "
         "of channels will be shifted by -1 along the temporal dimension, "
         "and the second :attr:`shift_ratio` part of channels will be shifted "
-        "by 1 along the temporal dimension. Default 0.25.")
+        "by 1 along the temporal dimension. :attr:`shift_ratio` should be in "
+        "range [0, 0.5]. Default 0.25.")
         .SetDefault(0.25);
 
     AddComment(R"DOC(

python/paddle/fluid/layers/learning_rate_scheduler.py

@@ -109,20 +109,25 @@ def exponential_decay(learning_rate, decay_steps, decay_rate, staircase=False):
     training progresses. By using this function, the learning rate will be decayed by
     'decay_rate' every 'decay_steps' steps.
 
+    Decayed learning rate calcualtes as follows:
+
     >>> if staircase == True:
     >>>     decayed_learning_rate = learning_rate * decay_rate ^ floor(global_step / decay_steps)
     >>> else:
     >>>     decayed_learning_rate = learning_rate * decay_rate ^ (global_step / decay_steps)
 
     Args:
-        learning_rate(Variable|float): The initial learning rate.
-        decay_steps(int): See the decay computation above.
-        decay_rate(float): The decay rate. See the decay computation above.
-        staircase(Boolean): If True, decay the learning rate at discrete intervals.
-                            Default: False
+        learning_rate(Variable|float): The initial learning rate. It should be a Variable 
+                                       or a float
+        decay_steps(int): The learning rate decay steps. See the decay computation above.
+        decay_rate(float): The learning rate decay rate. See the decay computation above.
+        staircase(bool): If True, decay the learning rate at discrete intervals, which 
+                         means the learning rate will be decayed by `decay_rate` every
+                         `decay_steps`. If False, learning rate will be decayed continuously
+                         and following the formula above. Default: False
 
     Returns:
-        Variable: The decayed learning rate
+        Variable: The decayed learning rate. The data type is float32.
 
     Examples:
         .. code-block:: python
@@ -156,20 +161,29 @@ def exponential_decay(learning_rate, decay_steps, decay_rate, staircase=False):
 def natural_exp_decay(learning_rate, decay_steps, decay_rate, staircase=False):
     """Applies natural exponential decay to the initial learning rate.
 
+    When training a model, it is often recommended to lower the learning rate as the
+    training progresses. By using this function, the learning rate will be decayed by
+    natural exponential power 'decay_rate' every 'decay_steps' steps.
+
+    Decayed learning rate calcualtes as follows:
+
     >>> if not staircase:
     >>>     decayed_learning_rate = learning_rate * exp(- decay_rate * (global_step / decay_steps))
     >>> else:
     >>>     decayed_learning_rate = learning_rate * exp(- decay_rate * floor(global_step / decay_steps))
 
     Args:
-        learning_rate: A scalar float32 value or a Variable. This
-          will be the initial learning rate during training
-        decay_steps: A Python `int32` number.
-        decay_rate: A Python `float` number.
-        staircase: Boolean. If set true, decay the learning rate every decay_steps.
+        learning_rate(Variable|float): The initial learning rate. It should be a Variable 
+                                       or a float
+        decay_steps(int): The learning rate decay steps. See the decay computation above.
+        decay_rate(float): The learning rate decay rate. See the decay computation above.
+        staircase(bool): If True, decay the learning rate at discrete intervals, which 
+                         means the learning rate will be decayed by natual exponential power
+                         `decay_rate` every `decay_steps`. If False, learning rate will be
+                         decayed continuously and following the formula above. Default: False
 
     Returns:
-        The decayed learning rate
+        The decayed learning rate. The data type is float32.
 
     Examples:
         .. code-block:: python
@@ -208,20 +222,25 @@ def inverse_time_decay(learning_rate, decay_steps, decay_rate, staircase=False):
     training progresses. By using this function, an inverse decay function will be
     applied to the initial learning rate.
 
