From 4b2e90d31c12ce1c15295ea9f956d93c21684ee4 Mon Sep 17 00:00:00 2001
From: co63oc <co63oc@users.noreply.github.com>
Date: Thu, 18 Jan 2024 11:31:56 +0800
Subject: [PATCH]  Fix minimun minimum (#60920)

---
 python/paddle/sparse/creation.py              |  4 +-
 python/paddle/sparse/nn/layer/activation.py   |  2 +-
 python/paddle/sparse/nn/layer/conv.py         | 40 +++++++++----------
 python/paddle/sparse/nn/layer/norm.py         |  2 +-
 python/paddle/sparse/unary.py                 |  4 +-
 python/paddle/static/input.py                 |  2 +-
 python/paddle/static/io.py                    | 26 ++++++------
 python/paddle/static/nn/common.py             | 16 ++++----
 python/paddle/static/nn/control_flow.py       | 24 +++++------
 .../static/quantization/cal_kl_threshold.py   |  2 +-
 .../post_training_quantization.py             | 22 +++++-----
 python/paddle/static/quantization/quanter.py  |  6 +--
 .../static/quantization/quantization_pass.py  | 12 +++---
 python/paddle/tensor/array.py                 | 16 ++++----
 14 files changed, 89 insertions(+), 89 deletions(-)

diff --git a/python/paddle/sparse/creation.py b/python/paddle/sparse/creation.py
index f5a7fe306723f..89ee841053a97 100644
--- a/python/paddle/sparse/creation.py
+++ b/python/paddle/sparse/creation.py
@@ -155,7 +155,7 @@ def sparse_coo_tensor(
             shape = list(shape)
             if shape < min_shape:
                 raise ValueError(
-                    f"the minimun shape required is {min_shape}, but get {shape}"
+                    f"the minimum shape required is {min_shape}, but get {shape}"
                 )
             if len(shape) != sparse_dim + dense_dim:
                 raise ValueError(
@@ -188,7 +188,7 @@ def sparse_csr_tensor(
     r"""
     Constructs a sparse ``paddle.Tensor`` in CSR(Compressed Sparse Row) format according to the
     ``crows``, ``cols`` and ``values``.
-    Currently, the crows and cols of each batch must be incrementd.
+    Currently, the crows and cols of each batch must be incremented.
 
     Args:
         crows(list|tuple|ndarray|Tensor): 1-D array, each element in the rows represents the
diff --git a/python/paddle/sparse/nn/layer/activation.py b/python/paddle/sparse/nn/layer/activation.py
index eedecc7a3b1d2..ec01db4fc0dc7 100644
--- a/python/paddle/sparse/nn/layer/activation.py
+++ b/python/paddle/sparse/nn/layer/activation.py
@@ -72,7 +72,7 @@ class Softmax(Layer):
         Only support axis=-1 for SparseCsrTensor, which is faster when read data
         by row (axis=-1).
 
-    Transform x to dense matix, and :math:`i` is row index, :math:`j` is column index.
+    Transform x to dense matrix, and :math:`i` is row index, :math:`j` is column index.
     If axis=-1, We have:
 
     .. math::
diff --git a/python/paddle/sparse/nn/layer/conv.py b/python/paddle/sparse/nn/layer/conv.py
index d3295148fbc15..6ed3c840f39e9 100644
--- a/python/paddle/sparse/nn/layer/conv.py
+++ b/python/paddle/sparse/nn/layer/conv.py
@@ -238,7 +238,7 @@ def extra_repr(self):
 
 class Conv3D(_Conv3D):
     r"""
-    **Sparse Convlution3d Layer**
+    **Sparse Convolution3d Layer**
     The Sparse convolution3d layer calculates the output based on the input, filter
     and strides, paddings, dilations, groups parameters. Input(Input) and
     Output(Output) are multidimensional SparseCooTensors with a shape of
@@ -267,11 +267,11 @@ class Conv3D(_Conv3D):
         stride(int|list|tuple, optional): The stride size. If stride is a list/tuple, it must
             contain three integers, (stride_D, stride_H, stride_W). Otherwise, the
             stride_D = stride_H = stride_W = stride. The default value is 1.
-        padding(int|str|tuple|list, optional): The padding size. Padding coule be in one of the following forms.
+        padding(int|str|tuple|list, optional): The padding size. Padding couple be in one of the following forms.
             1. a string in ['valid', 'same'].
-            2. an int, which means each spartial dimension(depth, height, width) is zero paded by size of `padding`
-            3. a list[int] or tuple[int] whose length is the number of spartial dimensions, which contains the amount of padding on each side for each spartial dimension. It has the form [pad_d1, pad_d2, ...].
-            4. a list[int] or tuple[int] whose length is 2 * number of spartial dimensions. It has the form  [pad_before, pad_after, pad_before, pad_after, ...] for all spartial dimensions.
+            2. an int, which means each spatial dimension(depth, height, width) is zero padded by size of `padding`
+            3. a list[int] or tuple[int] whose length is the number of spatial dimensions, which contains the amount of padding on each side for each spatial dimension. It has the form [pad_d1, pad_d2, ...].
+            4. a list[int] or tuple[int] whose length is 2 * number of spatial dimensions. It has the form  [pad_before, pad_after, pad_before, pad_after, ...] for all spatial dimensions.
             5. a list or tuple of pairs of ints. It has the form [[pad_before, pad_after], [pad_before, pad_after], ...]. Note that, the batch dimension and channel dimension are also included. Each pair of integers correspond to the amount of padding for a dimension of the input. Padding in batch dimension and channel dimension should be [0, 0] or (0, 0).
             The default value is 0.
         dilation(int|list|tuple, optional): The dilation size. If dilation is a list/tuple, it must
@@ -373,7 +373,7 @@ def __init__(
 
 class Conv2D(_Conv2D):
     r"""
-    **Sparse Convlution2d Layer**
+    **Sparse Convolution2d Layer**
 
