Fix spelling errors (#18213)

benchmark/fluid/README.md

@@ -59,7 +59,7 @@ python -c 'from recordio_converter import *; prepare_mnist("data", 1)'
 ## Run Distributed Benchmark on Kubernetes Cluster
 
 You may need to build a Docker image before submitting a cluster job onto Kubernetes, or you will
-have to start all those processes mannually on each node, which is not recommended.
+have to start all those processes manually on each node, which is not recommended.
 
 To build the Docker image, you need to choose a paddle "whl" package to run with, you may either
 download it from

paddle/.common_test_util.sh

@@ -26,7 +26,7 @@ chmod a+rw $PORT_FILE $PORT_LOCK_FILE 2>/dev/null
 #
 # There are two parameter of this method
 # param 1: the begin of port range
-# param 2: the lenght of port range.
+# param 2: the length of port range.
 # so, the port range is [param1, param1+param2)
 acquire_ports(){
   (

paddle/fluid/API.spec

@@ -73,8 +73,8 @@ paddle.fluid.initializer.init_on_cpu (ArgSpec(args=[], varargs=None, keywords=No
 paddle.fluid.initializer.NumpyArrayInitializer.__init__ (ArgSpec(args=['self', 'value'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.layers.fc (ArgSpec(args=['input', 'size', 'num_flatten_dims', 'param_attr', 'bias_attr', 'act', 'is_test', 'name'], varargs=None, keywords=None, defaults=(1, None, None, None, False, None)), ('document', '424e898365195e3ccbc2e7dc8b63605e'))
 paddle.fluid.layers.embedding (ArgSpec(args=['input', 'size', 'is_sparse', 'is_distributed', 'padding_idx', 'param_attr', 'dtype'], varargs=None, keywords=None, defaults=(False, False, None, None, 'float32')), ('document', '6f9f96d2a1517cd1affebc960c3526f7'))
-paddle.fluid.layers.dynamic_lstm (ArgSpec(args=['input', 'size', 'h_0', 'c_0', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'float32', None)), ('document', '8e35ca26adbe44eb631d71045c8d64d5'))
-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', 'b4b608b986eb9617aa0525e1be21d32d'))
+paddle.fluid.layers.dynamic_lstm (ArgSpec(args=['input', 'size', 'h_0', 'c_0', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'float32', None)), ('document', '246ff18abc877dd576653006991918e9'))
+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', '4f63053354bcc6c743b4d2f4e7104e25'))
 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'], varargs=None, keywords=None, defaults=(None,)), ('document', '34f96be41684b0959897a9e735997e20'))
@@ -118,7 +118,7 @@ paddle.fluid.layers.dropout (ArgSpec(args=['x', 'dropout_prob', 'is_test', 'seed
 paddle.fluid.layers.split (ArgSpec(args=['input', 'num_or_sections', 'dim', 'name'], varargs=None, keywords=None, defaults=(-1, None)), ('document', '59b28903ce8fb6a7e3861ff355592eb4'))
 paddle.fluid.layers.ctc_greedy_decoder (ArgSpec(args=['input', 'blank', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '2bc3a59efa9d52b628a6255422d9f0e8'))
 paddle.fluid.layers.edit_distance (ArgSpec(args=['input', 'label', 'normalized', 'ignored_tokens'], varargs=None, keywords=None, defaults=(True, None)), ('document', 'f2c252aa2f83f8e503ffaf79668eaa28'))
-paddle.fluid.layers.l2_normalize (ArgSpec(args=['x', 'axis', 'epsilon', 'name'], varargs=None, keywords=None, defaults=(1e-12, None)), ('document', '35c6a241bcc1a1fc89508860d82ad62b'))
+paddle.fluid.layers.l2_normalize (ArgSpec(args=['x', 'axis', 'epsilon', 'name'], varargs=None, keywords=None, defaults=(1e-12, None)), ('document', 'd0484a1f85b40009a794d45a1a298c12'))
 paddle.fluid.layers.matmul (ArgSpec(args=['x', 'y', 'transpose_x', 'transpose_y', 'alpha', 'name'], varargs=None, keywords=None, defaults=(False, False, 1.0, None)), ('document', 'aa27ca4405e70c6a733cb9806a76af30'))
 paddle.fluid.layers.topk (ArgSpec(args=['input', 'k', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '2a1e9ea041ff4d6a9948bb8d03b743ea'))
 paddle.fluid.layers.warpctc (ArgSpec(args=['input', 'label', 'blank', 'norm_by_times', 'use_cudnn'], varargs=None, keywords=None, defaults=(0, False, False)), ('document', '4aa9df890b47eb67d5442f04aaf9eeec'))
@@ -195,7 +195,7 @@ paddle.fluid.layers.elementwise_floordiv (ArgSpec(args=['x', 'y', 'axis', 'act',
 paddle.fluid.layers.uniform_random_batch_size_like (ArgSpec(args=['input', 'shape', 'dtype', 'input_dim_idx', 'output_dim_idx', 'min', 'max', 'seed'], varargs=None, keywords=None, defaults=('float32', 0, 0, -1.0, 1.0, 0)), ('document', 'c8c7518358cfbb3822a019e6b5fbea52'))
