[PolishComments] Polish some code comments (#46032)

* polish code comments

* polish data_device_transform.cc

paddle/fluid/framework/attribute_checker.h

@@ -342,13 +342,12 @@ class OpAttrChecker {
   AttributeMap default_attrs_;
 
   // in order to improve the efficiency of dynamic graph mode,
-  // we divede the attribute into explicit type and implicit type.
+  // we divide the attribute into explicit type and implicit type.
   // for explicit attribute, we mean the attribute added in the customized
   // op makers, usually it's defined in the overloaded Make method.
   // for implicit attribute, we mean the attribute added outside of the Make
   // method like "op_role", "op_role_var", and they are useless in dynamic
-  // graph
-  // mode
+  // graph mode
   size_t explicit_checker_num_;
 };
 

paddle/fluid/framework/custom_operator.cc

@@ -801,7 +801,7 @@ void RegisterOperatorWithMetaInfo(const std::vector<OpMetaInfo>& op_meta_infos,
 
   // Infer Dtype
   if (infer_dtype_func == nullptr) {
-    // use defalut InferDtype
+    // use default InferDtype
     info.infer_var_type_ = [op_inputs, op_outputs](InferVarTypeContext* ctx) {
       PADDLE_ENFORCE_EQ(
           op_inputs.size(),

paddle/fluid/framework/data_device_transform.cc

@@ -51,8 +51,7 @@ void TransDataDevice(const Tensor &in,
   // the elements of learning rate are one and it's CPU side.
   // One solution is to use a CUDA kernel to complete the copy operation when
   // the transforming is from CPU to GPU and the number of elements is little.
-  // But the embarrassment is that this solution this solution makes training
-  // slower.
+  // But the embarrassment is that this solution makes training slower.
   TensorCopySync(in, dst_place, out);
 }
 

paddle/fluid/framework/operator.h

@@ -695,7 +695,7 @@ class OperatorWithKernel : public OperatorBase {
    * Transfer data from scope to a transferred scope. If there is no data need
    * to be transferred, it returns nullptr.
    *
-   * * transfered_inplace_vars is a output vector.
+   * transfered_inplace_vars is a output vector.
    */
   Scope* PrepareData(const Scope& scope,
                      const OpKernelType& expected_kernel_key,

paddle/fluid/imperative/infer_shape_context.h

@@ -169,6 +169,7 @@ class DygraphInferShapeContext : public framework::InferShapeContext {
 
     return vec_res;
   }
+
   std::string GetInputNameByIdx(size_t idx) const override {
     auto& op_proto =
         paddle::framework::OpInfoMap::Instance().Get(op_type_).proto_;

paddle/fluid/operators/fill_any_like_op.cc

@@ -58,7 +58,7 @@ class FillAnyLikeOpMaker : public framework::OpProtoAndCheckerMaker {
     AddOutput("Out", "The variable will be filled up with specified value.");
     AddAttr<float>("value", "The filled value").SetDefault(0.0);
     AddAttr<int>("dtype",
-                 "Output tensor data type. defalut value is -1,"
+                 "Output tensor data type. default value is -1,"
                  "according to the input dtype.")
         .SetDefault(-1);
     AddComment(R"DOC(

paddle/fluid/pybind/cuda_streams_py.cc

@@ -321,7 +321,7 @@ void BindCudaStream(py::module *m_ptr) {
       Parameters:
         enable_timing(bool, optional): Whether the event will measure time. Default: False.
         blocking(bool, optional): Whether the wait() func will be blocking. Default: False;
-        interprocess(bool, optional): Whether the event can be shared between processes. Defalut: False.
+        interprocess(bool, optional): Whether the event can be shared between processes. Default: False.
 
       Examples:
         .. code-block:: python

paddle/phi/api/lib/data_transform.cc

@@ -81,7 +81,7 @@ inline phi::DenseTensor TransDataLayout(const phi::DenseTensor& tensor,
 }
 
 template <typename Context>
-phi::DenseTensor CastDateType(const Context& dev_ctx,
+phi::DenseTensor CastDataType(const Context& dev_ctx,
                               const phi::DenseTensor& tensor,
                               DataType dtype) {
   switch (tensor.dtype()) {
@@ -111,7 +111,7 @@ phi::DenseTensor CastDateType(const Context& dev_ctx,
 }
 
