!15358 Some API comments of mindspore should be fixed

From: @zhang_yi2020
Reviewed-by: @gemini524,@liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui,@wuxuejian

mindspore/compression/common/constant.py

@@ -24,7 +24,7 @@ __all__ = ["QuantDtype"]
 @enum.unique
 class QuantDtype(enum.Enum):
     """
-    An enum for quant datatype, contains `INT2`~`INT8`, `UINT2`~`UINT8`.
+    An enum for quant datatype, contains `INT2` ~ `INT8`, `UINT2` ~ `UINT8`.
     """
     INT2 = "INT2"
     INT3 = "INT3"

mindspore/dataset/transforms/py_transforms.py

@@ -137,6 +137,7 @@ class Compose:
     def reduce(operations):
         """
         Wraps adjacent Python operations in a Compose to allow mixing of Python and C++ operations
+
         Args:
             operations (list): list of tensor operations
 

mindspore/explainer/_image_classification_runner.py

@@ -236,7 +236,7 @@ class ImageClassificationRunner:
         """
         Register uncertainty instance to compute the epistemic uncertainty base on the Bayes' theorem.
 
-        Notes:
+        Note:
             Please refer to the documentation of mindspore.nn.probability.toolbox.uncertainty_evaluation for the
             details. The actual output is standard deviation of the classification predictions and the corresponding
             95% confidence intervals. Users have to invoke register_saliency() as well for the uncertainty results are

mindspore/nn/layer/quant.py

@@ -1288,7 +1288,7 @@ class MulQuant(Cell):
         ema_decay (float): Exponential Moving Average algorithm parameter. Default: 0.999.
         quant_config (QuantConfig): Configures the oberser types and quant settings of weight and activation. Can be
             generated by compression.quant.create_quant_config method.
-            Default: both set to default FakeQuantWithMinMaxObserver.
+            Default: both set to default :class:`FakeQuantWithMinMaxObserver`.
         quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
 
     Inputs:

mindspore/nn/metrics/hausdorff_distance.py

@@ -258,7 +258,7 @@ class HausdorffDistance(Metric):
                     predicted binary image. 'y' is the actual binary image. 'label_idx', the data type of `label_idx`
                     is int.
 
-         Raises:
+        Raises:
             ValueError: If the number of the inputs is not 3.
         """
         self._is_update = True

mindspore/nn/metrics/mean_surface_distance.py

@@ -93,7 +93,7 @@ class MeanSurfaceDistance(Metric):
                     predicted binary image. 'y' is the actual binary image. 'label_idx', the data type of `label_idx`
                     is int.
 
-         Raises:
+        Raises:
             ValueError: If the number of the inputs is not 3.
         """
         if len(inputs) != 3:

mindspore/nn/metrics/root_mean_square_surface_distance.py

@@ -95,7 +95,7 @@ class RootMeanSquareDistance(Metric):
                     predicted binary image. 'y' is the actual binary image. 'label_idx', the data type of `label_idx`
                     is int.
 
-         Raises:
+        Raises:
             ValueError: If the number of the inputs is not 3.
         """
         if len(inputs) != 3:

mindspore/nn/metrics/topk.py

@@ -96,7 +96,7 @@ class TopKCategoricalAccuracy(Metric):
 class Top1CategoricalAccuracy(TopKCategoricalAccuracy):
     """
     Calculates the top-1 categorical accuracy. This class is a specialized class for TopKCategoricalAccuracy.
-    Refer to class 'TopKCategoricalAccuracy' for more details.
+    Refer to :class:`TopKCategoricalAccuracy` for more details.
 
     Examples:
         >>> x = Tensor(np.array([[0.2, 0.5, 0.3, 0.6, 0.2], [0.1, 0.35, 0.5, 0.2, 0.],
@@ -116,7 +116,7 @@ class Top1CategoricalAccuracy(TopKCategoricalAccuracy):
 class Top5CategoricalAccuracy(TopKCategoricalAccuracy):
     """
     Calculates the top-5 categorical accuracy. This class is a specialized class for TopKCategoricalAccuracy.
-    Refer to class 'TopKCategoricalAccuracy' for more details.
+    Refer to :class:`TopKCategoricalAccuracy` for more details.
 
