!11281 fix bugs of op NPUClearFloatStatus, ApplyFtrl, SGD and so on

From: @lihongkang1
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui

mindspore/compression/common/constant.py

@@ -66,7 +66,7 @@ class QuantDtype(enum.Enum):
     @staticmethod
     def switch_signed(dtype):
         """
-        Swicth the signed state of the input quant datatype.
+        Switch the signed state of the input quant datatype.
 
         Args:
             dtype (QuantDtype): quant datatype.

mindspore/compression/quant/qat.py

@@ -43,10 +43,10 @@ def create_quant_config(quant_observer=(nn.FakeQuantWithMinMaxObserver, nn.FakeQ
                         symmetric=(False, False),
                         narrow_range=(False, False)):
     r"""
-    Configs the oberser type of weights and data flow with quant params.
+    Configs the observer type of weights and data flow with quant params.
 
     Args:
-        quant_observer (Observer, list or tuple): The oberser type to do quantization. The first element represent
+        quant_observer (Observer, list or tuple): The observer type to do quantization. The first element represent
             weights and second element represent data flow.
             Default: (nn.FakeQuantWithMinMaxObserver, nn.FakeQuantWithMinMaxObserver)
         quant_delay (int, list or tuple): Number of steps after which weights and activations are quantized during
@@ -64,7 +64,7 @@ def create_quant_config(quant_observer=(nn.FakeQuantWithMinMaxObserver, nn.FakeQ
             The first element represents weights and the second element represents data flow. Default: (False, False)
 
     Returns:
-        QuantConfig, Contains the oberser type of weight and activation.
+        QuantConfig, Contains the observer type of weight and activation.
     """
     weight_observer = quant_observer[0].partial_init(quant_delay=quant_delay[0], quant_dtype=quant_dtype[0],
                                                      per_channel=per_channel[0], symmetric=symmetric[0],

mindspore/compression/quant/quant_utils.py

@@ -273,7 +273,7 @@ def load_nonquant_param_into_quant_net(quant_model, params_dict, quant_new_param
     Args:
         quant_model: quantization model.
         params_dict: parameter dict that stores fp32 parameters.
-        quant_new_params: parameters that exist in quantative network but not in unquantative network.
+        quant_new_params: parameters that exist in quantitative network but not in unquantitative network.
 
     Returns:
         None

mindspore/context.py

@@ -452,7 +452,7 @@ def reset_auto_parallel_context():
 
 
 def _check_target_specific_cfgs(device, arg_key):
-    """Checking whether a config is sutable for a specified device"""
+    """Checking whether a config is suitable for a specified device"""
     device_cfgs = {
         'enable_auto_mixed_precision': ['Ascend'],
         'enable_dump': ['Ascend'],
@@ -545,7 +545,7 @@ def set_context(**kwargs):
             - op_trace: collect single operator performance data.
 
             The profiling can choose the combination of `training_trace`, `task_trace`,
-            `training_trace` and `task_trace` combination, and eparated by colons;
+            `training_trace` and `task_trace` combination, and separated by colons;
             a single operator can choose `op_trace`, `op_trace` cannot be combined with
             `training_trace` and `task_trace`. Default: "training_trace".
         check_bprop (bool): Whether to check bprop. Default: False.

mindspore/nn/layer/basic.py

@@ -553,7 +553,7 @@ class Pad(Cell):
         - If `mode` is "CONSTANT", it fills the edge with 0, regardless of the values of the `input_x`.
           If the `input_x` is [[1,2,3], [4,5,6], [7,8,9]] and `paddings` is [[1,1], [2,2]], then the
           Outputs is [[0,0,0,0,0,0,0], [0,0,1,2,3,0,0], [0,0,4,5,6,0,0], [0,0,7,8,9,0,0], [0,0,0,0,0,0,0]].
-        - If `mode` is "REFLECT", it uses a way of symmetrical copying throught the axis of symmetry to fill in.
+        - If `mode` is "REFLECT", it uses a way of symmetrical copying through the axis of symmetry to fill in.
           If the `input_x` is [[1,2,3], [4,5,6], [7,8,9]] and `paddings` is [[1,1], [2,2]], then the
           Outputs is [[6,5,4,5,6,5,4], [3,2,1,2,3,2,1], [6,5,4,5,6,5,4], [9,8,7,8,9,8,7], [6,5,4,5,6,5,4]].
         - If `mode` is "SYMMETRIC", the filling method is similar to the "REFLECT". It is also copied

mindspore/nn/layer/lstm.py

@@ -99,7 +99,7 @@ class LSTM(Cell):
           Data type of `hx` must be the same as `input`.
 