 paddle.fluid.layers.gaussian_random (ArgSpec(args=['shape', 'mean', 'std', 'seed', 'dtype'], varargs=None, keywords=None, defaults=(0.0, 1.0, 0, 'float32')), ('document', '8c78ccb77e291e4a0f0673d34823ce4b'))
 paddle.fluid.layers.sampling_id (ArgSpec(args=['x', 'min', 'max', 'seed', 'dtype'], varargs=None, keywords=None, defaults=(0.0, 1.0, 0, 'float32')), ('document', '35428949368cad5121dd37f8522ef8b0'))
-paddle.fluid.layers.gaussian_random_batch_size_like (ArgSpec(args=['input', 'shape', 'input_dim_idx', 'output_dim_idx', 'mean', 'std', 'seed', 'dtype'], varargs=None, keywords=None, defaults=(0, 0, 0.0, 1.0, 0, 'float32')), ('document', '9e520987168f8ddb7dd71ffd68aa352c'))
+paddle.fluid.layers.gaussian_random_batch_size_like (ArgSpec(args=['input', 'shape', 'input_dim_idx', 'output_dim_idx', 'mean', 'std', 'seed', 'dtype'], varargs=None, keywords=None, defaults=(0, 0, 0.0, 1.0, 0, 'float32')), ('document', '7536418f4cf0360a1a897c265f06e77e'))
 paddle.fluid.layers.sum (ArgSpec(args=['x'], varargs=None, keywords=None, defaults=None), ('document', '4527fd90e222f67b5f7451fb0cf7c845'))
 paddle.fluid.layers.slice (ArgSpec(args=['input', 'axes', 'starts', 'ends'], varargs=None, keywords=None, defaults=None), ('document', '3ca6a761570d86e303e473afba99bb49'))
 paddle.fluid.layers.shape (ArgSpec(args=['input'], varargs=None, keywords=None, defaults=None), ('document', 'bf61c8f79d795a8371bdb3b5468aa82b'))
@@ -339,18 +339,17 @@ paddle.fluid.layers.uniform_random (ArgSpec(args=['shape', 'dtype', 'min', 'max'
 paddle.fluid.layers.hard_shrink (ArgSpec(args=['x', 'threshold'], varargs=None, keywords=None, defaults=(None,)), ('document', 'c142f5884f3255e0d6075c286bbd531e'))
 paddle.fluid.layers.cumsum (ArgSpec(args=['x', 'axis', 'exclusive', 'reverse'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', '944d7c03057f5fc88bc78acd4d82f926'))
 paddle.fluid.layers.thresholded_relu (ArgSpec(args=['x', 'threshold'], varargs=None, keywords=None, defaults=(None,)), ('document', '90566ea449ea4c681435546e2f70610a'))
-paddle.fluid.layers.prior_box (ArgSpec(args=['input', 'image', 'min_sizes', 'max_sizes', 'aspect_ratios', 'variance', 'flip', 'clip', 'steps', 'offset', 'name', 'min_max_aspect_ratios_order'], varargs=None, keywords=None, defaults=(None, [1.0], [0.1, 0.1, 0.2, 0.2], False, False, [0.0, 0.0], 0.5, None, False)), ('document', 'a00d43a08ec664454e8e685bc54e9e78'))
-paddle.fluid.layers.density_prior_box (ArgSpec(args=['input', 'image', 'densities', 'fixed_sizes', 'fixed_ratios', 'variance', 'clip', 'steps', 'offset', 'flatten_to_2d', 'name'], varargs=None, keywords=None, defaults=(None, None, None, [0.1, 0.1, 0.2, 0.2], False, [0.0, 0.0], 0.5, False, None)), ('document', '7e62e12ce8b127f2c7ce8db79299c3c3'))
+paddle.fluid.layers.prior_box (ArgSpec(args=['input', 'image', 'min_sizes', 'max_sizes', 'aspect_ratios', 'variance', 'flip', 'clip', 'steps', 'offset', 'name', 'min_max_aspect_ratios_order'], varargs=None, keywords=None, defaults=(None, [1.0], [0.1, 0.1, 0.2, 0.2], False, False, [0.0, 0.0], 0.5, None, False)), ('document', 'b351a05b758f7e5370898cc7d7d40dca'))
+paddle.fluid.layers.density_prior_box (ArgSpec(args=['input', 'image', 'densities', 'fixed_sizes', 'fixed_ratios', 'variance', 'clip', 'steps', 'offset', 'flatten_to_2d', 'name'], varargs=None, keywords=None, defaults=(None, None, None, [0.1, 0.1, 0.2, 0.2], False, [0.0, 0.0], 0.5, False, None)), ('document', '05c43e8fd25efe34f75e35a2c045ded3'))
 paddle.fluid.layers.multi_box_head (ArgSpec(args=['inputs', 'image', 'base_size', 'num_classes', 'aspect_ratios', 'min_ratio', 'max_ratio', 'min_sizes', 'max_sizes', 'steps', 'step_w', 'step_h', 'offset', 'variance', 'flip', 'clip', 'kernel_size', 'pad', 'stride', 'name', 'min_max_aspect_ratios_order'], varargs=None, keywords=None, defaults=(None, None, None, None, None, None, None, 0.5, [0.1, 0.1, 0.2, 0.2], True, False, 1, 0, 1, None, False)), ('document', 'fd58078fdfffd899b91f992ba224628f'))
 paddle.fluid.layers.bipartite_match (ArgSpec(args=['dist_matrix', 'match_type', 'dist_threshold', 'name'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', '3ddb9b966f193900193a95a3df77c3c1'))
 paddle.fluid.layers.target_assign (ArgSpec(args=['input', 'matched_indices', 'negative_indices', 'mismatch_value', 'name'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', 'e9685f32d21bec8c013626c0254502c5'))