     The Sparse convolution2d layer calculates the output based on the input, filter
     and strides, paddings, dilations, groups parameters. Input(Input) and
@@ -403,12 +403,12 @@ class Conv2D(_Conv2D):
         stride(int|list|tuple, optional): The stride size. If stride is a list/tuple, it must
             contain three integers, (stride_H, stride_W). Otherwise, the
             stride_H = stride_W = stride. The default value is 1.
-        padding(int|str|tuple|list, optional): The padding size. Padding coule be in one of the following forms.
+        padding(int|str|tuple|list, optional): The padding size. Padding couple be in one of the following forms.
 
             1. a string in ['valid', 'same'].
-            2. an int, which means each spartial dimension(height, width) is zero paded by size of `padding`
-            3. a list[int] or tuple[int] whose length is the number of spartial dimensions, which contains the amount of padding on each side for each spartial dimension. It has the form [pad_d1, pad_d2, ...].
-            4. a list[int] or tuple[int] whose length is 2 * number of spartial dimensions. It has the form  [pad_before, pad_after, pad_before, pad_after, ...] for all spartial dimensions.
+            2. an int, which means each spatial dimension(height, width) is zero padded by size of `padding`
+            3. a list[int] or tuple[int] whose length is the number of spatial dimensions, which contains the amount of padding on each side for each spatial dimension. It has the form [pad_d1, pad_d2, ...].
+            4. a list[int] or tuple[int] whose length is 2 * number of spatial dimensions. It has the form  [pad_before, pad_after, pad_before, pad_after, ...] for all spatial dimensions.
             5. a list or tuple of pairs of ints. It has the form [[pad_before, pad_after], [pad_before, pad_after], ...].
 
             Note that, the batch dimension and channel dimension are also included. Each pair of integers correspond to the amount of padding for a dimension of the input. Padding in batch dimension and channel dimension should be [0, 0] or (0, 0).
@@ -508,7 +508,7 @@ def __init__(
 
 class SubmConv3D(_Conv3D):
     r"""
-    **Submanifold Sparse Convlution3d Layer**
+    **Submanifold Sparse Convolution3d Layer**
     The submanifold sparse convolution3d layer calculates the output based on the input, filter
     and strides, paddings, dilations, groups parameters. Input(Input) and
     Output(Output) are multidimensional SparseCooTensors with a shape of
@@ -537,11 +537,11 @@ class SubmConv3D(_Conv3D):
         stride(int|list|tuple, optional): The stride size. If stride is a list/tuple, it must
             contain three integers, (stride_D, stride_H, stride_W). Otherwise, the
             stride_D = stride_H = stride_W = stride. The default value is 1.
-        padding(int|str|tuple|list, optional): The padding size. Padding coule be in one of the following forms.
+        padding(int|str|tuple|list, optional): The padding size. Padding couple be in one of the following forms.
             1. a string in ['valid', 'same'].
-            2. an int, which means each spartial dimension(depth, height, width) is zero paded by size of `padding`
-            3. a list[int] or tuple[int] whose length is the number of spartial dimensions, which contains the amount of padding on each side for each spartial dimension. It has the form [pad_d1, pad_d2, ...].
-            4. a list[int] or tuple[int] whose length is 2 * number of spartial dimensions. It has the form  [pad_before, pad_after, pad_before, pad_after, ...] for all spartial dimensions.
+            2. an int, which means each spatial dimension(depth, height, width) is zero padded by size of `padding`
+            3. a list[int] or tuple[int] whose length is the number of spatial dimensions, which contains the amount of padding on each side for each spatial dimension. It has the form [pad_d1, pad_d2, ...].
+            4. a list[int] or tuple[int] whose length is 2 * number of spatial dimensions. It has the form  [pad_before, pad_after, pad_before, pad_after, ...] for all spatial dimensions.
             5. a list or tuple of pairs of ints. It has the form [[pad_before, pad_after], [pad_before, pad_after], ...]. Note that, the batch dimension and channel dimension are also included. Each pair of integers correspond to the amount of padding for a dimension of the input. Padding in batch dimension and channel dimension should be [0, 0] or (0, 0).
             The default value is 0.
         dilation(int|list|tuple, optional): The dilation size. If dilation is a list/tuple, it must
@@ -648,7 +648,7 @@ def __init__(
 
 class SubmConv2D(_Conv2D):
     r"""
-    **Submanifold Sparse Convlution2d Layer**
+    **Submanifold Sparse Convolution2d Layer**
 
     The submanifold sparse convolution2d layer calculates the output based on the input, filter
     and strides, paddings, dilations, groups parameters. Input(Input) and
@@ -678,12 +678,12 @@ class SubmConv2D(_Conv2D):
         stride(int|list|tuple, optional): The stride size. If stride is a list/tuple, it must
             contain two integers, (stride_H, stride_W). Otherwise, the
             stride_H = stride_W = stride. The default value is 1.
-        padding(int|str|tuple|list, optional): The padding size. Padding coule be in one of the following forms.
+        padding(int|str|tuple|list, optional): The padding size. Padding couple be in one of the following forms.
 