     Outputs:
-        Tuple, a tuple constains (`output`, (`h_n`, `c_n`)).
+        Tuple, a tuple contains (`output`, (`h_n`, `c_n`)).
 
         - **output** (Tensor) - Tensor of shape (seq_len, batch_size, num_directions * `hidden_size`).
         - **hx_n** (tuple) - A tuple of two Tensor (h_n, c_n) both of shape

mindspore/nn/layer/math.py

@@ -162,7 +162,7 @@ class Range(Cell):
 
 class LGamma(Cell):
     r"""
-    Calculates LGamma using Lanczos' approximation refering to "A Precision Approximationof the Gamma Function".
+    Calculates LGamma using Lanczos' approximation referring to "A Precision Approximation of the Gamma Function".
     The algorithm is:
 
     .. math::
@@ -291,7 +291,7 @@ class LGamma(Cell):
 
 class DiGamma(Cell):
     r"""
-    Calculates Digamma using Lanczos' approximation refering to "A Precision Approximationof the Gamma Function".
+    Calculates Digamma using Lanczos' approximation referring to "A Precision Approximation of the Gamma Function".
     The algorithm is:
 
     .. math::

mindspore/nn/layer/normalization.py

@@ -235,7 +235,7 @@ class BatchNorm1d(_BatchNorm):
 
     Note:
         The implementation of BatchNorm is different in graph mode and pynative mode, therefore the mode is not
-        recommended to be changed after net was initilized.
+        recommended to be changed after net was initialized.
 
     Args:
         num_features (int): `C` from an expected input of size (N, C).
@@ -322,7 +322,7 @@ class BatchNorm2d(_BatchNorm):
 
     Note:
         The implementation of BatchNorm is different in graph mode and pynative mode, therefore that mode can not be
-        changed after net was initilized.
+        changed after net was initialized.
         Note that the formula for updating the running_mean and running_var is
         :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times x_t + \text{momentum} \times \hat{x}`,
         where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the new observed value.

mindspore/nn/layer/quant.py

@@ -111,7 +111,7 @@ def _partial_init(cls_or_self, **kwargs):
     This can be useful when there is a need to create classes with the same
     constructor arguments, but different instances.
 
-    Example::
+    Examples:
         >>> Foo.partial_init = classmethod(_partial_init)
         >>> foo_builder = Foo.partial_init(a=3, b=4).partial_init(answer=42)
         >>> foo_instance1 = foo_builder()
@@ -365,7 +365,7 @@ class Conv2dBnFoldQuantOneConv(Cell):
         var_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the
             variance vector. Default: 'ones'.
         fake (bool): Whether Conv2dBnFoldQuant Cell adds FakeQuantWithMinMaxObserver. Default: True.
-        quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be
+        quant_config (QuantConfig): Configs the observer types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
             Default: both set to default FakeQuantWithMinMaxObserver.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
@@ -565,7 +565,7 @@ class Conv2dBnFoldQuant(Cell):
         var_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the
             variance vector. Default: 'ones'.
         fake (bool): Whether Conv2dBnFoldQuant Cell adds FakeQuantWithMinMaxObserver. Default: True.
-        quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be
+        quant_config (QuantConfig): Configs the observer types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
             Default: both set to default FakeQuantWithMinMaxObserver.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
@@ -743,7 +743,7 @@ class Conv2dBnWithoutFoldQuant(Cell):
         weight_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the convolution kernel.
             Default: 'normal'.
         bias_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the bias vector. Default: 'zeros'.
-        quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be
+        quant_config (QuantConfig): Configs the observer types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
             Default: both set to default FakeQuantWithMinMaxObserver.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
@@ -856,7 +856,7 @@ class Conv2dQuant(Cell):
         weight_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the convolution kernel.
             Default: 'normal'.
         bias_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the bias vector. Default: 'zeros'.
-        quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be
+        quant_config (QuantConfig): Configs the observer types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
             Default: both set to default FakeQuantWithMinMaxObserver.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
@@ -962,7 +962,7 @@ class DenseQuant(Cell):
         has_bias (bool): Specifies whether the layer uses a bias vector. Default: True.
         activation (Union[str, Cell, Primitive]): The regularization function applied to the output of the layer,
             eg. 'relu'. Default: None.
-        quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be
+        quant_config (QuantConfig): Configs the observer types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
             Default: both set to default FakeQuantWithMinMaxObserver.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
@@ -1073,7 +1073,7 @@ class ActQuant(_QuantActivation):
         ema (bool): The exponential Moving Average algorithm updates min and max. Default: False.
         ema_decay (float): Exponential Moving Average algorithm parameter. Default: 0.999.
         fake_before (bool): Whether add fake quantized operation before activation. Default: False.
-        quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be
+        quant_config (QuantConfig): Configs the observer types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
             Default: both set to default FakeQuantWithMinMaxObserver.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
@@ -1138,7 +1138,7 @@ class TensorAddQuant(Cell):
 