 paddle.fluid.layers.detection_output (ArgSpec(args=['loc', 'scores', 'prior_box', 'prior_box_var', 'background_label', 'nms_threshold', 'nms_top_k', 'keep_top_k', 'score_threshold', 'nms_eta'], varargs=None, keywords=None, defaults=(0, 0.3, 400, 200, 0.01, 1.0)), ('document', 'efae414c1137c7944d6174dd08c5347a'))
-paddle.fluid.layers.ssd_loss (ArgSpec(args=['location', 'confidence', 'gt_box', 'gt_label', 'prior_box', 'prior_box_var', 'background_label', 'overlap_threshold', 'neg_pos_ratio', 'neg_overlap', 'loc_loss_weight', 'conf_loss_weight', 'match_type', 'mining_type', 'normalize', 'sample_size'], varargs=None, keywords=None, defaults=(None, 0, 0.5, 3.0, 0.5, 1.0, 1.0, 'per_prediction', 'max_negative', True, None)), ('document', '6d5028fd09d01ab82d296adc0ea95aee'))
-paddle.fluid.layers.detection_map (ArgSpec(args=['detect_res', 'label', 'class_num', 'background_label', 'overlap_threshold', 'evaluate_difficult', 'has_state', 'input_states', 'out_states', 'ap_version'], varargs=None, keywords=None, defaults=(0, 0.3, True, None, None, None, 'integral')), ('document', '1467d91b50c22cd52103b4aa1ee9d0a1'))
-paddle.fluid.layers.rpn_target_assign (ArgSpec(args=['bbox_pred', 'cls_logits', 'anchor_box', 'anchor_var', 'gt_boxes', 'is_crowd', 'im_info', 'rpn_batch_size_per_im', 'rpn_straddle_thresh', 'rpn_fg_fraction', 'rpn_positive_overlap', 'rpn_negative_overlap', 'use_random'], varargs=None, keywords=None, defaults=(256, 0.0, 0.5, 0.7, 0.3, True)), ('document', '1e164a56fe9376e18a56d22563d9f801'))
+paddle.fluid.layers.ssd_loss (ArgSpec(args=['location', 'confidence', 'gt_box', 'gt_label', 'prior_box', 'prior_box_var', 'background_label', 'overlap_threshold', 'neg_pos_ratio', 'neg_overlap', 'loc_loss_weight', 'conf_loss_weight', 'match_type', 'mining_type', 'normalize', 'sample_size'], varargs=None, keywords=None, defaults=(None, 0, 0.5, 3.0, 0.5, 1.0, 1.0, 'per_prediction', 'max_negative', True, None)), ('document', '055bd5070ad72dccc0949b4ed036f39c'))
+paddle.fluid.layers.rpn_target_assign (ArgSpec(args=['bbox_pred', 'cls_logits', 'anchor_box', 'anchor_var', 'gt_boxes', 'is_crowd', 'im_info', 'rpn_batch_size_per_im', 'rpn_straddle_thresh', 'rpn_fg_fraction', 'rpn_positive_overlap', 'rpn_negative_overlap', 'use_random'], varargs=None, keywords=None, defaults=(256, 0.0, 0.5, 0.7, 0.3, True)), ('document', '70d0109c864bced99b6b0aca4574af5e'))
 paddle.fluid.layers.retinanet_target_assign (ArgSpec(args=['bbox_pred', 'cls_logits', 'anchor_box', 'anchor_var', 'gt_boxes', 'gt_labels', 'is_crowd', 'im_info', 'num_classes', 'positive_overlap', 'negative_overlap'], varargs=None, keywords=None, defaults=(1, 0.5, 0.4)), ('document', 'fa1d1c9d5e0111684c0db705f86a2595'))
 paddle.fluid.layers.sigmoid_focal_loss (ArgSpec(args=['x', 'label', 'fg_num', 'gamma', 'alpha'], varargs=None, keywords=None, defaults=(2, 0.25)), ('document', 'aeac6aae100173b3fc7f102cf3023a3d'))
-paddle.fluid.layers.anchor_generator (ArgSpec(args=['input', 'anchor_sizes', 'aspect_ratios', 'variance', 'stride', 'offset', 'name'], varargs=None, keywords=None, defaults=(None, None, [0.1, 0.1, 0.2, 0.2], None, 0.5, None)), ('document', '82b2aefeeb1b706bc4afec70928a259a'))
+paddle.fluid.layers.anchor_generator (ArgSpec(args=['input', 'anchor_sizes', 'aspect_ratios', 'variance', 'stride', 'offset', 'name'], varargs=None, keywords=None, defaults=(None, None, [0.1, 0.1, 0.2, 0.2], None, 0.5, None)), ('document', 'acc23232f4c8c03791598500b5bf7790'))
 paddle.fluid.layers.roi_perspective_transform (ArgSpec(args=['input', 'rois', 'transformed_height', 'transformed_width', 'spatial_scale'], varargs=None, keywords=None, defaults=(1.0,)), ('document', 'd1ddc75629fedee46f82e631e22c79dc'))
 paddle.fluid.layers.generate_proposal_labels (ArgSpec(args=['rpn_rois', 'gt_classes', 'is_crowd', 'gt_boxes', 'im_info', 'batch_size_per_im', 'fg_fraction', 'fg_thresh', 'bg_thresh_hi', 'bg_thresh_lo', 'bbox_reg_weights', 'class_nums', 'use_random', 'is_cls_agnostic', 'is_cascade_rcnn'], varargs=None, keywords=None, defaults=(256, 0.25, 0.25, 0.5, 0.0, [0.1, 0.1, 0.2, 0.2], None, True, False, False)), ('document', 'e87c1131e98715d3657a96c44db1b910'))
 paddle.fluid.layers.generate_proposals (ArgSpec(args=['scores', 'bbox_deltas', 'im_info', 'anchors', 'variances', 'pre_nms_top_n', 'post_nms_top_n', 'nms_thresh', 'min_size', 'eta', 'name'], varargs=None, keywords=None, defaults=(6000, 1000, 0.5, 0.1, 1.0, None)), ('document', 'b7d707822b6af2a586bce608040235b1'))