             1. a string in ['valid', 'same'].
-            2. an int, which means each spartial dimension(depth, height, width) is zero paded by size of `padding`
-            3. a list[int] or tuple[int] whose length is the number of spartial dimensions, which contains the amount of padding on each side for each spartial dimension. It has the form [pad_d1, pad_d2, ...].
-            4. a list[int] or tuple[int] whose length is 2 * number of spartial dimensions. It has the form  [pad_before, pad_after, pad_before, pad_after, ...] for all spartial dimensions.
+            2. an int, which means each spatial dimension(depth, height, width) is zero padded by size of `padding`
+            3. a list[int] or tuple[int] whose length is the number of spatial dimensions, which contains the amount of padding on each side for each spatial dimension. It has the form [pad_d1, pad_d2, ...].
+            4. a list[int] or tuple[int] whose length is 2 * number of spatial dimensions. It has the form  [pad_before, pad_after, pad_before, pad_after, ...] for all spatial dimensions.
             5. a list or tuple of pairs of ints. It has the form [[pad_before, pad_after], [pad_before, pad_after], ...].
 
             Note that, the batch dimension and channel dimension are also included. Each pair of integers correspond to the amount of padding for a dimension of the input. Padding in batch dimension and channel dimension should be [0, 0] or (0, 0).
diff --git a/python/paddle/sparse/nn/layer/norm.py b/python/paddle/sparse/nn/layer/norm.py
index 4b9b4087bd1b5..c83ce82f80686 100644
--- a/python/paddle/sparse/nn/layer/norm.py
+++ b/python/paddle/sparse/nn/layer/norm.py
@@ -260,7 +260,7 @@ class SyncBatchNorm(paddle.nn.SyncBatchNorm):
         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.
         weight_attr(ParamAttr|bool, optional): The parameter attribute for Parameter `scale`
-             of this layer. If it is set to None or one attribute of ParamAttr, this layerr
+             of this layer. If it is set to None or one attribute of ParamAttr, this layer
              will create ParamAttr as param_attr. If the Initializer of the param_attr
              is not set, the parameter is initialized with Xavier. If it is set to False,
              this layer will not have trainable scale parameter. Default: None.
diff --git a/python/paddle/sparse/unary.py b/python/paddle/sparse/unary.py
index 9f9bafc135b63..ddb8fc669e8f8 100644
--- a/python/paddle/sparse/unary.py
+++ b/python/paddle/sparse/unary.py
@@ -953,7 +953,7 @@ def slice(x, axes, starts, ends, name=None):
     ``starts`` or ``ends`` such as :math:`-i`, it represents the reverse position of
     the axis :math:`i-1` (here 0 is the initial position).
     If the value passed to ``starts`` or ``ends`` is greater than the number of elements
-    in the dimenstion (n), it represents n.
+    in the dimension (n), it represents n.
     For slicing to the end of a dimension with unknown size, it is recommended to pass
     in INT_MAX. The size of ``axes`` must be equal to ``starts`` and ``ends``.
 
@@ -1039,7 +1039,7 @@ def pca_lowrank(x, q=None, center=True, niter=2, name=None):
 
     Args:
         x (Tensor): The input tensor. Its shape should be `[N, M]`,
-            N and M can be arbitraty positive number.
+            N and M can be arbitrary positive number.
             The data type of x should be float32 or float64.
         q (int, optional): a slightly overestimated rank of :math:`X`.
             Default value is :math:`q=min(6,N,M)`.
diff --git a/python/paddle/static/input.py b/python/paddle/static/input.py
index f8ee2b9bfafbd..554aaf28a1cbd 100644
--- a/python/paddle/static/input.py
+++ b/python/paddle/static/input.py
@@ -207,7 +207,7 @@ class InputSpec:
     def __init__(self, shape, dtype='float32', name=None, stop_gradient=False):
         # replace `None` in shape  with -1
         self.shape = self._verify(shape)
-        # convert dtype into united represention
+        # convert dtype into united representation
         if dtype is not None:
             if isinstance(dtype, (np.dtype, str)):
                 dtype = convert_np_dtype_to_dtype_(dtype)
diff --git a/python/paddle/static/io.py b/python/paddle/static/io.py
index 7426dc0b05b0f..64ee380b4b392 100644
--- a/python/paddle/static/io.py
+++ b/python/paddle/static/io.py
@@ -197,7 +197,7 @@ def normalize_program(program, feed_vars, fetch_vars, **kwargs):
         feed_vars(Tensor | list[Tensor]): Variables needed by inference.
         fetch_vars(Tensor | list[Tensor]): Variables returned by inference.
         kwargs: Supported keys including ``skip_prune_program``.
-            - skip_prune_program(bool): whether to skip prunning program. Defaults to False.
+            - skip_prune_program(bool): whether to skip pruning program. Defaults to False.
 