     Args:
         ema_decay (float): Exponential Moving Average algorithm parameter. Default: 0.999.
-        quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be
+        quant_config (QuantConfig): Configs the observer types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
             Default: both set to default FakeQuantWithMinMaxObserver.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
@@ -1190,7 +1190,7 @@ class MulQuant(Cell):
 
     Args:
         ema_decay (float): Exponential Moving Average algorithm parameter. Default: 0.999.
-        quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be
+        quant_config (QuantConfig): Configs the observer types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
             Default: both set to default FakeQuantWithMinMaxObserver.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.

mindspore/nn/metrics/metric.py

@@ -59,7 +59,7 @@ class Metric(metaclass=ABCMeta):
             data (numpy.array): Input data.
 
         Returns:
-            bool, return trun, if input data are one-hot encoding.
+            bool, return true, if input data are one-hot encoding.
         """
         if data.ndim > 1 and np.equal(data ** 2, data).all():
             shp = (data.shape[0],) + data.shape[2:]

mindspore/nn/optim/optimizer.py

@@ -260,7 +260,7 @@ class Optimizer(Cell):
         return gradients
 
     def _grad_sparse_indices_deduplicate(self, gradients):
-        """ In the case of using big operators, de duplicate the 'indexes' in gradients."""
+        """ In the case of using big operators, deduplicate the 'indexes' in gradients."""
         if self._target != 'CPU' and self._unique:
             gradients = self.map_(F.partial(_indices_deduplicate), gradients)
         return gradients

mindspore/nn/optim/rmsprop.py

@@ -78,7 +78,7 @@ class RMSProp(Optimizer):
     :math:`m_{t}` is moment, the delta of `w`, :math:`m_{t-1}` is the last moment of :math:`m_{t}`.
     :math:`\\rho` represents `decay`. :math:`\\beta` is the momentum term, represents `momentum`.
     :math:`\\epsilon` is a smoothing term to avoid division by zero, represents `epsilon`.
-    :math:`\\eta` is learning rate, represents `learning_rate`. :math:`\\nabla Q_{i}(w)` is gradientse,
+    :math:`\\eta` is learning rate, represents `learning_rate`. :math:`\\nabla Q_{i}(w)` is gradients,
     represents `gradients`.
 
     Note:

mindspore/nn/probability/bijector/bijector.py

@@ -253,7 +253,7 @@ class Bijector(Cell):
         If args[0] is a distribution instance, the call will generate a new distribution derived from
         the input distribution.
         Otherwise, input[0] must be the name of a Bijector function, e.g. "forward", then this call will
-        go in the construct and invoke the correstpoding Bijector function.
+        go in the construct and invoke the corresponding Bijector function.
 
         Args:
             *args: args[0] shall be either a distribution or the name of a Bijector function.

mindspore/nn/probability/distribution/_utils/custom_ops.py

@@ -12,14 +12,14 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # ============================================================================
-"""Utitly functions to help distribution class."""
+"""Utility functions to help distribution class."""
 import numpy as np
 from mindspore.ops import operations as P
 from mindspore.common import dtype as mstype
 
 def exp_generic(input_x):
     """
-    Log op on Ascend doesn't supprot int types.
+    Log op on Ascend doesn't support int types.
     Fix this with casting the type.
     """
     exp = P.Exp()
@@ -36,7 +36,7 @@ def log_generic(input_x):
     """
     Log op on Ascend is calculated as log(abs(x)).
     Fix this with putting negative values as nan.
-    And log op on Ascend doesn't supprot int types.
+    And log op on Ascend doesn't support int types.
     Fix this with casting the type.
     """
     log = P.Log()

mindspore/nn/probability/distribution/_utils/utils.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # ============================================================================
-"""Utitly functions to help distribution class."""
+"""Utility functions to help distribution class."""
 import numpy as np
 from mindspore import context
 from mindspore._checkparam import Validator as validator