paddle/fluid/inference/api/demo_ci/run.sh

@@ -4,7 +4,7 @@ PADDLE_ROOT=$1
 TURN_ON_MKL=$2 # use MKL or Openblas
 TEST_GPU_CPU=$3 # test both GPU/CPU mode or only CPU mode
 DATA_DIR=$4 # dataset
-TENSORRT_INCLUDE_DIR=$5 # TensorRT header file dir, defalut to /usr/local/TensorRT/include
+TENSORRT_INCLUDE_DIR=$5 # TensorRT header file dir, default to /usr/local/TensorRT/include
 TENSORRT_LIB_DIR=$6 # TensorRT lib file dir, default to /usr/local/TensorRT/lib
 inference_install_dir=${PADDLE_ROOT}/build/fluid_inference_install_dir
 

paddle/fluid/operators/attention_lstm_op.cc

@@ -207,7 +207,7 @@ void AttentionLSTMOpMaker::Make() {
       .InEnum({"sigmoid", "tanh", "relu", "identity"});
   AddAttr<std::string>("cell_activation",
                        "(string, default: tanh)"
-                       "The activation for cell output, `tanh` by defalut.")
+                       "The activation for cell output, `tanh` by default.")
       .SetDefault("tanh")
       .InEnum({"sigmoid", "tanh", "relu", "identity"});
   AddAttr<std::string>("candidate_activation",

paddle/fluid/operators/batch_norm_op.cu

@@ -31,7 +31,7 @@ limitations under the License. */
 // input data range.
 DEFINE_bool(cudnn_batchnorm_spatial_persistent, false,
             "Whether enable CUDNN_BATCHNORM_SPATIAL_PERSISTENT mode for cudnn "
-            "batch_norm, defalut is False.");
+            "batch_norm, default is False.");
 
 namespace paddle {
 namespace operators {

paddle/fluid/operators/conv_cudnn_op.cu.cc

@@ -33,7 +33,7 @@ DEFINE_uint64(conv_workspace_size_limit,
               "cuDNN convolution workspace limit in MB unit.");
 DEFINE_bool(cudnn_exhaustive_search, false,
             "Whether enable exhaustive search for cuDNN convolution or "
-            "not, defalut is False.");
+            "not, default is False.");
 
 namespace paddle {
 namespace operators {
@@ -102,7 +102,7 @@ class CUDNNConvOpKernel : public framework::OpKernel<T> {
         conv_desc.descriptor<T>(paddings, strides, dilations);
 
 #if CUDNN_VERSION_MIN(7, 0, 1)
-    // cudnn 7 can support groups, no need to do it mannually
+    // cudnn 7 can support groups, no need to do it manually
     // FIXME(typhoonzero): find a better way to disable groups
     // rather than setting it to 1.
     CUDNN_ENFORCE(platform::dynload::cudnnSetConvolutionGroupCount(
@@ -300,7 +300,7 @@ class CUDNNConvGradOpKernel : public framework::OpKernel<T> {
         FLAGS_cudnn_exhaustive_search || ctx.Attr<bool>("exhaustive_search");
     if (exhaustive_search && FLAGS_cudnn_deterministic) {
       PADDLE_THROW(
-          "Cann't set exhaustive_search True and "
+          "Can't set exhaustive_search True and "
           "FLAGS_cudnn_deterministic True at same time.");
     }
 
@@ -320,7 +320,7 @@ class CUDNNConvGradOpKernel : public framework::OpKernel<T> {
         conv_desc.descriptor<T>(paddings, strides, dilations);
 
 #if CUDNN_VERSION_MIN(7, 0, 1)
-    // cudnn 7 can support groups, no need to do it mannually
+    // cudnn 7 can support groups, no need to do it manually
     // FIXME(typhoonzero): find a better way to disable groups
     // rather than setting it to 1.
     CUDNN_ENFORCE(platform::dynload::cudnnSetConvolutionGroupCount(
@@ -665,7 +665,7 @@ class CUDNNConvDoubleGradOpKernel : public framework::OpKernel<T> {
     bool deterministic = FLAGS_cudnn_deterministic;
     if (exhaustive_search && deterministic) {
       PADDLE_THROW(
-          "Cann't set exhaustive_search True and "
+          "Can't set exhaustive_search True and "
           "FLAGS_cudnn_deterministic True at same time.");
     }
 

paddle/fluid/operators/conv_fusion_op.cu.cc

@@ -18,7 +18,7 @@ limitations under the License. */
 
 DEFINE_int64(cudnn_exhaustive_search_times, -1,
              "Exhaustive search times for cuDNN convolution, "
-             "defalut is -1, not exhaustive search");
+             "default is -1, not exhaustive search");
 
 namespace paddle {
 namespace operators {

paddle/fluid/operators/conv_op.cc

@@ -259,7 +259,7 @@ void Conv2DOpMaker::Make() {
   AddAttr<bool>("exhaustive_search",
                 "(bool, default false) cuDNN has many algorithm to calculation "
                 "convolution, whether enable exhaustive search "
-                "for cuDNN convolution or not, defalut is False.")
+                "for cuDNN convolution or not, default is False.")
       .SetDefault(false);
   AddComment(R"DOC(
 Convolution Operator.
@@ -378,7 +378,7 @@ void Conv3DOpMaker::Make() {
   AddAttr<bool>("exhaustive_search",
                 "(bool, default false) cuDNN has many algorithm to calculation "
                 "convolution, whether enable exhaustive search "
-                "for cuDNN convolution or not, defalut is False.")
+                "for cuDNN convolution or not, default is False.")
       .SetDefault(false);
   AddComment(R"DOC(
 Convolution3D Operator.

paddle/fluid/operators/detection/bipartite_match_op.cc

@@ -231,14 +231,14 @@ class BipartiteMatchOpMaker : public framework::OpProtoAndCheckerMaker {
         "entities.");
     AddAttr<std::string>(
         "match_type",
-        "(string, defalut: per_prediction) "
+        "(string, default: per_prediction) "
         "The type of matching method, should be 'bipartite' or "
-        "'per_prediction', 'bipartite' by defalut.")
+        "'per_prediction', 'bipartite' by default.")
         .SetDefault("bipartite")
         .InEnum({"bipartite", "per_prediction"});
     AddAttr<float>(
         "dist_threshold",
-        "(float, defalut: 0.5) "
+        "(float, default: 0.5) "
         "If `match_type` is 'per_prediction', this threshold is to determine "
         "the extra matching bboxes based on the maximum distance.")
         .SetDefault(0.5);