+    Decayed learning rate calcualtes as follows:
+
     >>> if staircase == True:
     >>>     decayed_learning_rate = learning_rate / (1 + decay_rate * floor(global_step / decay_step))
     >>> else:
     >>>     decayed_learning_rate = learning_rate / (1 + decay_rate * global_step / decay_step)
 
     Args:
-        learning_rate(Variable|float): The initial learning rate.
-        decay_steps(int): See the decay computation above.
-        decay_rate(float): The decay rate. See the decay computation above.
-        staircase(Boolean): If True, decay the learning rate at discrete intervals.
-                            Default: False
+        learning_rate(Variable|float): The initial learning rate. It should be a Variable 
+                                       or a float
+        decay_steps(int): The learning rate decay steps. See the decay computation above.
+        decay_rate(float): The learning rate decay rate. See the decay computation above.
+        staircase(bool): If True, decay the learning rate at discrete intervals, which 
+                         means the learning rate will be decayed by `decay_rate` times 
+                         every `decay_steps`. If False, learning rate will be decayed 
+                         continuously and following the formula above. Default: False
 
     Returns:
-        Variable: The decayed learning rate
+        Variable: The decayed learning rate. The data type is float32.
 
     Examples:
         .. code-block:: python
@@ -229,7 +248,7 @@ def inverse_time_decay(learning_rate, decay_steps, decay_rate, staircase=False):
           import paddle.fluid as fluid
           base_lr = 0.1
           sgd_optimizer = fluid.optimizer.SGD(
-	      learning_rate=fluid.layers.natural_exp_decay(
+	      learning_rate=fluid.layers.inverse_time_decay(
 		    learning_rate=base_lr,
 		    decay_steps=10000,
 		    decay_rate=0.5,

python/paddle/fluid/layers/nn.py

@@ -3272,10 +3272,11 @@ def pool2d(input,
     ${comment}
 
     Args:
-        input (Variable): The input tensor of pooling operator. The format of
-                          input tensor is `"NCHW"` or `"NHWC"`, where `N` is batch size, `C` is
-                          the number of channels, `H` is the height of the
-                          feature, and `W` is the width of the feature.
+        input (Variable): The input tensor of pooling operator which is a 4-D tensor with
+                          shape [N, C, H, W]. The format of input tensor is `"NCHW"` or
+                          `"NHWC"`, where `N` is batch size, `C` is the number of channels,
+                          `H` is the height of the feature, and `W` is the width of the
+                          feature. The data type if float32 or float64.
         pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list,
             it must contain two integers, (pool_size_Height, pool_size_Width).
             Otherwise, the pool kernel size will be a square of an int.
@@ -3294,8 +3295,9 @@ def pool2d(input,
         global_pooling (bool): ${global_pooling_comment}
         use_cudnn (bool): ${use_cudnn_comment}
         ceil_mode (bool): ${ceil_mode_comment}
-        name (str|None): A name for this layer(optional). If set None, the
-                        layer will be named automatically.
+        name(str, optional): For detailed information, please refer
+                             to :ref:`api_guide_Name`. Usually name is no need to set and
+                             None by default.
         exclusive (bool): Whether to exclude padding points in average pooling
                           mode, default is `true`.
         data_format (string): The data format of the input and output data. An optional string from: `"NCHW"`, `"NDHW"`.
@@ -3303,7 +3305,7 @@ def pool2d(input,
                 `[batch_size, input_channels, input_height, input_width]`.
 
     Returns:
-        Variable: The pooling result.
+        Variable: The output tensor of pooling result. The data type is same as input tensor.
 