mindspore/nn/probability/distribution/beta.py

@@ -52,7 +52,7 @@ class Beta(Distribution):
         >>> from mindspore import Tensor
         >>> # To initialize a Beta distribution of the concentration1 3.0 and the concentration0 4.0.
         >>> b1 = msd.Beta([3.0], [4.0], dtype=mindspore.float32)
-        >>> # A Beta distribution can be initilized without arguments.
+        >>> # A Beta distribution can be initialized without arguments.
         >>> # In this case, `concentration1` and `concentration0` must be passed in through arguments.
         >>> b2 = msd.Beta(dtype=mindspore.float32)
         >>> # Here are some tensors used below for testing

mindspore/nn/probability/distribution/gamma.py

@@ -52,7 +52,7 @@ class Gamma(Distribution):
         >>> from mindspore import Tensor
         >>> # To initialize a Gamma distribution of the concentration 3.0 and the rate 4.0.
         >>> g1 = msd.Gamma([3.0], [4.0], dtype=mindspore.float32)
-        >>> # A Gamma distribution can be initilized without arguments.
+        >>> # A Gamma distribution can be initialized without arguments.
         >>> # In this case, `concentration` and `rate` must be passed in through arguments.
         >>> g2 = msd.Gamma(dtype=mindspore.float32)
         >>> # Here are some tensors used below for testing

mindspore/nn/probability/distribution/geometric.py

@@ -26,8 +26,9 @@ from ._utils.custom_ops import exp_generic, log_generic
 class Geometric(Distribution):
     """
     Geometric Distribution.
-    It represents that there are k failures before the first sucess, namely taht there are in total k+1 Bernoulli trials
-    when the first success is achieved.
+
+    It represents that there are k failures before the first success, namely that there are in total k+1 Bernoulli
+    trials when the first success is achieved.
 
     Args:
         probs (float, list, numpy.ndarray, Tensor): The probability of success.

mindspore/nn/probability/distribution/log_normal.py

@@ -235,7 +235,7 @@ class LogNormal(msd.TransformedDistribution):
 
     def _var(self, loc=None, scale=None):
         """
-        The varience of the distribution.
+        The variance of the distribution.
         """
         mean, sd = self._check_param_type(loc, scale)
         var = self.distribution("var", mean=mean, sd=sd)

mindspore/nn/probability/distribution/poisson.py

@@ -48,7 +48,7 @@ class Poisson(Distribution):
         >>> from mindspore import Tensor
         >>> # To initialize an Poisson distribution of the rate 0.5.
         >>> p1 = msd.Poisson([0.5], dtype=mindspore.float32)
-        >>> # An Poisson distribution can be initilized without arguments.
+        >>> # An Poisson distribution can be initialized without arguments.
         >>> # In this case, `rate` must be passed in through `args` during function calls.
         >>> p2 = msd.Poisson(dtype=mindspore.float32)
         >>>

mindspore/nn/probability/distribution/transformed_distribution.py

@@ -33,7 +33,7 @@ class TransformedDistribution(Distribution):
         bijector (Bijector): The transformation to perform.
         distribution (Distribution): The original distribution. Must has a float dtype.
         seed (int): The seed is used in sampling. The global seed is used if it is None. Default:None.
-          If this seed is given when a TransformedDistribution object is initialised, the object's sampling function
+          If this seed is given when a TransformedDistribution object is initialized, the object's sampling function
           will use this seed; elsewise, the underlying distribution's seed will be used.
         name (str): The name of the transformed distribution. Default: 'transformed_distribution'.
 

mindspore/nn/probability/distribution/uniform.py

@@ -240,7 +240,7 @@ class Uniform(Distribution):
 
     def _cross_entropy(self, dist, low_b, high_b, low=None, high=None):
         """
-        Evaluate cross entropy between Uniform distributoins.
+        Evaluate cross entropy between Uniform distributions.
 
         Args:
             dist (str): The type of the distributions. Should be "Uniform" in this case.

mindspore/ops/composite/multitype_ops/div_impl.py

@@ -33,7 +33,7 @@ def _div_scalar(x, y):
 
     Args:
        x (Number): x
-       y (NUmber): y
+       y (Number): y
 
     Returns:
        Number, equal to x / y, the type is same as x.

mindspore/ops/composite/multitype_ops/equal_impl.py

@@ -48,7 +48,7 @@ def _equal_scalar(x, y):
 
     Args:
        x (Number): first input number.
-       y (NUmber): second input number.
+       y (Number): second input number.
 
     Returns:
        bool, if x == y return true, x != y return false.

mindspore/ops/composite/multitype_ops/getitem_impl.py

@@ -194,7 +194,7 @@ def _tensor_getitem_by_slice(data, slice_index):
 @getitem.register("Tensor", "Tensor")
 def _tensor_getitem_by_tensor(data, tensor_index):
     """
-    Getting item of tensor by tensor indice.
+    Getting item of tensor by tensor indices.
 