     Returns:
         Program: Normalized/Optimized program.
@@ -211,7 +211,7 @@ def normalize_program(program, feed_vars, fetch_vars, **kwargs):
 
             >>> path_prefix = "./infer_model"
 
-            # User defined network, here a softmax regession example
+            # User defined network, here a softmax regression example
             >>> image = paddle.static.data(name='img', shape=[None, 28, 28], dtype='float32')
             >>> label = paddle.static.data(name='label', shape=[None, 1], dtype='int64')
             >>> predict = paddle.static.nn.fc(image, 10, activation='softmax')
@@ -283,10 +283,10 @@ def normalize_program(program, feed_vars, fetch_vars, **kwargs):
                 # remove backward block
                 copy_program.blocks.pop(backward_block_id)
                 # update attrs ``blocks``
-                reserverd_blocks = []
+                reserved_blocks = []
                 for block_id in sub_blocks_ids[:-1]:
-                    reserverd_blocks.append(copy_program.block(block_id))
-                op._update_desc_attr("blocks", reserverd_blocks)
+                    reserved_blocks.append(copy_program.block(block_id))
+                op._update_desc_attr("blocks", reserved_blocks)
 
     for idx in remove_op_idx[::-1]:
         global_block._remove_op(idx)
@@ -332,7 +332,7 @@ def serialize_program(feed_vars, fetch_vars, **kwargs):
 
             >>> path_prefix = "./infer_model"
 
-            # User defined network, here a softmax regession example
+            # User defined network, here a softmax regression example
             >>> image = paddle.static.data(name='img', shape=[None, 28, 28], dtype='float32')
             >>> label = paddle.static.data(name='label', shape=[None, 1], dtype='int64')
             >>> predict = paddle.static.nn.fc(image, 10, activation='softmax')
@@ -391,7 +391,7 @@ def serialize_persistables(feed_vars, fetch_vars, executor, **kwargs):
 
             >>> path_prefix = "./infer_model"
 
-            # User defined network, here a softmax regession example
+            # User defined network, here a softmax regression example
             >>> image = paddle.static.data(name='img', shape=[None, 28, 28], dtype='float32')
             >>> label = paddle.static.data(name='label', shape=[None, 1], dtype='int64')
             >>> predict = paddle.static.nn.fc(image, 10, activation='softmax')
@@ -431,7 +431,7 @@ def _serialize_persistables(program, executor):
             "variables in your model to save"
         )
         return None
-    # create a new program and clone persitable vars to it
+    # create a new program and clone persistable vars to it
     save_program = Program()
     save_block = save_program.global_block()
     save_var_map = {}
@@ -543,7 +543,7 @@ def save_inference_model(
 
             >>> path_prefix = "./infer_model"
 
-            # User defined network, here a softmax regession example
+            # User defined network, here a softmax regression example
             >>> image = paddle.static.data(name='img', shape=[None, 28, 28], dtype='float32')
             >>> label = paddle.static.data(name='label', shape=[None, 1], dtype='int64')
             >>> predict = paddle.static.nn.fc(image, 10, activation='softmax')
@@ -644,7 +644,7 @@ def deserialize_program(data):
 
             >>> path_prefix = "./infer_model"
 
-            # User defined network, here a softmax regession example
+            # User defined network, here a softmax regression example
             >>> image = paddle.static.data(name='img', shape=[None, 28, 28], dtype='float32')
             >>> label = paddle.static.data(name='label', shape=[None, 1], dtype='int64')
             >>> predict = paddle.static.nn.fc(image, 10, activation='softmax')
@@ -693,7 +693,7 @@ def deserialize_persistables(program, data, executor):
 
             >>> path_prefix = "./infer_model"
 
-            # User defined network, here a softmax regession example
+            # User defined network, here a softmax regression example
             >>> image = paddle.static.data(name='img', shape=[None, 28, 28], dtype='float32')
             >>> label = paddle.static.data(name='label', shape=[None, 1], dtype='int64')
             >>> predict = paddle.static.nn.fc(image, 10, activation='softmax')
@@ -1620,7 +1620,7 @@ def load(program, model_path, executor=None, var_list=None):
             program_var_list = program.list_vars()
             program_var_name_set = {var.name for var in program_var_list}
 