     Raises:
         ValueError: If `pool_type` is not "max" nor "avg"
@@ -3316,10 +3318,32 @@ def pool2d(input,
 
           import paddle.fluid as fluid
 
-          data = fluid.layers.data(
-              name='data', shape=[10, 3, 32, 32], append_batch_size=False, dtype='float32')
+          data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
+
+          # max pool2d
+          pool2d = fluid.layers.pool2d(
+            input = data,
+            pool_size = 2,
+            pool_type = "max",
+            pool_stride = 1,
+            global_pooling=False)
+
+          # average pool2d
+          pool2d = fluid.layers.pool2d(
+            input = data,
+            pool_size = 2,
+            pool_type = "avg",
+            pool_stride = 1,
+            global_pooling=False)
+
+          # global average pool2d
+          pool2d = fluid.layers.pool2d(
+            input = data,
+            pool_size = 2,
+            pool_type = "avg",
+            pool_stride = 1,
+            global_pooling=True)
 
-          # example 1:
           # Attr(pool_padding) is a list with 4 elements, Attr(data_format) is "NCHW".
           out_1 = fluid.layers.pool2d(
             input = data,
@@ -3329,7 +3353,6 @@ def pool2d(input,
             pool_padding = [1, 2, 1, 0],
             data_format = "NCHW")
 
-          # example 2:
           # Attr(pool_padding) is a string, Attr(data_format) is "NCHW".
           out_2 = fluid.layers.pool2d(
             input = data,
@@ -3451,7 +3474,8 @@ def pool3d(input,
     ${comment}
 
     Args:
-        input (Variable): The input tensor of pooling operator. The format of
+        input (Variable): The input tensor of pooling operator, which is a 5-D tensor with
+                          shape [N, C, D, H, W]. The format of
                           input tensor is `"NCDHW"` or `"NDHWC"`, where `N` is batch size, `C` is
                           the number of channels, `D` is the depth of the feature,
                           `H` is the height of the feature, and `W` is the width
@@ -3475,8 +3499,9 @@ def pool3d(input,
         global_pooling (bool): ${global_pooling_comment}
         use_cudnn (bool): ${use_cudnn_comment}
         ceil_mode (bool): ${ceil_mode_comment}
-        name (str): A name for this layer(optional). If set None, the layer
-            will be named automatically.
+        name(str, optional): For detailed information, please refer
+                             to :ref:`api_guide_Name`. Usually name is no need to set and
+                             None by default.
         exclusive (bool): Whether to exclude padding points in average pooling
                           mode, default is true.
         data_format (string): The data format of the input and output data. An optional string from: `"NCDHW"`, `"NDHWC"`.
@@ -3484,7 +3509,7 @@ def pool3d(input,
                 `[batch_size, input_channels, input_depth, input_height, input_width]`.
 
     Returns:
-        Variable: output of pool3d layer.
+        Variable: The output tensor of pooling result. The data type is same as input tensor.
 
     Examples:
 
@@ -3492,8 +3517,31 @@ def pool3d(input,
 
           import paddle.fluid as fluid
 
-          data = fluid.layers.data(
-              name='data', shape=[10, 3, 32, 32, 32], append_batch_size=False, dtype='float32')
+          data = fluid.data(name='data', shape=[None, 3, 32, 32, 32], dtype='float32')
+
+          # max pool3d
+          pool3d = fluid.layers.pool3d(
+            input = data,
+            pool_size = 2,
+            pool_type = "max",
+            pool_stride = 1,
+            global_pooling=False)
+
+          # average pool3d
+          pool3d = fluid.layers.pool3d(
+            input = data,
+            pool_size = 2,
+            pool_type = "avg",
+            pool_stride = 1,
+            global_pooling=False)
+
+          # global average pool3d
+          pool3d = fluid.layers.pool3d(
+            input = data,
+            pool_size = 2,
+            pool_type = "avg",
+            pool_stride = 1,
+            global_pooling=True)
 