     Inputs:
         data (Tensor): A tensor.

mindspore/ops/composite/multitype_ops/mul_impl.py

@@ -62,7 +62,7 @@ def _scalar_mul_tensor(x, y):
 @mul.register("Tensor", "Number")
 def _tensor_mul_scalar(x, y):
     """
-    Returns x * y where x is a tensor and y is a scalar. x and y hava same dtype.
+    Returns x * y where x is a tensor and y is a scalar. x and y have same dtype.
 
     Outputs:
         Tensor, has the same dtype as x.

mindspore/ops/composite/multitype_ops/not_equal_impl.py

@@ -33,7 +33,7 @@ def _not_equal_scalar(x, y):
 
     Args:
        x (Number): x
-       y (NUmber): y
+       y (Number): y
 
     Returns:
        bool, if x != y return true, x == y return false.
@@ -123,7 +123,7 @@ def _none_not_equal_scalar(x, y):
 
     Args:
        x: None.
-       y: NUmber.
+       y: Number.
 
     Returns:
        bool, return True.

mindspore/ops/composite/multitype_ops/setitem_impl.py

@@ -28,7 +28,7 @@ def _list_setitem_with_string(data, number_index, value):
     Assigns value to list.
 
     Inputs:
-        data (list): Data of type lis.
+        data (list): Data of type list.
         number_index (Number): Index of data.
 
     Outputs:
@@ -43,7 +43,7 @@ def _list_setitem_with_number(data, number_index, value):
     Assigns value to list.
 
     Inputs:
-        data (list): Data of type lis.
+        data (list): Data of type list.
         number_index (Number): Index of data.
         value (Number): Value given.
 
@@ -59,7 +59,7 @@ def _list_setitem_with_Tensor(data, number_index, value):
     Assigns value to list.
 
     Inputs:
-        data (list): Data of type lis.
+        data (list): Data of type list.
         number_index (Number): Index of data.
         value (Tensor): Value given.
 
@@ -75,7 +75,7 @@ def _list_setitem_with_List(data, number_index, value):
     Assigns value to list.
 
     Inputs:
-        data (list): Data of type lis.
+        data (list): Data of type list.
         number_index (Number): Index of data.
         value (list): Value given.
 
@@ -91,7 +91,7 @@ def _list_setitem_with_Tuple(data, number_index, value):
     Assigns value to list.
 
     Inputs:
-        data (list): Data of type lis.
+        data (list): Data of type list.
         number_index (Number): Index of data.
         value (list): Value given.
 

mindspore/ops/composite/random_ops.py

@@ -81,7 +81,7 @@ def laplace(shape, mean, lambda_param, seed=None):
         shape (tuple): The shape of random tensor to be generated.
         mean (Tensor): The mean μ distribution parameter, which specifies the location of the peak.
           With float32 data type.
-        lambda_param (Tensor): The parameter used for controling the variance of this random distribution. The
+        lambda_param (Tensor): The parameter used for controlling the variance of this random distribution. The
           variance of Laplace distribution is equal to twice the square of lambda_param. With float32 data type.
         seed (int): Seed is used as entropy source for Random number engines generating pseudo-random numbers.
           Default: None, which will be treated as 0.

mindspore/ops/operations/array_ops.py

@@ -141,7 +141,6 @@ class ExpandDims(PrimitiveWithInfer):
 
     Inputs:
         - **input_x** (Tensor) - The shape of tensor is :math:`(x_1, x_2, ..., x_R)`.
-          The data type should be one of the following types: int32, float16, float32.
         - **axis** (int) - Specifies the dimension index at which to expand
           the shape of `input_x`. The value of axis must be in the range
           `[-input_x.ndim-1, input_x.ndim]`. Only constant value is allowed.
@@ -939,7 +938,7 @@ class Split(PrimitiveWithCheck):
 
     Args:
         axis (int): Index of the split position. Default: 0.
-        output_num (int): The number of output tensors. Must be postive int. Default: 1.
+        output_num (int): The number of output tensors. Must be positive int. Default: 1.
 
     Raises:
         ValueError: If `axis` is out of the range [-len(`input_x.shape`), len(`input_x.shape`)),
@@ -1466,7 +1465,7 @@ class InvertPermutation(PrimitiveWithInfer):
         - **input_x** (Union(tuple[int], list[int]) - The input is constructed by multiple
           integers, i.e., :math:`(y_1, y_2, ..., y_S)` representing the indices.
           The values must include 0. There can be no duplicate values or negative values.
-          Only constant value is allowed. The maximum value msut be equal to length of input_x.
+          Only constant value is allowed. The maximum value must be equal to length of input_x.
 