paddle/fluid/operators/detection/multiclass_nms_op.cc

@@ -463,7 +463,7 @@ class MultiClassNMSOpMaker : public framework::OpProtoAndCheckerMaker {
              "Input BBoxes should be the second case with shape [M, C, 4].");
     AddAttr<int>(
         "background_label",
-        "(int, defalut: 0) "
+        "(int, default: 0) "
         "The index of background label, the background label will be ignored. "
         "If set to -1, then all categories will be considered.")
         .SetDefault(0);
@@ -477,7 +477,7 @@ class MultiClassNMSOpMaker : public framework::OpProtoAndCheckerMaker {
                  "confidences aftern the filtering detections based on "
                  "score_threshold");
     AddAttr<float>("nms_threshold",
-                   "(float, defalut: 0.3) "
+                   "(float, default: 0.3) "
                    "The threshold to be used in NMS.")
         .SetDefault(0.3);
     AddAttr<float>("nms_eta",

paddle/fluid/operators/detection_map_op.cc

@@ -150,7 +150,7 @@ class DetectionMAPOpMaker : public framework::OpProtoAndCheckerMaker {
                  "The class number.");
     AddAttr<int>(
         "background_label",
-        "(int, defalut: 0) "
+        "(int, default: 0) "
         "The index of background label, the background label will be ignored. "
         "If set to -1, then all categories will be considered.")
         .SetDefault(0);

paddle/fluid/operators/fused/fused_embedding_fc_lstm_op.cc

@@ -174,15 +174,15 @@ void FusedEmbeddingFCLSTMOpMaker::Make() {
   AddOutput("ReorderedH0", "(LoDTensor) (N x D).").AsIntermediate();
   AddOutput("ReorderedC0", "(LoDTensor) (N x D).").AsIntermediate();
   AddAttr<bool>("use_peepholes",
-                "(bool, defalut: True) "
+                "(bool, default: True) "
                 "whether to enable diagonal/peephole connections.")
       .SetDefault(true);
   AddAttr<bool>("is_reverse",
-                "(bool, defalut: False) "
+                "(bool, default: False) "
                 "whether to compute reversed LSTM.")
       .SetDefault(false);
   AddAttr<bool>("use_seq",
-                "(bool, defalut: True) "
+                "(bool, default: True) "
                 "whether to use seq mode to compute.")
       .SetDefault(true);
   AddAttr<std::string>("gate_activation",
@@ -193,7 +193,7 @@ void FusedEmbeddingFCLSTMOpMaker::Make() {
       .InEnum({"sigmoid", "tanh", "relu", "identity"});
   AddAttr<std::string>("cell_activation",
                        "(string, default: tanh)"
-                       "The activation for cell output, `tanh` by defalut.")
+                       "The activation for cell output, `tanh` by default.")
       .SetDefault("tanh")
       .InEnum({"sigmoid", "tanh", "relu", "identity"});
   AddAttr<std::string>("candidate_activation",

paddle/fluid/operators/fused/fusion_conv_inception_op.cc

@@ -67,7 +67,7 @@ class ConvInceptionFusionOpMaker : public framework::OpProtoAndCheckerMaker {
   void Make() override {
     AddInput("Input", "(Tensor) NCHW layout.");
     AddInput("Filter", "(vector<Tensor>) 4 aggregated filters").AsDuplicable();
-    AddInput("Bias", "(vector<Tensor>) it's lenght is equal to Filter")
+    AddInput("Bias", "(vector<Tensor>) it's length is equal to Filter")
         .AsDuplicable();
     AddOutput("Output",
               "(Tensor) The output tensor of convolution operator. "
@@ -82,7 +82,7 @@ class ConvInceptionFusionOpMaker : public framework::OpProtoAndCheckerMaker {
         "exclusive",
         "(bool, default True) 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 defalut is True.")
+        "is only used when pooling_type is avg. The default is True.")
         .SetDefault(true);
     AddAttr<std::string>(
         "activation",

paddle/fluid/operators/fused/fusion_gru_op.cc

@@ -147,11 +147,11 @@ void FusionGRUOpMaker::Make() {
       "The activation type used in update gate and reset gate.")
       .SetDefault("sigmoid");
   AddAttr<bool>("is_reverse",
-                "(bool, defalut: False) "
+                "(bool, default: False) "
                 "whether to compute reversed GRU.")
       .SetDefault(false);
   AddAttr<bool>("use_seq",
-                "(bool, defalut: True) "
+                "(bool, default: True) "
                 "whether to use seq mode to compute GRU.")
       .SetDefault(true);
   AddComment(R"DOC(

paddle/fluid/operators/fused/fusion_lstm_op.cc

@@ -179,15 +179,15 @@ void FusionLSTMOpMaker::Make() {
   AddOutput("CheckedCell", "(Tensor) (2 x D) only for peephole.")
       .AsIntermediate();
   AddAttr<bool>("use_peepholes",
-                "(bool, defalut: True) "
+                "(bool, default: True) "
                 "whether to enable diagonal/peephole connections.")
       .SetDefault(true);
   AddAttr<bool>("is_reverse",
-                "(bool, defalut: False) "
+                "(bool, default: False) "
                 "whether to compute reversed LSTM.")
       .SetDefault(false);
   AddAttr<bool>("use_seq",
-                "(bool, defalut: True) "
+                "(bool, default: True) "
                 "whether to use seq mode to compute.")
       .SetDefault(true);
   AddAttr<std::string>("gate_activation",
@@ -198,7 +198,7 @@ void FusionLSTMOpMaker::Make() {
       .InEnum({"sigmoid", "tanh", "relu", "identity"});
   AddAttr<std::string>("cell_activation",
                        "(string, default: tanh)"
-                       "The activation for cell output, `tanh` by defalut.")
+                       "The activation for cell output, `tanh` by default.")
       .SetDefault("tanh")
       .InEnum({"sigmoid", "tanh", "relu", "identity"});
   AddAttr<std::string>("candidate_activation",

paddle/fluid/operators/gaussian_random_batch_size_like_op.cc

@@ -58,7 +58,7 @@ class GaussianRandomBatchSizeLikeOpMaker : public BatchSizeLikeOpMaker {
     AddComment(R"DOC(
 