           # example 1:
           # Attr(pool_padding) is a list with 6 elements, Attr(data_format) is "NCDHW".
@@ -3625,13 +3673,12 @@ def adaptive_pool2d(input,
                     require_index=False,
                     name=None):
     """
-    **Adaptive Pool2d Operator**
-    The adaptive_pool2d operation calculates the output based on the input, pool_size,
+    This operation calculates the output based on the input, pool_size,
     pool_type parameters. Input(X) and output(Out) are in NCHW format, where N is batch
     size, C is the number of channels, H is the height of the feature, and W is
     the width of the feature. Parameters(pool_size) should contain two elements which
     represent height and width, respectively. Also the H and W dimensions of output(Out)
-    is same as Parameter(pool_size).
+    is same as Parameter(pool_size). The output tensor shape will be [N, C, pool_size[0], pool_size[1]]
 
     For average adaptive pool2d:
 
@@ -3648,20 +3695,23 @@ def adaptive_pool2d(input,
        Output(i ,j) &= \\frac{sum(Input[hstart:hend, wstart:wend])}{(hend - hstart) * (wend - wstart)}
 
     Args:
-        input (Variable): The input tensor of pooling operator. The format of
-                          input tensor is NCHW, where N is batch size, C is
-                          the number of channels, H is the height of the
-                          feature, and W is the width of the feature.
+        input (Variable): The input tensor of pooling operator, which is a 4-D tensor
+                          with shape [N, C, H, W].  The format of input tensor is NCHW,
+                          where N is batch size, C is the number of channels, H is the
+                          height of the feature, and W is the width of the feature.
+                          The data type is float32 or float64.
         pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list,
             it must contain two integers, (pool_size_Height, pool_size_Width).
         pool_type: ${pooling_type_comment}
         require_index (bool): If true, the index of max pooling point will be returned along
-            with outputs. It cannot be set in average pooling type.
-        name (str|None): A name for this layer(optional). If set None, the
-                        layer will be named automatically.
+            with outputs. It cannot be set in average pooling type. Default False.
+        name(str, optional): For detailed information, please refer
+                             to :ref:`api_guide_Name`. Usually name is no need to set and
+                             None by default.
 
     Returns:
-        Variable: The pooling result.
+        Variable: The output tensor of adaptive pooling result. The data type is same 
+                  as input tensor.
 
     Raises:
         ValueError: 'pool_type' is not 'max' nor 'avg'.
@@ -3671,6 +3721,7 @@ def adaptive_pool2d(input,
     Examples:
         .. code-block:: python
 
+          # average adaptive pool2d
           # suppose input data in shape of [N, C, H, W], `pool_size` is [m, n],
           # output shape is [N, C, m, n], adaptive pool divide H and W dimentions
           # of input data into m * n grids averagely and performs poolings in each
@@ -3686,12 +3737,33 @@ def adaptive_pool2d(input,
           #             output[:, :, i, j] = avg(input[:, :, hstart: hend, wstart: wend])
           #
           import paddle.fluid as fluid
-          data = fluid.layers.data(
-              name='data', shape=[3, 32, 32], dtype='float32')
+          data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
           pool_out = fluid.layers.adaptive_pool2d(
                             input=data,
                             pool_size=[3, 3],
                             pool_type='avg')
+
+          # max adaptive pool2d
+          # suppose input data in shape of [N, C, H, W], `pool_size` is [m, n],
+          # output shape is [N, C, m, n], adaptive pool divide H and W dimentions
+          # of input data into m * n grids averagely and performs poolings in each
+          # grid to get output.
+          # adaptive average pool performs calculations as follow:
+          #
+          #     for i in range(m):
+          #         for j in range(n):
+          #             hstart = floor(i * H / m)
+          #             hend = ceil((i + 1) * H / m)
+          #             wstart = floor(i * W / n)
+          #             wend = ceil((i + 1) * W / n)
+          #             output[:, :, i, j] = max(input[:, :, hstart: hend, wstart: wend])
+          #
+          import paddle.fluid as fluid
+          data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
+          pool_out = fluid.layers.adaptive_pool2d(
+                            input=data,
+                            pool_size=[3, 3],
+                            pool_type='max')
     """
     if pool_type not in ["max", "avg"]:
         raise ValueError(
@@ -3738,13 +3810,13 @@ def adaptive_pool3d(input,
                     require_index=False,
                     name=None):
     """
-    **Adaptive Pool3d Operator**
-    The adaptive_pool3d operation calculates the output based on the input, pool_size,
+    This operation calculates the output based on the input, pool_size,
     pool_type parameters. Input(X) and output(Out) are in NCDHW format, where N is batch
     size, C is the number of channels, D is the depth of the feature, H is the height of
     the feature, and W is the width of the feature. Parameters(pool_size) should contain
     three elements which represent height and width, respectively. Also the D, H and W
-    dimensions of output(Out) is same as Parameter(pool_size).
+    dimensions of output(Out) is same as Parameter(pool_size). The output tensor shape
+    will be [N, C, pool_size[0], pool_size[1], pool_size[2]]
 