     Examples:
         >>> x = Tensor(np.array([[0.2, 0.5, 0.3, 0.6, 0.2], [0.1, 0.35, 0.5, 0.2, 0.],

mindspore/nn/optim/sgd.py

@@ -52,7 +52,7 @@ class SGD(Optimizer):
     .. math::
             p_{t+1} = p_{t} - lr \ast v_{t+1}
 
-    To be noticed, for the first step, v_{t+1} = gradient
+    To be noticed, for the first step, :math:`v_{t+1} = gradient`
 
     Here : where p, v and u denote the parameters, accum, and momentum respectively.
 

mindspore/nn/probability/bijector/bijector.py

@@ -44,7 +44,7 @@ class Bijector(Cell):
         has to be float type. During initialization, when `dtype` is None, there is no enforcement on the dtype
         of the parameters. All parameters should have the same float type, otherwise a TypeError will be raised.
         Specifically, the parameter type will follow the dtype of the input value, i.e. parameters of the bijector
-        will be casted into the same type as input value when `dtype`is None.
+        will be casted into the same type as input value when `dtype` is None.
         When `dtype` is specified, it is forcing the parameters and input value to be the same dtype as `dtype`.
         When the type of parameters or the type of the input value is not the same as `dtype`, a TypeError will be
         raised. Only subtype of mindspore.float_type can be used to specify bijector's `dtype`.

mindspore/nn/wrap/cell_wrapper.py

@@ -222,8 +222,8 @@ class ForwardValueAndGrad(Cell):
     Inputs:
         - **(\*inputs)** (Tuple(Tensor...)) - Tuple of inputs with shape :math:`(N, \ldots)`.
         - **(sens)** - A sensitivity (gradient with respect to output) as the input of backpropagation.
-            If network has single output, the sens is a tensor.
-            If network has multiple outputs, the sens is the tuple(tensor).
+          If network has single output, the sens is a tensor.
+          If network has multiple outputs, the sens is the tuple(tensor).
 
     Outputs:
         - **forward value** - The result of network forward running.

mindspore/numpy/array_creations.py

@@ -181,7 +181,7 @@ def asfarray(a, dtype=mstype.float32):
     If non-float dtype is defined, this function will return a float32 tensor instead.
 
     Args:
-       a (Union[int, float, bool, list, tuple, Tensor]): Input data, in any form that can
+        a (Union[int, float, bool, list, tuple, Tensor]): Input data, in any form that can
             be converted to a `Tensor`. This includes Tensor, list, tuple and numbers.
         dtype (Union[:class:`mindspore.dtype`, str], optional): Designated tensor dtype, can
             be in format of np.int32, or \'int32\'. If dtype is :class:`None`, the data type

mindspore/numpy/math_ops.py

@@ -726,6 +726,7 @@ def outer(a, b):
 
     Given two vectors, ``a = [a0, a1, ..., aM]`` and ``b = [b0, b1, ..., bN]``,
     the outer product is:
+
     ``[[a0*b0  a0*b1 ... a0*bN ]``
 
     ``[a1*b0    .              ]``

mindspore/ops/composite/base.py

@@ -111,6 +111,7 @@ class GradOperation(GradOperation_):
     Given an input function `net = Net()` that takes `x` and `y` as inputs, and has a parameter `z`,
     see `Net` in Examples.
 
+
     To generate a gradient function that returns gradients with respect to the first input
     (see `GradNetWrtX` in Examples).
 
@@ -122,6 +123,7 @@ class GradOperation(GradOperation_):
     3. Call the gradient function with input function's inputs to get the gradients with respect to the first input:
        `grad_op(net)(x, y)`.
 