-            # check all the variable inlcuded in program
+            # check all the variable included in program
             for var in var_list:
                 if var.name not in program_var_name_set:
                     raise LookupError(
@@ -1804,7 +1804,7 @@ def set_program_state(program, state_dict):
             unused_para_list.append(k)
     if len(unused_para_list) > 0:
         warnings.warn(
-            "This list is not set, Because of Paramerter not found in program. There are: {}".format(
+            "This list is not set, Because of Parameter not found in program. There are: {}".format(
                 " ".join(unused_para_list)
             )
         )
diff --git a/python/paddle/static/nn/common.py b/python/paddle/static/nn/common.py
index 837420900502c..65f21a169cb63 100644
--- a/python/paddle/static/nn/common.py
+++ b/python/paddle/static/nn/common.py
@@ -496,7 +496,7 @@ def data_norm(
             should do model average when model average is enabled. Default: True.
         slot_dim (int, optional): The embedding dimension of one slot. Slot is a set of one specific feature. In pslib mode,
             we distinguish feature ids by slot and pull their embeddings from parameter server (pslib). The first
-            place of the embedding is the historical show number (occurence time of this feature id with a label 0).
+            place of the embedding is the historical show number (occurrence time of this feature id with a label 0).
             If the input of this op is concated by slot-wise embeddings, and the show number is zero when this slot
             is new or empty, the normalization result may be impractical. To avoid this, we add slot_dim to locate
             the show number and judge if the show number is zero. If so, we choose to skip normalization on this
@@ -920,7 +920,7 @@ def conv2d(
     num_channels = input.shape[3] if channel_last else input.shape[1]
     if num_channels < 0:
         raise ValueError(
-            "The channel dimmention of the input({}) should be defined. "
+            "The channel dimension of the input({}) should be defined. "
             "Received: {}.".format(str(input.shape), str(num_channels))
         )
     assert param_attr is not False, "param_attr should not be False here."
@@ -1236,7 +1236,7 @@ def conv3d(
     num_channels = input.shape[4] if channel_last else input.shape[1]
     if num_channels < 0:
         raise ValueError(
-            "The channel dimmention of the input({}) should be defined. "
+            "The channel dimension of the input({}) should be defined. "
             "Received: {}.".format(str(input.shape), str(num_channels))
         )
 
@@ -2811,11 +2811,11 @@ def batch_norm(
     variance_out = variance
 
     if in_dygraph_mode():
-        inputs_has_MomemtumTensor = False
+        inputs_has_MomentumTensor = False
         attrs_has_momentum = False
         tmp_tensor_type = core.eager.Tensor
         if isinstance(momentum, tmp_tensor_type):
-            inputs_has_MomemtumTensor = True
+            inputs_has_MomentumTensor = True
         else:
             attrs_has_momentum = True
 
@@ -2848,7 +2848,7 @@ def batch_norm(
                 'use_global_stats',
                 use_global_stats,
             )
-        if inputs_has_MomemtumTensor:
+        if inputs_has_MomentumTensor:
             batch_norm_out, _, _, _, _, _ = paddle._legacy_C_ops.batch_norm(
                 input,
                 scale,
@@ -3426,7 +3426,7 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None):
                   Input(Weight) is the weight of conv layer, default 0.
         power_iters(int): number of power iterations to calculate spectral norm, default 1.
         eps(float): epsilon for numerical stability in calculating norms, it will be added to
-                    the denominator to aviod divide zero. Default 1e-12.
+                    the denominator to avoid divide zero. Default 1e-12.
         name(str, optional): For detailed information, please refer
                              to :ref:`api_guide_Name`. Usually name is no need to set and
                              None by default.
@@ -3880,7 +3880,7 @@ def sparse_embedding(
             If :math:`padding\_idx < 0`, the :math:`padding\_idx` will automatically be converted
             to :math:`vocab\_size + padding\_idx` . It will output all-zero padding data whenever
             lookup encounters :math:`padding\_idx` in id. And the padding data will not be updated
-            while training. If set None, it makes no efe mfect to output. Default: None.
+            while training. If set None, it makes no effect to output. Default: None.
         is_test(bool, optional): Training or prediction mode. In prediction mode (is_test=False),
             the output is not initialized and created, and it is filled with 0 and returned. Default: False.
         entry(str, optional): Entry config with parameter server whose value is ProbabilityEntry,
diff --git a/python/paddle/static/nn/control_flow.py b/python/paddle/static/nn/control_flow.py
index 7f6f607e0ed4e..2e3a4f3de69dd 100644
--- a/python/paddle/static/nn/control_flow.py
+++ b/python/paddle/static/nn/control_flow.py
@@ -283,7 +283,7 @@ def append_conditional_block_grad(
         `conditional_block_grad` is appended manually.
 
         Args:
-            parent_block (Block): The block that `conditional_block_op` blongs to.
+            parent_block (Block): The block that `conditional_block_op` belongs to.
             inside_block (Block): The sub block of `conditional_block_op`.
             conditional_block_op (Operator): The forward op conditional_block.
         '''
@@ -397,7 +397,7 @@ def is_ignore_vars(op, var_name):
 
     # Step1: update inner_inputs and inner_outputs
     # NOTE: Here assumes that all variables are input or output of Ops,
-    # but some variables are created without appendding a real op.
+    # but some variables are created without appending a real op.
     # For example, in `arr = create_array(dtype)`, `arr` is not a output of a op.
     for op in current_block.ops:
         assert isinstance(op, Operator)
@@ -614,7 +614,7 @@ def has_shape_diff(x_var, y_var):
             and has_shape_diff(input, output)
         ):
             warnings.warn(
-                "In dy2static mode, we attemp to assign a variable with shape {} into a variable with shape{}, which is not always right.".format(
+                "In dy2static mode, we attempt to assign a variable with shape {} into a variable with shape{}, which is not always right.".format(
                     input.shape, output.shape
                 )
             )
@@ -1123,7 +1123,7 @@ def cond(pred, true_fn=None, false_fn=None, name=None, return_names=None):
     ``None`` in this case.
 