     For average adaptive pool3d:
 
@@ -3765,20 +3837,22 @@ def adaptive_pool3d(input,
       Output(i ,j, k) &= \\frac{sum(Input[dstart:dend, hstart:hend, wstart:wend])}{(dend - dstart) * (hend - hstart) * (wend - wstart)}
 
     Args:
-        input (Variable): The input tensor of pooling operator. The format of
-                          input tensor is NCDHW, where N is batch size, C is
-                          the number of channels, D is the depth of the feature,
+        input (Variable): The input tensor of pooling operator, which is a 5-D tensor with 
+                          shape [N, C, D, H, W]. The format of input tensor is NCDHW, where
+                          N is batch size, C is the number of channels, D is the depth of the feature,
                           H is the height of the feature, and W is the width of the feature.
+                          The data type is float32 or float64.
         pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list,
             it must contain three integers, (Depth, Height, Width).
         pool_type: ${pooling_type_comment}
         require_index (bool): If true, the index of max pooling point will be returned along
-            with outputs. It cannot be set in average pooling type.
-        name (str|None): A name for this layer(optional). If set None, the
-                        layer will be named automatically.
+            with outputs. It cannot be set in average pooling type. Default False.
+        name(str, optional): For detailed information, please refer
+                             to :ref:`api_guide_Name`. Usually name is no need to set and
+                             None by default.
 
     Returns:
-        Variable: The pooling result.
+        Variable: The output tensor of adaptive pooling result. The data type is same as input tensor.
 
     Raises:
         ValueError: 'pool_type' is not 'max' nor 'avg'.
@@ -3788,6 +3862,7 @@ def adaptive_pool3d(input,
     Examples:
         .. code-block:: python
 
+          # average adaptive pool3d
           # suppose input data in shape of [N, C, D, H, W], `pool_size` is [l, m, n],
           # output shape is [N, C, l, m, n], adaptive pool divide D, H and W dimentions
           # of input data into l * m * n grids averagely and performs poolings in each
@@ -3809,12 +3884,41 @@ def adaptive_pool3d(input,
 
           import paddle.fluid as fluid
 
-          data = fluid.layers.data(
-              name='data', shape=[3, 32, 32, 32], dtype='float32')
+          data = fluid.data(
+              name='data', shape=[None, 3, 32, 32, 32], dtype='float32')
           pool_out = fluid.layers.adaptive_pool3d(
                             input=data,
                             pool_size=[3, 3, 3],
                             pool_type='avg')
+
+          # max adaptive pool3d
+          # suppose input data in shape of [N, C, D, H, W], `pool_size` is [l, m, n],
+          # output shape is [N, C, l, m, n], adaptive pool divide D, H and W dimentions
+          # of input data into l * m * n grids averagely and performs poolings in each
+          # grid to get output.
+          # adaptive average pool performs calculations as follow:
+          #
+          #     for i in range(l):
+          #         for j in range(m):
+          #             for k in range(n):
+          #                 dstart = floor(i * D / l)
+          #                 dend = ceil((i + 1) * D / l)
+          #                 hstart = floor(j * H / m)
+          #                 hend = ceil((j + 1) * H / m)
+          #                 wstart = floor(k * W / n)
+          #                 wend = ceil((k + 1) * W / n)
+          #                 output[:, :, i, j, k] =
+          #                     avg(input[:, :, dstart:dend, hstart: hend, wstart: wend])
+          #
+
+          import paddle.fluid as fluid
+
+          data = fluid.data(
+              name='data', shape=[None, 3, 32, 32, 32], dtype='float32')
+          pool_out = fluid.layers.adaptive_pool3d(
+                            input=data,
+                            pool_size=[3, 3, 3],
+                            pool_type='max')
     """
     if pool_type not in ["max", "avg"]:
         raise ValueError(
@@ -4524,9 +4628,10 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None):
     """
     **Spectral Normalization Layer**
 