     Outputs:
         tuple[int]. It has the same length as the input.
@@ -1927,7 +1926,7 @@ class UnsortedSegmentMin(PrimitiveWithCheck):
           The data type must be float16, float32 or int32.
         - **segment_ids** (Tensor) - A `1-D` tensor whose shape is :math:`(x_1)`, the value must be >= 0.
           The data type must be int32.
-        - **num_segments** (int) - The value spcifies the number of distinct `segment_ids`.
+        - **num_segments** (int) - The value specifies the number of distinct `segment_ids`.
 
     Note:
         If the segment_id i is absent in the segment_ids, then output[i] will be filled with
@@ -1983,7 +1982,7 @@ class UnsortedSegmentMax(PrimitiveWithCheck):
           The data type must be float16, float32 or int32.
         - **segment_ids** (Tensor) - A `1-D` tensor whose shape is :math:`(x_1)`, the value must be >= 0.
           The data type must be int32.
-        - **num_segments** (int) - The value spcifies the number of distinct `segment_ids`.
+        - **num_segments** (int) - The value specifies the number of distinct `segment_ids`.
 
     Note:
         If the segment_id i is absent in the segment_ids, then output[i] will be filled with
@@ -2040,7 +2039,7 @@ class UnsortedSegmentProd(PrimitiveWithInfer):
           With float16, float32 or int32 data type.
         - **segment_ids** (Tensor) - A `1-D` tensor whose shape is :math:`(x_1)`, the value must be >= 0.
           Data type must be int32.
-        - **num_segments** (int) - The value spcifies the number of distinct `segment_ids`,
+        - **num_segments** (int) - The value specifies the number of distinct `segment_ids`,
           must be greater than 0.
 
     Outputs:
@@ -2505,7 +2504,7 @@ class Select(PrimitiveWithInfer):
 
     If neither is None, :math:`x` and :math:`y` must have the same shape. If :math:`x` and :math:`y` are
     scalars, the conditional tensor must be a scalar. If :math:`x` and :math:`y` are
-    higher-demensional vectors, the `condition` must be a vector whose size matches the
+    higher-dimensional vectors, the `condition` must be a vector whose size matches the
     first dimension of :math:`x`, or must have the same shape as :math:`y`.
 
     The conditional tensor acts as an optional compensation (mask), which
@@ -2513,7 +2512,7 @@ class Select(PrimitiveWithInfer):
     selected from :math:`x` (if true) or :math:`y` (if false) based on the value of each
     element.
 
-    If condition is a vector, then :math:`x` and :math:`y` are higher-demensional matrices, then it
+    If condition is a vector, then :math:`x` and :math:`y` are higher-dimensional matrices, then it
     chooses to copy that row (external dimensions) from :math:`x` and :math:`y`. If condition has
     the same shape as :math:`x` and :math:`y`, you can choose to copy these elements from :math:`x`
     and :math:`y`.
@@ -2629,7 +2628,7 @@ class StridedSlice(PrimitiveWithInfer):
 
     Given an input tensor, this operation inserts a dimension of length 1 at the dimension.
     This operation extracts a fragment of size (end-begin)/stride from the given 'input_tensor'.
-    Starting from the begining position, the fragment continues adding stride to the index until
+    Starting from the beginning position, the fragment continues adding stride to the index until
     all dimensions are not less than the ending position.
 
     Note:
@@ -3906,7 +3905,7 @@ class SpaceToBatchND(PrimitiveWithInfer):
 
     Args:
         block_shape (Union[list(int), tuple(int)]): The block shape of dividing block with all value greater than 1.
-            The length of `block_shape` is M correspoding to the number of spatial dimensions. M must be 2.
+            The length of `block_shape` is M corresponding to the number of spatial dimensions. M must be 2.
         paddings (Union[tuple, list]): The padding values for H and W dimension, containing 2 subtraction list.
             Each contains 2 integer value. All values must be greater than 0.
             `paddings[i]` specifies the paddings for the spatial dimension i,
@@ -4005,7 +4004,7 @@ class BatchToSpaceND(PrimitiveWithInfer):
 