     ``true_fn`` and ``false_fn`` should return same nest structure of tensors
-    or both return ``None`` if user doens't like to return anything. A nest
+    or both return ``None`` if user doesn't like to return anything. A nest
     structure of tensors in PaddlePaddle is tensor(s), or tuple of tensors, or
     list of tensors.
 
@@ -1319,13 +1319,13 @@ def cond(pred, true_fn=None, false_fn=None, name=None, return_names=None):
 
     # Merge true and false output if they are not None
     if return_names is None:
-        is_dy2staic = False
+        is_dy2static = False
         return_names = ["no name"] * len(_to_sequence_except_dict(true_output))
     else:
         """
         dy2static will set the return_names and expand the return values to UndefinedVar.
         """
-        is_dy2staic = True
+        is_dy2static = True
 
         # TODO:  expand_undefined_var will replace None to Undefinedvar(), to fix cases like:
         #       a = None
@@ -1371,7 +1371,7 @@ def check_ret_none(seq_true, seq_false, seq_names):
                     and f_true[idx] is not None
                 ):
                     warnings.warn(
-                        "In cond : Var '{}' or part of it is set differently in ifelse branchs, "
+                        "In cond : Var '{}' or part of it is set differently in ifelse branches, "
                         "<{}, {}> in true branch and <{}, {}> in false branch. Set var to "
                         "'None' in ifelse block might lead to error.".format(
                             f_name,
@@ -1388,7 +1388,7 @@ def check_ret_none(seq_true, seq_false, seq_names):
         _to_sequence_except_dict(return_names),
     )
 
-    if is_dy2staic:
+    if is_dy2static:
         true_output, false_output = change_none_to_undefinedvar(
             true_output, false_output
         )
@@ -1542,7 +1542,7 @@ def start_select_input():
             return select_input(inputs, mask)
         except Exception as e:
             raise RuntimeError(
-                f"Exceptions throwed while doing select_input on {name}:\n{e}"
+                f"Exceptions thrown while doing select_input on {name}:\n{e}"
             )
 
     if isinstance(false_var, UndefinedVar) and isinstance(
@@ -1640,7 +1640,7 @@ def map_fn(n1, n2, name, order):
             if n1 is None and n2 is not None:
                 if order == 0:
                     warnings.warn(
-                        "In cond : Var '{}' or part of it is set differently in ifelse branchs, "
+                        "In cond : Var '{}' or part of it is set differently in ifelse branches, "
                         "<{}, {}> in true branch and <{}, {}> in false branch. Set var to "
                         "'None' in ifelse block might lead to error.".format(
                             name, type(n1), n1, type(n2), n2
@@ -1648,7 +1648,7 @@ def map_fn(n1, n2, name, order):
                     )
                 else:
                     warnings.warn(
-                        "In cond : Var '{}' or part of it is set differently in ifelse branchs, "
+                        "In cond : Var '{}' or part of it is set differently in ifelse branches, "
                         "<{}, {}> in true branch and <{}, {}> in false branch. Set var to "
                         "'None' in ifelse block might lead to error.".format(
                             name, type(n2), n2, type(n1), n1
@@ -1726,7 +1726,7 @@ def Print(
         summarize (int, optional): Number of elements in the tensor to be print. If
                 it's value is -1, then all elements in the tensor will be print.
         print_tensor_name (bool, optional): Print the tensor name. Default: True.
-        print_tensor_type (bool, optional): Print the tensor type. Defaultt: True.
+        print_tensor_type (bool, optional): Print the tensor type. Default: True.
         print_tensor_shape (bool, optional): Print the tensor shape. Default: True.
         print_tensor_layout (bool, optional): Print the tensor layout. Default: True.
         print_tensor_lod (bool, optional): Print the tensor lod. Default: True.
diff --git a/python/paddle/static/quantization/cal_kl_threshold.py b/python/paddle/static/quantization/cal_kl_threshold.py
index c8101a892cfde..bf788d3070ea7 100644
--- a/python/paddle/static/quantization/cal_kl_threshold.py
+++ b/python/paddle/static/quantization/cal_kl_threshold.py
@@ -80,7 +80,7 @@ def safe_entropy(reference_distr_P, P_sum, candidate_distr_Q, Q_sum):
 
 def cal_kl_threshold(hist, bin_width, bits):
     '''
-    Using the KL-divergenc method to get the more precise threshold.
+    Using the KL-divergence method to get the more precise threshold.
 
     Args:
         hist(List): The hist of the tensor.
diff --git a/python/paddle/static/quantization/post_training_quantization.py b/python/paddle/static/quantization/post_training_quantization.py
index 9fa7188b05572..04b94655a4d83 100644
--- a/python/paddle/static/quantization/post_training_quantization.py
+++ b/python/paddle/static/quantization/post_training_quantization.py
@@ -112,7 +112,7 @@ def _apply_pass(
 