-    This layer calculates the spectral normalization value of weight parameters of
+    This operation calculates the spectral normalization value of weight parameters of
     fc, conv1d, conv2d, conv3d layers which should be 2-D, 3-D, 4-D, 5-D
-    Parameters. Calculations are showed as follows.
+    Parameters. Output tensor will be in same shape with input tensor.
+    Calculations are showed as follows.
 
     Step 1:
     Generate vector U in shape of [H], and V in shape of [W].
@@ -4535,7 +4640,8 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None):
 
     Step 2:
     :attr:`power_iters` shoule be a positive interger, do following
-    calculations with U and V for :attr:`power_iters` rounds.
+    calculations with U and V for :attr:`power_iters` rounds. Calculations
+    as follows:
 
     .. math:: 
 
@@ -4560,18 +4666,20 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None):
         dim(int): ${dim_comment}
         power_iters(int): ${power_iters_comment}
         eps(float): ${eps_comment}
-        name (str): The name of this layer. It is optional.
+        name(str, optional): For detailed information, please refer
+                             to :ref:`api_guide_Name`. Usually name is no need to set and
+                             None by default.
 
     Returns:
         Variable: A tensor variable of weight parameters after spectral normalization.
+                  The data type and shape is same as input tensor.
 
     Examples:
        .. code-block:: python
 
             import paddle.fluid as fluid
 
-            weight = fluid.layers.data(name='weight', shape=[2, 8, 32, 32], 
-                                       append_batch_size=False, dtype='float32')
+            weight = fluid.data(name='weight', shape=[2, 8, 32, 32], dtype='float32')
             x = fluid.layers.spectral_norm(weight=weight, dim=1, power_iters=2)
     """
     helper = LayerHelper('spectral_norm', **locals())
@@ -13986,19 +14094,22 @@ def grid_sampler(x, grid, name=None):
     """
     This operation samples input X by using bilinear interpolation based on
     flow field grid, which is usually gennerated by :code:`affine_grid` . The grid of
-    shape [N, H, W, 2] is the concatenation of (grid_x, grid_y) coordinates
-    with shape [N, H, W] each, where grid_x is indexing the 4th dimension
-    (in width dimension) of input data x and grid_y is indexng the 3rd
+    shape [N, H, W, 2] is the concatenation of (x, y) coordinates
+    with shape [N, H, W] each, where x is indexing the 4th dimension
+    (in width dimension) of input data x and y is indexng the 3rd
     dimention (in height dimension), finally results is the bilinear
-    interpolation value of 4 nearest corner points.
+    interpolation value of 4 nearest corner points. The output tensor 
+    shape will be [N, C, H, W].
 
     .. code-block:: text
 
         Step 1:
         Get (x, y) grid coordinates and scale to [0, H-1/W-1].
 