 #if defined(PADDLE_WITH_CUDA) || defined(PADDLE_WITH_HIP)
-phi::DenseTensor CastDateType(const phi::GPUContext& dev_ctx,
+phi::DenseTensor CastDataType(const phi::GPUContext& dev_ctx,
                               const phi::DenseTensor& tensor,
                               DataType dtype) {
   switch (tensor.dtype()) {
@@ -151,11 +151,11 @@ inline phi::DenseTensor TransDataType(const phi::DenseTensor& tensor,
 
   if (platform::is_cpu_place(tensor.place())) {
     auto* dev_ctx = static_cast<phi::CPUContext*>(pool.Get(tensor.place()));
-    return CastDateType(*dev_ctx, tensor, dtype);
+    return CastDataType(*dev_ctx, tensor, dtype);
 #if defined(PADDLE_WITH_CUDA) || defined(PADDLE_WITH_HIP)
   } else if (platform::is_gpu_place(tensor.place())) {
     auto* dev_ctx = static_cast<phi::GPUContext*>(pool.Get(tensor.place()));
-    return CastDateType(*dev_ctx, tensor, dtype);
+    return CastDataType(*dev_ctx, tensor, dtype);
 #endif
   } else {
     PADDLE_THROW(phi::errors::Unimplemented(

paddle/phi/kernels/cpu/put_along_axis_kernel.cc

@@ -67,7 +67,7 @@ void PutAlongAxisKernel(const Context& dev_ctx,
     PADDLE_THROW(errors::InvalidArgument(
         "can not support reduce: '%s' for scatter kernel, only "
         "support reduce op: 'add', 'assign', 'mul' and 'multiply', the "
-        "defalut reduce "
+        "default reduce "
         "op is 'assign' ",
         reduce));
     return;

paddle/phi/kernels/gpu/put_along_axis_kernel.cu

@@ -68,7 +68,7 @@ void PutAlongAxisKernel(const Context& dev_ctx,
     PADDLE_THROW(errors::InvalidArgument(
         "can not support reduce: '%s' for scatter kernel, only "
         "support reduce op: 'add', 'assign', 'mul' and 'multiply', the "
-        "defalut reduce op is 'assign' ",
+        "default reduce op is 'assign' ",
         reduce));
     return;
   }

python/paddle/distributed/fleet/dataset/dataset.py

@@ -54,7 +54,7 @@ class DatasetBase(object):
             thread_num(int): thread num, it is the num of readers. default is 1.
             use_var(list): list of variables. Variables which you will use. default is [].
             pipe_command(str): pipe command of current dataset. A pipe command is a UNIX pipeline command that can be used only. default is "cat"
-            input_type(int): the input type of generated input. 0 is for one sample, 1 is for one batch. defalut is 0.
+            input_type(int): the input type of generated input. 0 is for one sample, 1 is for one batch. default is 0.
             fs_name(str): fs name. default is "".
             fs_ugi(str): fs ugi. default is "".
             download_cmd(str): customized download command. default is "cat"
@@ -441,7 +441,7 @@ class InMemoryDataset(DatasetBase):
             batch_size(int): batch size. It will be effective during training. default is 1.
             thread_num(int): thread num, it is the num of readers. default is 1.
             use_var(list): list of variables. Variables which you will use. default is [].
-            input_type(int): the input type of generated input. 0 is for one sample, 1 is for one batch. defalut is 0.
+            input_type(int): the input type of generated input. 0 is for one sample, 1 is for one batch. default is 0.
             fs_name(str): fs name. default is "".
             fs_ugi(str): fs ugi. default is "".
             pipe_command(str): pipe command of current dataset. A pipe command is a UNIX pipeline command that can be used only. default is "cat"
@@ -522,7 +522,7 @@ class InMemoryDataset(DatasetBase):
             batch_size(int): batch size. It will be effective during training. default is 1.
             thread_num(int): thread num, it is the num of readers. default is 1.
             use_var(list): list of variables. Variables which you will use. default is [].
-            input_type(int): the input type of generated input. 0 is for one sample, 1 is for one batch. defalut is 0.
+            input_type(int): the input type of generated input. 0 is for one sample, 1 is for one batch. default is 0.
             fs_name(str): fs name. default is "".
             fs_ugi(str): fs ugi. default is "".
             pipe_command(str): pipe command of current dataset. A pipe command is a UNIX pipeline command that can be used only. default is "cat"

python/paddle/fluid/contrib/sparsity/asp.py

@@ -316,7 +316,7 @@ def prune_model(model, n=2, m=4, mask_algo='mask_1d', with_mask=True):
         m (int, optional): m of `n:m` sparse pattern. Default is 4.
         mask_algo (string, optional): The function name to generate spase mask. Default is `mask_1d`.
                                       The vaild inputs should be one of 'mask_1d', 'mask_2d_greedy' and 'mask_2d_best'.
-        with_mask (bool, optional): To prune mask Variables related to parameters or not. Ture is purning also, False is not. Defalut is True.
+        with_mask (bool, optional): To prune mask Variables related to parameters or not. Ture is purning also, False is not. Default is True.
     Returns:
         dictionary: A dictionary with key: `parameter name` (string) and value: its corresponding mask Variable.
     Examples:

python/paddle/fluid/layers/nn.py

@@ -14912,7 +14912,7 @@ def unique_with_counts(x, dtype='int32'):
 