 Used to initialize tensors with gaussian random generator.
-The defalut mean of the distribution is 0. and defalut standard
+The default mean of the distribution is 0. and default standard
 deviation (std) of the distribution is 1.. Uers can set mean and std
 by input arguments.
 )DOC");

paddle/fluid/operators/gru_op.cc

@@ -137,7 +137,7 @@ class GRUOpMaker : public framework::OpProtoAndCheckerMaker {
         "The activation type used in update gate and reset gate.")
         .SetDefault("sigmoid");
     AddAttr<bool>("is_reverse",
-                  "(bool, defalut: False) "
+                  "(bool, default: False) "
                   "whether to compute reversed GRU.")
         .SetDefault(false);
     AddAttr<bool>("origin_mode",

paddle/fluid/operators/lstm_op.cc

@@ -153,11 +153,11 @@ class LSTMOpMaker : public framework::OpProtoAndCheckerMaker {
               "in the backward.")
         .AsIntermediate();
     AddAttr<bool>("use_peepholes",
-                  "(bool, defalut: True) "
+                  "(bool, default: True) "
                   "whether to enable diagonal/peephole connections.")
         .SetDefault(true);
     AddAttr<bool>("is_reverse",
-                  "(bool, defalut: False) "
+                  "(bool, default: False) "
                   "whether to compute reversed LSTM.")
         .SetDefault(false);
     AddAttr<std::string>(
@@ -169,7 +169,7 @@ class LSTMOpMaker : public framework::OpProtoAndCheckerMaker {
         .InEnum({"sigmoid", "tanh", "relu", "identity"});
     AddAttr<std::string>("cell_activation",
                          "(string, default: tanh)"
-                         "The activation for cell output, `tanh` by defalut.")
+                         "The activation for cell output, `tanh` by default.")
         .SetDefault("tanh")
         .InEnum({"sigmoid", "tanh", "relu", "identity"});
     AddAttr<std::string>("candidate_activation",
@@ -181,7 +181,7 @@ class LSTMOpMaker : public framework::OpProtoAndCheckerMaker {
     AddComment(R"DOC(
 Long-Short Term Memory (LSTM) Operator.
 
-The defalut implementation is diagonal/peephole connection
+The default implementation is diagonal/peephole connection
 (https://arxiv.org/pdf/1402.1128.pdf), the formula is as follows:
 
 $$ i_t = \\sigma(W_{ix}x_{t} + W_{ih}h_{t-1} + W_{ic}c_{t-1} + b_i) $$
@@ -199,7 +199,7 @@ $$ h_t = o_t \\odot act_h(c_t) $$
 - W terms denote weight matrices (e.g. $W_{xi}$ is the matrix
   of weights from the input gate to the input), $W_{ic}, W_{fc}, W_{oc}$
   are diagonal weight matrices for peephole connections. In our implementation,
-  we use vectors to reprenset these diagonal weight matrices.
+  we use vectors to represent these diagonal weight matrices.
 - The b terms denote bias vectors ($b_i$ is the input gate bias vector).
 - $\sigma$ is the non-line activations, such as logistic sigmoid function.
 - $i, f, o$ and $c$ are the input gate, forget gate, output gate,

paddle/fluid/operators/lstmp_op.cc

@@ -177,20 +177,20 @@ class LSTMPOpMaker : public framework::OpProtoAndCheckerMaker {
               "backward.")
         .AsIntermediate();
     AddAttr<bool>("use_peepholes",
-                  "(bool, defalut: True) "
+                  "(bool, default: True) "
                   "whether to enable diagonal/peephole connections.")
         .SetDefault(true);
     AddAttr<bool>("is_reverse",
-                  "(bool, defalut: False) "
+                  "(bool, default: False) "
                   "whether to compute reversed LSTMP.")
         .SetDefault(false);
     AddAttr<float>("cell_clip",
-                   "(float, defalut: 0.0) "
+                   "(float, default: 0.0) "
                    "Clip for Tensor for cell state tensor when clip value is "
                    "greater than 0.0")
         .SetDefault(0.0);
     AddAttr<float>("proj_clip",
-                   "(float, defalut: 0.0) "
+                   "(float, default: 0.0) "
                    "Clip for Tensor for projection tensor when clip value is "
                    "greater than 0.0")
         .SetDefault(0.0);
@@ -203,7 +203,7 @@ class LSTMPOpMaker : public framework::OpProtoAndCheckerMaker {
         .InEnum({"sigmoid", "tanh", "relu", "identity"});
     AddAttr<std::string>("cell_activation",
                          "(string, default: tanh)"
-                         "The activation for cell output, `tanh` by defalut.")
+                         "The activation for cell output, `tanh` by default.")
         .SetDefault("tanh")
         .InEnum({"sigmoid", "tanh", "relu", "identity"});
     AddAttr<std::string>("candidate_activation",
@@ -215,7 +215,7 @@ class LSTMPOpMaker : public framework::OpProtoAndCheckerMaker {
     AddAttr<std::string>("proj_activation",
                          "(string, default: tanh)"
                          "The activation for projection output, "
-                         "`tanh` by defalut.")
+                         "`tanh` by default.")
         .SetDefault("tanh")
         .InEnum({"sigmoid", "tanh", "relu", "identity"});
     AddComment(R"DOC(
@@ -248,7 +248,7 @@ $$
 where the W terms denote weight matrices (e.g. $W_{xi}$ is the matrix
 of weights from the input gate to the input), $W_{ic}, W_{fc}, W_{oc}$
 are diagonal weight matrices for peephole connections. In our implementation,
-we use vectors to reprenset these diagonal weight matrices. The b terms
+we use vectors to represent these diagonal weight matrices. The b terms
 denote bias vectors ($b_i$ is the input gate bias vector), $\sigma$
 is the activation, such as logistic sigmoid function, and
 $i, f, o$ and $c$ are the input gate, forget gate, output gate,

paddle/fluid/operators/pool_op.cc

@@ -190,7 +190,7 @@ void Pool2dOpMaker::Make() {
       "exclusive",
       "(bool, default True) 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 defalut is True.")
+      "is only used when pooling_type is avg. The default is True.")
       .SetDefault(true);
   AddAttr<bool>(
       "adaptive",
@@ -360,7 +360,7 @@ void Pool3dOpMaker::Make() {
       "exclusive",
       "(bool, default True) 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 defalut is True.")
+      "is only used when pooling_type is avg. The default is True.")
       .SetDefault(true);
   AddAttr<bool>(
       "adaptive",