 class PostTrainingQuantization:
     """
-    Utilizing post training quantization methon to quantize the FP32 model,
+    Utilizing post training quantization method to quantize the FP32 model,
     and it uses calibrate data to get the quantization information for all
     quantized variables.
     """
@@ -168,14 +168,14 @@ def __init__(
                 When all parameters were saved in a single binary file, set it
                 as the real filename. If parameters were saved in separate files,
                 set it as 'None'. Default is 'None'.
-            batch_generator(Python Generator, depreceated): The batch generator provides
+            batch_generator(Python Generator, deprecated): The batch generator provides
                 calibrate data for DataLoader, and it returns a batch every
                 time. Note that, sample_generator and batch_generator, only one
-                should be set. Beisdes, batch_generator supports lod tensor.
-            sample_generator(Python Generator, depreceated): The sample generator provides
+                should be set. Besides, batch_generator supports lod tensor.
+            sample_generator(Python Generator, deprecated): The sample generator provides
                 calibrate data for DataLoader, and it only returns a sample every
                 time. Note that, sample_generator and batch_generator, only one
-                should be set. Beisdes, sample_generator dose not support lod tensor.
+                should be set. Besides, sample_generator dose not support lod tensor.
             data_loader(Paddle.io.DataLoader): The
                 Dataloader provides calibrate data, and it could
                 return a batch every time.
@@ -183,7 +183,7 @@ def __init__(
             batch_nums(int, optional): If batch_nums is not None, the number of
                 calibrate data is batch_size*batch_nums. If batch_nums is None, use
                 all data provided by sample_generator as calibrate data.
-            algo(str, optional): If algo='KL', use KL-divergenc method to
+            algo(str, optional): If algo='KL', use KL-divergence method to
                 get the KL threshold for quantized activations and get the abs_max
                 value for quantized weights. If algo='abs_max', get the abs max
                 value for activations and weights. If algo= 'min_max', get the min
@@ -327,7 +327,7 @@ def __init__(
         )
         assert (
             weight_quantize_type in self._support_weight_quantize_type
-        ), "The weight_quantize_type ({}) shoud in ({}).".format(
+        ), "The weight_quantize_type ({}) should in ({}).".format(
             weight_quantize_type, self._support_weight_quantize_type
         )
 
@@ -500,7 +500,7 @@ def quantize(self):
         self._reset_activation_persistable()
 
         if self._algo == 'min_max':
-            self._save_input_threhold()
+            self._save_input_threshold()
         else:
             self._update_program()
 
@@ -1055,7 +1055,7 @@ def _sample_ptf(self):
             threshold = q_max * scale
             self._quantized_threshold[var_name] = threshold
 
-    def _save_input_threhold(self):
+    def _save_input_threshold(self):
         '''
         Save input threshold to the quantized op.
         '''
@@ -1570,7 +1570,7 @@ class WeightQuantization:
     def __init__(self, model_dir, model_filename=None, params_filename=None):
         '''
         This class quantizes the weight of some ops to reduce the size of model
-        or improve the perforemace.
+        or improve the performance.
 
         Args:
             model_dir(str): The path of the fp32 model that will be quantized,
@@ -1625,7 +1625,7 @@ def quantize_weight_to_int(
                 as True, it saves a fake quantized model, in which the weights
                 are quantized and dequantized. We can use PaddlePaddle to load
                 the fake quantized model and test the accuracy on GPU or CPU.
-            threshold_rate(float, optional): This api uses abs_max methd to
+            threshold_rate(float, optional): This api uses abs_max method to
                 quantize the weight from float32 to int8/16, and the abs max
                 value is important for quantization diff. When the abs_max
                 value is far away from the center of the numerical distribution,
diff --git a/python/paddle/static/quantization/quanter.py b/python/paddle/static/quantization/quanter.py
index 7a71b05c6c189..86696fe82247f 100644
--- a/python/paddle/static/quantization/quanter.py
+++ b/python/paddle/static/quantization/quanter.py
@@ -97,13 +97,13 @@
     'quantize_op_types': ['conv2d', 'depthwise_conv2d', 'mul'],
     # data type after quantization, such as 'uint8', 'int8', etc. default is 'int8'
     'dtype': 'int8',
-    # window size for 'range_abs_max' quantization. defaulf is 10000
+    # window size for 'range_abs_max' quantization. default is 10000
     'window_size': 10000,
     # The decay coefficient of moving average, default is 0.9
     'moving_rate': 0.9,
     # if True, 'quantize_op_types' will be TENSORRT_OP_TYPES
     'for_tensorrt': False,
-    # if True, 'quantoze_op_types' will be TRANSFORM_PASS_OP_TYPES + QUANT_DEQUANT_PASS_OP_TYPES
+    # if True, 'quantize_op_types' will be TRANSFORM_PASS_OP_TYPES + QUANT_DEQUANT_PASS_OP_TYPES
     'is_full_quantize': False,
     # if True, use onnx format to quant.
     'onnx_format': True,
@@ -276,7 +276,7 @@ def quant_aware(
                 is non-quantized activation and function returns processed activation to be quantized. If None, the activation will
                 be quantized directly.
                 Default is None.
-        optimizer_func(function): Fuction return a optimizer. When 'is_test' is False and user want to use self-defined
+        optimizer_func(function): Function return a optimizer. When 'is_test' is False and user want to use self-defined
             quantization function and preprocess function, this function must be set. Default is None.
         exe(paddle.static.Executor): If user want to use self-defined quantization function and preprocess function, exe must be set for
                 initialization. Default is None.
diff --git a/python/paddle/static/quantization/quantization_pass.py b/python/paddle/static/quantization/quantization_pass.py
index 453637b36aeb2..efd158d92f3cc 100644
--- a/python/paddle/static/quantization/quantization_pass.py
+++ b/python/paddle/static/quantization/quantization_pass.py
@@ -300,10 +300,10 @@ def _transform_forward(graph, op):
 