     Args:
         x(Variable): A 1-D input tensor with input shape of :math:`[N]` , the input data type is float32, float64, int32, int64.
-        dtype(np.dtype|core.VarDesc.VarType|str): The type of count and index tensor, it could be int32, int64. Defalut value is int32.
+        dtype(np.dtype|core.VarDesc.VarType|str): The type of count and index tensor, it could be int32, int64. Default value is int32.
 
     Returns:
         tuple, the variable type in tuple is Tensor, the output :attr:`out` data type is the same as input :attr:`x`, \

python/paddle/fluid/tests/custom_kernel/test_custom_kernel_load.py

@@ -48,7 +48,7 @@ class TestCustomKernelLoad(unittest.TestCase):
                     paddle_lib_path = lib_dir
         self.default_path = os.path.sep.join(
             [paddle_lib_path, '..', '..', 'paddle-plugins'])
-        # copy so to defalut path
+        # copy so to default path
         cmd = 'mkdir -p {} && cp ./*.so {}'.format(self.default_path,
                                                    self.default_path)
         os.system(cmd)  # wait

python/paddle/fluid/tests/unittests/collective/README.md

@@ -8,11 +8,11 @@
 * `name`: the test's name
 * `os`: The supported operator system, ignoring case. If the test run in multiple operator systems, use ";" to split systems, for example, `apple;linux` means the test runs on both Apple and Linux. The supported values are `linux`,`win32` and `apple`. If the value is empty, this means the test runs on all opertaor systems.
 * `arch`: the device's architecture. similar to `os`, multiple valuse ars splited by ";" and ignoring case. The supported architectures are `gpu`, `xpu`, `ASCEND`, `ASCEND_CL` and `rocm`.
-* `timeout`: timeout of a unittest, whose unit is second. Blank means defalut.
+* `timeout`: timeout of a unittest, whose unit is second. Blank means default.
 * `run_type`: run_type of a unittest. Supported values are `NIGHTLY`, `EXCLUSIVE`, `CINN`, `DIST`, `GPUPS`, `INFER`, `EXCLUSIVE:NIGHTLY`, `DIST:NIGHTLY`，which are case-insensitive.
 * `launcher`: the test launcher.Supported values are test_runner.py, dist_test.sh and custom scripts' name. Blank means test_runner.py.
 * `num_port`: the number of port used in a distributed unit test. Blank means automatically distributed port.
-* `run_serial`: whether in serial mode. the value can be 1 or 0.Default (empty) is 0. Blank means defalut.
+* `run_serial`: whether in serial mode. the value can be 1 or 0.Default (empty) is 0. Blank means default.
 * `ENVS`: required environments. multiple envirenmonts are splited by ";".
 * `conditions`: extra required conditions for some tests. The value is a list of boolean expression in cmake programmer, splited with ";". For example, the value can be `WITH_DGC;NOT WITH_NCCL` or `WITH_NCCL;${NCCL_VERSION} VERSION_GREATER_EQUAL 2212`,The relationship between these expressions is a conjunction.
 

python/paddle/incubate/sparse/nn/layer/norm.py

@@ -78,7 +78,7 @@ class BatchNorm(paddle.nn.BatchNorm1D):
             If it is set to None or one attribute of ParamAttr, batch_norm
             will create ParamAttr as bias_attr. If it is set to Fasle, the weight is not learnable.
             If the Initializer of the bias_attr is not set, the bias is initialized zero. Default: None.
-        data_format(str, optional): Specify the input data format, may be "NC", "NCL" or "NLC". Defalut "NCL".
+        data_format(str, optional): Specify the input data format, may be "NC", "NCL" or "NLC". Default "NCL".
         use_global_stats(bool|None, optional): Whether to use global mean and variance. If set to False, use the statistics of one mini-batch, if set to True, use the global statistics, if set to None, use global statistics in the test phase and use the statistics of one mini-batch in the training phase. Default: None.
         name(str, optional): Name for the BatchNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 