paddle/fluid/operators/unpool_op.cc

@@ -46,7 +46,7 @@ class Unpool2dOpMaker : public framework::OpProtoAndCheckerMaker {
                               "strides (height, width) of unpooling operator.")
         .SetDefault({1, 1});
     AddAttr<std::vector<int>>("paddings",
-                              "(vector defalut:{0,0}), "
+                              "(vector default:{0,0}), "
                               "paddings (height, width) of unpooling operator.")
         .SetDefault({0, 0});
     AddAttr<std::string>(

python/paddle/fluid/contrib/slim/quantization/quantization_strategy.py

@@ -53,11 +53,11 @@ class QuantizationStrategy(Strategy):
             start_epoch(int): The 'on_epoch_begin' function will be called in start_epoch. default: 0
             end_epoch(int): The 'on_epoch_end' function will be called in end_epoch. default: 0
             float_model_save_path(str): The path to save model with float weights.
-                            None means it doesn't save float model. defalut: None.
+                            None means it doesn't save float model. default: None.
             mobile_model_save_path(str): The path to save model for paddle-mobile execution.
-                            None means it doesn't save mobile model. defalut: None.
+                            None means it doesn't save mobile model. default: None.
             int8_model_save_path(str): The path to save model with int8_t weight.
-                            None means it doesn't save int8 model. defalut: None.
+                            None means it doesn't save int8 model. default: None.
             activation_bits(int): quantization bit number for activation. default: 8.
             weight_bits(int): quantization bit number for weights. The bias is not quantized.
                               default: 8.
@@ -90,7 +90,7 @@ class QuantizationStrategy(Strategy):
 
     def restore_from_checkpoint(self, context):
         """
-        Restore graph when the compressoin task is inited from checkpoint.
+        Restore graph when the compression task is inited from checkpoint.
         """
         # It is inited from checkpoint and has missed start epoch.
         if context.epoch_id != 0 and context.epoch_id > self.start_epoch:
@@ -100,7 +100,7 @@ class QuantizationStrategy(Strategy):
 
     def _modify_graph_for_quantization(self, context):
         """
-        Insert fake_quantize_op and fake_dequantize_op before trainging and testing.
+        Insert fake_quantize_op and fake_dequantize_op before training and testing.
         """
         train_ir_graph = IrGraph(
             core.Graph(context.optimize_graph.program.clone().desc),
@@ -151,7 +151,7 @@ class QuantizationStrategy(Strategy):
 
     def on_epoch_begin(self, context):
         """
-        Insert fake_quantize_op and fake_dequantize_op before trainging and testing.
+        Insert fake_quantize_op and fake_dequantize_op before training and testing.
         """
         super(QuantizationStrategy, self).on_epoch_begin(context)
         if self.start_epoch == context.epoch_id:

python/paddle/fluid/contrib/slim/tests/quantization/compress.yaml

 #start_epoch(int): The epoch to insert quantization operators. default: 0
 #
-#end_epoch(int): The epoch to save inferecne model. default: 0
+#end_epoch(int): The epoch to save inference model. default: 0
 #
 #float_model_save_path(str): The path to save model with float weights.
-#                None means it doesn't save float model. defalut: None.
+#                None means it doesn't save float model. default: None.
 #
 #mobile_model_save_path(str): The path to save model for paddle-mobile execution.
-#                None means it doesn't save mobile model. defalut: None.
+#                None means it doesn't save mobile model. default: None.
 #
 #int8_model_save_path(str): The path to save model with int8_t weight.
-#                None means it doesn't save int8 model. defalut: None.
+#                None means it doesn't save int8 model. default: None.
 #
 #activation_bits(int): quantization bit number for activation. default: 8.
 #

python/paddle/fluid/evaluator.py

@@ -323,11 +323,11 @@ class DetectionMAP(Evaluator):
         class_num (int): The class number.
         background_label (int): The index of background label, the background
             label will be ignored. If set to -1, then all categories will be
-            considered, 0 by defalut.
+            considered, 0 by default.
         overlap_threshold (float): The threshold for deciding true/false
-            positive, 0.5 by defalut.
+            positive, 0.5 by default.
         evaluate_difficult (bool): Whether to consider difficult ground truth
-            for evaluation, True by defalut. This argument does not work when
+            for evaluation, True by default. This argument does not work when
             gt_difficult is None.
         ap_version (string): The average precision calculation ways, it must be
             'integral' or '11point'. Please check

python/paddle/fluid/layers/detection.py

@@ -266,7 +266,7 @@ def rpn_target_assign(bbox_pred,
             coordinate of the anchor box.
         anchor_var(Variable): A 2-D Tensor with shape [M,4] holds expanded 
             variances of anchors.
-        gt_boxes (Variable): The ground-truth boudding boxes (bboxes) are a 2D
+        gt_boxes (Variable): The ground-truth bounding boxes (bboxes) are a 2D
             LoDTensor with shape [Ng, 4], Ng is the total number of ground-truth
             bboxes of mini-batch input.
         is_crowd (Variable): A 1-D LoDTensor which indicates groud-truth is crowd.
@@ -1258,8 +1258,8 @@ def ssd_loss(location,
     """
     **Multi-box loss layer for object detection algorithm of SSD**
 