     Args:
         block_shape (Union[list(int), tuple(int)]): The block shape of dividing block with all value >= 1.
-            The length of block_shape is M correspoding to the number of spatial dimensions. M must be 2.
+            The length of block_shape is M corresponding to the number of spatial dimensions. M must be 2.
         crops (Union[list(int), tuple(int)]): The crop value for H and W dimension, containing 2 subtraction list,
             each containing 2 int value.
             All values must be >= 0. crops[i] specifies the crop values for spatial dimension i, which corresponds to
@@ -4404,7 +4403,7 @@ class ReverseSequence(PrimitiveWithInfer):
 
 class EditDistance(PrimitiveWithInfer):
     """
-    Computes the Levebshtein Edit Distance. It is used to measure the similarity of two sequences. The inputs are
+    Computes the Levenshtein Edit Distance. It is used to measure the similarity of two sequences. The inputs are
     variable-length sequences provided by SparseTensors (hypothesis_indices, hypothesis_values, hypothesis_shape)
     and (truth_indices, truth_values, truth_shape).
 

mindspore/ops/operations/math_ops.py

@@ -1309,7 +1309,7 @@ class SquaredDifference(_MathBinaryOp):
         - **input_x** (Union[Tensor, Number, bool]) - The first input is a number, or a bool,
           or a tensor whose data type is float16, float32, int32 or bool.
         - **input_y** (Union[Tensor, Number, bool]) - The second input is a number, or a bool when the first input
-          is a tensor or a tensor whose data type isfloat16, float32, int32 or bool.
+          is a tensor or a tensor whose data type is float16, float32, int32 or bool.
 
     Outputs:
         Tensor, the shape is the same as the one after broadcasting,
@@ -3036,7 +3036,7 @@ class IsInf(PrimitiveWithInfer):
 
 class IsFinite(PrimitiveWithInfer):
     """
-    Deternubes which elements are finite for each position.
+    Determines which elements are finite for each position.
 
     Inputs:
         - **input_x** (Tensor) - The input tensor.
@@ -3160,6 +3160,8 @@ class NPUGetFloatStatus(PrimitiveWithInfer):
         >>> get_status = ops.NPUGetFloatStatus()
         >>> init = alloc_status()
         >>> get_status(init)
+        Tensor(shape=[8], dtype=Float32, value= [ 0.00000000e+00,  0.00000000e+00,  0.00000000e+00,  0.00000000e+00,
+          0.00000000e+00,  0.00000000e+00,  0.00000000e+00,  0.00000000e+00])
         >>> print(init)
         [1. 1. 1. 1. 1. 1. 1. 1.]
     """
@@ -3207,6 +3209,8 @@ class NPUClearFloatStatus(PrimitiveWithInfer):
         >>> init = alloc_status()
         >>> flag = get_status(init)
         >>> clear_status(init)
+        Tensor(shape=[8], dtype=Float32, value= [ 0.00000000e+00,  0.00000000e+00,  0.00000000e+00,  0.00000000e+00,
+          0.00000000e+00,  0.00000000e+00,  0.00000000e+00,  0.00000000e+00])
         >>> print(init)
         [1. 1. 1. 1. 1. 1. 1. 1.]
     """

mindspore/ops/operations/nn_ops.py

@@ -2013,7 +2013,8 @@ class TopK(PrimitiveWithInfer):
         >>> k = 3
         >>> values, indices = topk(input_x, k)
         >>> print((values, indices))
-        ([5.0, 4.0, 3.0], [4, 3, 2])
+        (Tensor(shape=[3], dtype=Float16, value= [ 5.0000e+00,  4.0000e+00,  3.0000e+00]), Tensor(shape=[3],
+          dtype=Int32, value= [4, 3, 2]))
     """
 
     @prim_attr_register
@@ -2217,7 +2218,7 @@ class ApplyMomentum(PrimitiveWithInfer):
     Data type conversion of Parameter is not supported. RuntimeError exception will be thrown.
 
     Args:
-        use_locking (bool): Whether to enable a lock to protect the variable and accumlation tensors
+        use_locking (bool): Whether to enable a lock to protect the variable and accumulation tensors
                             from being updated. Default: False.
         use_nesterov (bool): Enable Nesterov momentum. Default: False.
         gradient_scale (float): The scale of the gradient. Default: 1.0.
@@ -2513,7 +2514,7 @@ class SGD(PrimitiveWithCheck):
         >>> stat = Tensor(np.array([1.5, -0.3, 0.2, -0.7]), mindspore.float32)
         >>> output = sgd(parameters, gradient, learning_rate, accum, momentum, stat)
         >>> print(output[0])
-        [ 1.9899   -0.4903   1.6952001  3.9801   ]
+        (Tensor(shape=[4], dtype=Float32, value= [ 1.98989999e+00, -4.90300000e-01,  1.69520009e+00,  3.98009992e+00]),)
     """
 