                     # if var node is weight and weight_preprocess_func is not None,
                     # will insert weight preprocess func
-                    # to preorocess weight before quantization
+                    # to preprocess weight before quantization
                     # if var node is activation and act_preprocess_func is not None,
                     # will insert activation preprocess func
-                    # to preorocess activation before quantization
+                    # to preprocess activation before quantization
                     if is_weight and self._weight_preprocess_func is not None:
                         var_node = self._insert_func(
                             graph, self._weight_preprocess_func, var_node, op
@@ -2550,10 +2550,10 @@ def _transform_forward(self, graph, op):
 
                 # if var node is weight and weight_preprocess_func is not None,
                 # will insert weight preprocess func
-                # to preorocess weight before quantization
+                # to preprocess weight before quantization
                 # if var node is activation and act_preprocess_func is not None,
                 # will insert activation preprocess func
-                # to preorocess activation before quantization
+                # to preprocess activation before quantization
                 if is_weight and self._weight_preprocess_func is not None:
                     var_node = self._insert_func(
                         graph, self._weight_preprocess_func, var_node, op
@@ -2762,7 +2762,7 @@ def apply(self, graph):
             ):
                 self.persistable_cast_output_vars.append(op.outputs[0].name())
 
-        # Do the preproccess of quantization, such as skipping some ops
+        # Do the preprocess of quantization, such as skipping some ops
         # for not being quantized.
         for op in ops:
             if (
@@ -3364,7 +3364,7 @@ def apply(self, graph):
                         dequantized_vars_map[var_name] = dequant_var_node
                     dequant_node_map[var_name] = dequant_var_node
 
-        # remove unuse node and link act quant/dequant linear to op node
+        # remove unused node and link act quant/dequant linear to op node
         for op_node in graph.all_op_nodes():
             if op_node.name() == 'moving_average_abs_max_scale':
                 graph.safe_remove_nodes(op_node)
diff --git a/python/paddle/tensor/array.py b/python/paddle/tensor/array.py
index b5cc0912650bc..f5c9851074968 100644
--- a/python/paddle/tensor/array.py
+++ b/python/paddle/tensor/array.py
@@ -60,7 +60,7 @@ def array_length(array):
             or not array.is_dense_tensor_array_type()
         ):
             raise TypeError(
-                "array should be tensor array vairable in array_length Op"
+                "array should be tensor array variable in array_length Op"
             )
         return paddle._pir_ops.array_length(array)
     else:
@@ -69,7 +69,7 @@ def array_length(array):
             or array.type != core.VarDesc.VarType.LOD_TENSOR_ARRAY
         ):
             raise TypeError(
-                "array should be tensor array vairable in array_length Op"
+                "array should be tensor array variable in array_length Op"
             )
 
         helper = LayerHelper('array_length', **locals())
@@ -141,7 +141,7 @@ def array_read(array, i):
             or not array.is_dense_tensor_array_type()
         ):
             raise TypeError(
-                "array should be tensor array vairable in array_length Op"
+                "array should be tensor array variable in array_length Op"
             )
         return paddle._pir_ops.array_read(array, i)
     else:
@@ -151,7 +151,7 @@ def array_read(array, i):
             not isinstance(array, Variable)
             or array.type != core.VarDesc.VarType.LOD_TENSOR_ARRAY
         ):
-            raise TypeError("array should be tensor array vairable")
+            raise TypeError("array should be tensor array variable")
         out = helper.create_variable_for_type_inference(dtype=array.dtype)
         helper.append_op(
             type='read_from_array',
@@ -220,13 +220,13 @@ def array_write(x, i, array=None):
     elif in_pir_mode():
         check_variable_and_dtype(i, 'i', ['int64'], 'array_write')
         if not isinstance(x, paddle.pir.Value):
-            raise TypeError(f"x should be pir.Value, but recevied {type(x)}.")
+            raise TypeError(f"x should be pir.Value, but received {type(x)}.")
         if array is not None:
             if (
                 not isinstance(array, paddle.pir.Value)
                 or not array.is_dense_tensor_array_type()
             ):
-                raise TypeError("array should be tensor array vairable")
+                raise TypeError("array should be tensor array variable")
         if array is None:
             array = paddle._pir_ops.create_array(x.dtype)
 
@@ -242,7 +242,7 @@ def array_write(x, i, array=None):
                 or array.type != core.VarDesc.VarType.LOD_TENSOR_ARRAY
             ):
                 raise TypeError(
-                    "array should be tensor array vairable in array_write Op"
+                    "array should be tensor array variable in array_write Op"
                 )
         if array is None:
             array = helper.create_variable(
@@ -302,7 +302,7 @@ def create_array(dtype, initialized_list=None):
     for val in array:
         if not isinstance(val, (Variable, paddle.pir.Value)):
             raise TypeError(
-                "All values in `initialized_list` should be Variable or pir.Value, but recevied {}.".format(
+                "All values in `initialized_list` should be Variable or pir.Value, but received {}.".format(
                     type(val)
                 )
             )