-    This layer is to compute dection loss for SSD given the location offset
-    predictions, confidence predictions, prior boxes and ground-truth boudding
+    This layer is to compute detection loss for SSD given the location offset
+    predictions, confidence predictions, prior boxes and ground-truth bounding
     boxes and labels, and the type of hard example mining. The returned loss
     is a weighted sum of the localization loss (or regression loss) and
     confidence loss (or classification loss) by performing the following steps:
@@ -1303,7 +1303,7 @@ def ssd_loss(location,
         confidence (Variable): The confidence predictions are a 3D Tensor
             with shape [N, Np, C], N and Np are the same as they are in
             `location`, C is the class number.
-        gt_box (Variable): The ground-truth boudding boxes (bboxes) are a 2D
+        gt_box (Variable): The ground-truth bounding boxes (bboxes) are a 2D
             LoDTensor with shape [Ng, 4], Ng is the total number of ground-truth
             bboxes of mini-batch input.
         gt_label (Variable): The ground-truth labels are a 2D LoDTensor
@@ -1316,14 +1316,14 @@ def ssd_loss(location,
             `overlap_threshold` to determine the extra matching bboxes when
              finding matched boxes. 0.5 by default.
         neg_pos_ratio (float): The ratio of the negative boxes to the positive
-            boxes, used only when mining_type is 'max_negative', 3.0 by defalut.
+            boxes, used only when mining_type is 'max_negative', 3.0 by default.
         neg_overlap (float): The negative overlap upper bound for the unmatched
             predictions. Use only when mining_type is 'max_negative',
             0.5 by default.
         loc_loss_weight (float): Weight for localization loss, 1.0 by default.
         conf_loss_weight (float): Weight for confidence loss, 1.0 by default.
         match_type (str): The type of matching method during training, should
-            be 'bipartite' or 'per_prediction', 'per_prediction' by defalut.
+            be 'bipartite' or 'per_prediction', 'per_prediction' by default.
         mining_type (str): The hard example mining type, should be 'hard_example'
             or 'max_negative', now only support `max_negative`.
         normalize (bool): Whether to normalize the SSD loss by the total number
@@ -1507,7 +1507,7 @@ def prior_box(input,
             Default:[0.1, 0.1, 0.2, 0.2].
        flip(bool): Whether to flip aspect ratios. Default:False.
        clip(bool): Whether to clip out-of-boundary boxes. Default: False.
-       step(list|turple): Prior boxes step across width and height, If
+       step(list|tuple): Prior boxes step across width and height, If
             step[0] == 0.0/step[1] == 0.0, the prior boxes step across
             height/weight of the input will be automatically calculated.
             Default: [0., 0.]
@@ -1636,7 +1636,7 @@ def density_prior_box(input,
        variance(list|tuple): the variances to be encoded in density prior boxes.
             Default:[0.1, 0.1, 0.2, 0.2].
        clip(bool): Whether to clip out-of-boundary boxes. Default: False.
-       step(list|turple): Prior boxes step across width and height, If
+       step(list|tuple): Prior boxes step across width and height, If
             step[0] == 0.0/step[1] == 0.0, the density prior boxes step across
             height/weight of the input will be automatically calculated.
             Default: [0., 0.]
@@ -2003,7 +2003,7 @@ def anchor_generator(input,
                                         anchors, e.g. [0.5, 1.0, 2.0].
        variance(list|tuple): The variances to be used in box regression deltas.
                              Default:[0.1, 0.1, 0.2, 0.2].
-       stride(list|turple): The anchors stride across width and height,e.g. [16.0, 16.0]
+       stride(list|tuple): The anchors stride across width and height,e.g. [16.0, 16.0]
        offset(float): Prior boxes center offset. Default: 0.5
        name(str): Name of the prior box op. Default: None.
 

python/paddle/fluid/layers/nn.py

@@ -769,7 +769,7 @@ def dynamic_lstmp(input,
           the matrix of weights from the input gate to the input).
     * :math:`W_{ic}`, :math:`W_{fc}`, :math:`W_{oc}`: Diagonal weight \
           matrices for peephole connections. In our implementation, \
-          we use vectors to reprenset these diagonal weight matrices.
+          we use vectors to represent these diagonal weight matrices.
     * :math:`b`: Denotes bias vectors (e.g. :math:`b_i` is the input gate \
           bias vector).
     * :math:`\sigma`: The activation, such as logistic sigmoid function.
@@ -5067,7 +5067,7 @@ def l2_normalize(x, axis, epsilon=1e-12, name=None):
             the dimension to normalization is rank(X) + axis. -1 is the
             last dimension.
         epsilon(float): The epsilon value is used to avoid division by zero, \
-            the defalut value is 1e-12.
+            the default value is 1e-12.
         name(str|None): A name for this layer(optional). If set None, the layer \
             will be named automatically.
 

python/paddle/fluid/metrics.py

@@ -713,11 +713,11 @@ class DetectionMAP(object):
         class_num (int): The class number.
         background_label (int): The index of background label, the background
             label will be ignored. If set to -1, then all categories will be
-            considered, 0 by defalut.
+            considered, 0 by default.
         overlap_threshold (float): The threshold for deciding true/false
-            positive, 0.5 by defalut.
+            positive, 0.5 by default.
         evaluate_difficult (bool): Whether to consider difficult ground truth
-            for evaluation, True by defalut. This argument does not work when
+            for evaluation, True by default. This argument does not work when
             gt_difficult is None.
         ap_version (string): The average precision calculation ways, it must be
             'integral' or '11point'. Please check

python/paddle/fluid/tests/unittests/dist_transformer.py

@@ -1563,7 +1563,7 @@ def fast_decode(
             } for cache in caches]
             pre_pos = layers.elementwise_mul(
                 x=layers.fill_constant_batch_size_like(
-                    input=pre_enc_output,  # cann't use pre_ids here since it has lod
+                    input=pre_enc_output,  # can't use pre_ids here since it has lod
                     value=1,
                     shape=[-1, 1, 1],
                     dtype=pre_ids.dtype),

python/paddle/fluid/tests/unittests/transformer_model.py

@@ -136,7 +136,7 @@ def multi_head_attention(queries,
         # The current implementation of softmax_op only supports 2D tensor,
         # consequently it cannot be directly used here.
         # If to use the reshape_op, Besides, the shape of product inferred in
-        # compile-time is not the actual shape in run-time. It cann't be used
+        # compile-time is not the actual shape in run-time. It can't be used
         # to set the attribute of reshape_op.
         # So, here define the softmax for temporary solution.