     @prim_attr_register
@@ -5759,7 +5760,7 @@ class ApplyProximalGradientDescent(PrimitiveWithInfer):
 
     Inputs:
         - **var** (Parameter) - Variable tensor to be updated. With float32 or float16 data type.
-        - **alpha** (Union[Number, Tensor]) - Saling factor, must be a scalar. With float32 or float16 data type.
+        - **alpha** (Union[Number, Tensor]) - Scaling factor, must be a scalar. With float32 or float16 data type.
         - **l1** (Union[Number, Tensor]) - l1 regularization strength, must be scalar.
           With float32 or float16 data type.
         - **l2** (Union[Number, Tensor]) - l2 regularization strength, must be scalar.
@@ -5951,7 +5952,7 @@ class ApplyFtrl(PrimitiveWithInfer):
 
         There is only one output for GPU environment.
 
-        - **var** (Tensor) - This value is alwalys zero and the input parameters has been updated in-place.
+        - **var** (Tensor) - This value is always zero and the input parameters has been updated in-place.
 
     Supported Platforms:
         ``Ascend`` ``GPU``
@@ -5994,7 +5995,7 @@ class ApplyFtrl(PrimitiveWithInfer):
          [ 1.43758726e+00,  9.89177322e+00]]), Tensor(shape=[2, 2], dtype=Float32, value=
         [[-1.86994812e+03, -1.64906018e+03],
          [-3.22187836e+02, -1.20163989e+03]]))
-         >>> else:
+         ... else:
          ...    print(net.var.asnumpy())
          [[0.4614181  0.5309642 ]
           [0.2687151  0.38206503]]
@@ -6321,6 +6322,7 @@ class CTCLoss(PrimitiveWithInfer):
         ``Ascend`` ``GPU``
 
     Examples:
+        >>> np.random.seed(0)
         >>> inputs = Tensor(np.random.random((2, 2, 3)), mindspore.float32)
         >>> labels_indices = Tensor(np.array([[0, 0], [1, 0]]), mindspore.int64)
         >>> labels_values = Tensor(np.array([2, 2]), mindspore.int32)
@@ -6328,12 +6330,12 @@ class CTCLoss(PrimitiveWithInfer):
         >>> ctc_loss = ops.CTCLoss()
         >>> loss, gradient = ctc_loss(inputs, labels_indices, labels_values, sequence_length)
         >>> print(loss)
-        [ 0.69121575  0.5381993 ]
+        [ 0.7864997  0.720426 ]
         >>> print(gradient)
-        [[[ 0.25831494  0.3623634  -0.62067937 ]
-          [ 0.25187883  0.2921483  -0.5440271 ]]
-         [[ 0.43522435  0.24408469  0.07787037 ]
-          [ 0.29642645  0.4232373   0.06138104 ]]]
+        [[[ 0.30898064  0.36491138  -0.673892  ]
+          [ 0.33421117  0.2960548  -0.63026595 ]]
+         [[ 0.23434742  0.36907154  0.11261538 ]
+          [ 0.27316454  0.41090325  0.07584976 ]]]
     """
 
     @prim_attr_register

mindspore/ops/operations/other_ops.py

@@ -564,7 +564,7 @@ class PopulationCount(PrimitiveWithInfer):
         - **input** (Tensor) -  The data type must be int16 or uint16.
 
     Outputs:
-        Tensor, with the sam  shape as the input.
+        Tensor, with the same shape as the input.
 
     Supported Platforms:
         ``Ascend``

mindspore/train/serialization.py

@@ -513,11 +513,11 @@ def export(net, *inputs, file_name, file_format='AIR', **kwargs):
         file_name (str): File name of the model to be exported.
         file_format (str): MindSpore currently supports 'AIR', 'ONNX' and 'MINDIR' format for exported model.
 
-            - AIR: Ascend Intermidiate Representation. An intermidiate representation format of Ascend model.
+            - AIR: Ascend Intermediate Representation. An intermediate representation format of Ascend model.
               Recommended suffix for output file is '.air'.
             - ONNX: Open Neural Network eXchange. An open format built to represent machine learning models.
               Recommended suffix for output file is '.onnx'.
-            - MINDIR: MindSpore Native Intermidiate Representation for Anf. An intermidiate representation format
+            - MINDIR: MindSpore Native Intermediate Representation for Anf. An intermediate representation format
               for MindSpore models.
               Recommended suffix for output file is '.mindir'.