python/paddle/nn/functional/norm.py

@@ -140,8 +140,8 @@ def batch_norm(x,
         bias(Tensor): The bias tensor of batch_norm can not be None.
         epsilon(float, optional): The small value added to the variance to prevent division by zero. Default: 1e-5.
         momentum(float, optional): The value used for the moving_mean and moving_var computation. Default: 0.9.
-        training(bool, optional): True means train mode which compute by batch data and track global mean and var during train period. False means inference mode which compute by global mean and var which calculated by train period. Defalut False.
-        data_format(str, optional): Specify the input data format, may be "NC", "NCL", "NCHW", "NCDHW", "NLC", "NHWC" or "NDHWC". Defalut "NCHW".
+        training(bool, optional): True means train mode which compute by batch data and track global mean and var during train period. False means inference mode which compute by global mean and var which calculated by train period. Default False.
+        data_format(str, optional): Specify the input data format, may be "NC", "NCL", "NCHW", "NCDHW", "NLC", "NHWC" or "NDHWC". Default "NCHW".
         use_global_stats(bool|None, optional): Whether to use global mean and variance. If set to False, use the statistics of one mini-batch, if set to True, use the global statistics, if set to None, use global statistics in the test phase and use the statistics of one mini-batch in the training phase. Default: None.
         name(str, optional): Name for the BatchNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 
@@ -392,7 +392,7 @@ def instance_norm(x,
         eps(float, optional): A value added to the denominator for numerical stability. Default is 1e-5.
         momentum(float, optional): The value used for the moving_mean and moving_var computation. Default: 0.9.
         use_input_stats(bool): Default True.
-        data_format(str, optional): Specify the input data format, may be "NC", "NCL", "NCHW" or "NCDHW". Defalut "NCHW".
+        data_format(str, optional): Specify the input data format, may be "NC", "NCL", "NCHW" or "NCDHW". Default "NCHW".
         name(str, optional): Name for the InstanceNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 
     Returns:

python/paddle/nn/layer/norm.py

@@ -144,7 +144,7 @@ class InstanceNorm1D(_InstanceNormBase):
 	     will create ParamAttr as bias_attr, the name of bias can be set in ParamAttr.
 	     If the Initializer of the bias_attr is not set, the bias is initialized zero.
              If it is set to False, will not create bias_attr. Default: None.
-        data_format(str, optional): Specify the input data format, may be "NC", "NCL". Defalut "NCL".
+        data_format(str, optional): Specify the input data format, may be "NC", "NCL". Default "NCL".
         name(str, optional): Name for the InstanceNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 
 
@@ -743,7 +743,7 @@ class BatchNorm1D(_BatchNormBase):
             If it is set to None or one attribute of ParamAttr, batch_norm
             will create ParamAttr as bias_attr. If it is set to Fasle, the weight is not learnable.
             If the Initializer of the bias_attr is not set, the bias is initialized zero. Default: None.
-        data_format(str, optional): Specify the input data format, may be "NC", "NCL" or "NLC". Defalut "NCL".
+        data_format(str, optional): Specify the input data format, may be "NC", "NCL" or "NLC". Default "NCL".
         use_global_stats(bool|None, optional): Whether to use global mean and variance. If set to False, use the statistics of one mini-batch, if set to True, use the global statistics, if set to None, use global statistics in the test phase and use the statistics of one mini-batch in the training phase. Default: None.
         name(str, optional): Name for the BatchNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 

python/paddle/tensor/linalg.py

@@ -276,7 +276,7 @@ def norm(x, p='fro', axis=None, keepdim=False, name=None):
             or list(int)/tuple(int)  with only one element, the vector norm is computed over the axis.
             If `axis < 0`, the dimension to norm operation is rank(input) + axis.
             If axis is a list(int)/tuple(int) with two elements, the matrix norm is computed over the axis.
-            Defalut value is `None`.
+            Default value is `None`.
         keepdim (bool, optional): Whether to reserve the reduced dimension in the
             output Tensor. The result tensor will have fewer dimension
             than the :attr:`input` unless :attr:`keepdim` is true, default
@@ -2589,7 +2589,7 @@ def pinv(x, rcond=1e-15, hermitian=False, name=None):
             True.
 
         rcond(Tensor, optional): the tolerance value to determine
-            when is a singular value zero. Defalut:1e-15.
+            when is a singular value zero. Default:1e-15.
 
         hermitian(bool, optional): indicates whether x is Hermitian
             if complex or symmetric if real. Default: False.