-        grid_x = 0.5 * (grid[:, :, :, 0] + 1) * (W - 1)
-        grid_y = 0.5 * (grid[:, :, :, 1] + 1) * (H - 1)
+        .. code-block:: text
+
+            grid_x = 0.5 * (grid[:, :, :, 0] + 1) * (W - 1)
+            grid_y = 0.5 * (grid[:, :, :, 1] + 1) * (H - 1)
 
         Step 2:
         Indices input data X with grid (x, y) in each [H, W] area, and bilinear
@@ -14033,13 +14144,20 @@ def grid_sampler(x, grid, name=None):
                + ws * d_e * d_n + es * d_w * d_n
 
     Args:
-        x(Variable): Input data of shape [N, C, H, W].
-        grid(Variable): Input grid tensor of shape [N, H, W, 2].
-        name (str, default None): The name of this layer.
+        x(Variable): The input tensor, which is a 4-D tensor with shape
+                     [N, C, H, W], N is the batch size, C is the channel
+                     number, H and W is the feature height and width.
+                     The data type is float32 or float64.
+        grid(Variable): Input grid tensor of shape [N, H, W, 2]. The
+                        data type is float32 or float64.
+        name(str, optional): For detailed information, please refer
+                             to :ref:`api_guide_Name`. Usually name is no need to set and
+                             None by default.
 
     Returns:
         Variable: Output of shape [N, C, H, W] data samples input X
-        using bilnear interpolation based on input grid.
+                  using bilnear interpolation based on input grid.
+                  The data type is same as input tensor.
 
     Examples:
 
@@ -14047,7 +14165,8 @@ def grid_sampler(x, grid, name=None):
 
             import paddle.fluid as fluid
 
-            x = fluid.layers.data(name='x', shape=[10, 32, 32], dtype='float32')
+            # use with affine_grid
+            x = fluid.data(name='x', shape=[None, 10, 32, 32], dtype='float32')
             theta = fluid.layers.data(name='theta', shape=[2, 3], dtype='float32')
             grid = fluid.layers.affine_grid(theta=theta, out_shape=[3, 10, 32, 32])
             out = fluid.layers.grid_sampler(x=x, grid=grid)
@@ -14431,11 +14550,13 @@ def temporal_shift(x, seg_num, shift_ratio=0.25, name=None):
         x(Variable): ${x_comment}
         seg_num(int): ${seg_num_comment}
         shift_ratio(float): ${shift_ratio_comment}
-        name (str, default None): The name of this layer.
+        name(str, optional): For detailed information, please refer
+                             to :ref:`api_guide_Name`. Usually name is no need to set and
+                             None by default.
 
     Returns:
         out(Variable): The temporal shifting result is a tensor variable with the 
-        same shape and same type as the input.
+        same shape and same data type as the input.
 
     Raises:
         TypeError: seg_num must be int type.
@@ -14444,7 +14565,7 @@ def temporal_shift(x, seg_num, shift_ratio=0.25, name=None):
         .. code-block:: python
 
             import paddle.fluid as fluid
-            input = fluid.layers.data(name='input', shape=[4,2,2], dtype='float32')
+            input = fluid.data(name='input', shape=[None,4,2,2], dtype='float32')
             out = fluid.layers.temporal_shift(x=input, seg_num=2, shift_ratio=0.2)
     """
     helper = LayerHelper("temporal_shift", **locals())
@@ -14875,16 +14996,18 @@ def kldiv_loss(x, target, reduction='mean', name=None):
         x (Variable): ${x_comment}
         target (Variable): ${target_comment}
         reduction (Variable): ${reduction_comment}
-        name (str, default None): The name of this layer.
+        name(str, optional): For detailed information, please refer
+                             to :ref:`api_guide_Name`. Usually name is no need to set and
+                             None by default.
 
     Returns:
-        kldiv\_loss (Variable): The KL divergence loss.
+        Variable(Tensor): The KL divergence loss. The data type is same as input tensor
 
     Examples:
         .. code-block:: python
 
             import paddle.fluid as fluid
-            x = fluid.layers.data(name='x', shape=[4,2,2], dtype='float32')
+            x = fluid.data(name='x', shape=[None,4,2,2], dtype='float32')
             target = fluid.layers.data(name='target', shape=[4,2,2], dtype='float32')
             loss = fluid.layers.kldiv_loss(x=x, target=target, reduction='batchmean')
     """