+
     To generate a gradient function that returns gradients with respect to all inputs (see `GradNetWrtXY` in Examples).
 
     1. Construct a `GradOperation` higher-order function with `get_all=True` which
@@ -164,6 +166,7 @@ class GradOperation(GradOperation_):
     4. Call the gradient function with input function's inputs
        to get the gradients with respect to all inputs and given parameters: `gradient_function(x, y)`.
 
+
     We can configure the sensitivity(gradient with respect to output) by setting `sens_param` as True and
     passing an extra sensitivity input to the gradient function, the sensitivity input should has the
     same shape and type with input function's output(see `GradNetWrtXYWithSensParam` in Examples).

mindspore/ops/operations/nn_ops.py

@@ -2746,9 +2746,9 @@ class ApplyRMSProp(PrimitiveWithInfer):
     where :math:`w` represents `var`, which will be updated.
     :math:`s_{t}` represents `mean_square`, :math:`s_{t-1}` is the last momentent of :math:`s_{t}`,
     :math:`m_{t}` represents `moment`, :math:`m_{t-1}` is the last momentent 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` represents `learning_rate`. :math:`\\nabla Q_{i}(w)` represents `grad`.
+    :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` represents `learning_rate`. :math:`\nabla Q_{i}(w)` represents `grad`.
 
     Args:
         use_locking (bool): Whether to enable a lock to protect the variable and accumlation tensors
@@ -2844,9 +2844,9 @@ class ApplyCenteredRMSProp(PrimitiveWithInfer):
     :math:`g_{t}` represents `mean_gradient`, :math:`g_{t-1}` is the last momentent of :math:`g_{t}`.
     :math:`s_{t}` represents `mean_square`, :math:`s_{t-1}` is the last momentent of :math:`s_{t}`,
     :math:`m_{t}` represents `moment`, :math:`m_{t-1}` is the last momentent 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` represents `learning_rate`. :math:`\\nabla Q_{i}(w)` represents `grad`.
+    :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` represents `learning_rate`. :math:`\nabla Q_{i}(w)` represents `grad`.
 
     Args:
         use_locking (bool): Whether to enable a lock to protect the variable and accumlation tensors
@@ -7101,7 +7101,7 @@ class CTCGreedyDecoder(PrimitiveWithCheck):
 
 class BasicLSTMCell(PrimitiveWithInfer):
     """
-    It's similar to operator DynamicRNN. BasicLSTMCell will be deprecated in the future.
+    It's similar to operator :class:`DynamicRNN`. BasicLSTMCell will be deprecated in the future.
     Please use DynamicRNN instead.
     """
 

mindspore/ops/operations/sponge_ops.py

@@ -1376,8 +1376,8 @@ class Dihedral14LJCFForceWithAtomEnergy(PrimitiveWithInfer):
     and potential energy for each atom.
 
     The calculation formula of force correction is the same as operator
-    Dihedral14LJForceWithDirectCF(), and the energy correction part is the same
-    as operator Dihedral14LJEnergy() and Dihedral14CFEnergy().
+    :class:`Dihedral14LJForceWithDirectCF`, and the energy correction part is the same
+    as operator :class:`Dihedral14LJEnergy` and :class:`Dihedral14CFEnergy`.
 
     Args:
         nb14_numbers (int32): the number of necessary dihedral 1,4 terms M.
@@ -1642,7 +1642,7 @@ class Dihedral14CFAtomEnergy(PrimitiveWithInfer):
     Add the potential energy caused by Coulumb energy correction for each
     necessary dihedral 1,4 terms to the total potential energy of each atom.
 
-    The calculation formula is the same as operator Dihedral14CFEnergy().
+    The calculation formula is the same as operator :class:`Dihedral14CFEnergy`.
 
     Args:
         nb14_numbers (int32): the number of necessary dihedral 1,4 terms M.
@@ -2253,7 +2253,7 @@ class LJForceWithPMEDirectForce(PrimitiveWithInfer):
     The calculation formula of Lennard-Jones part is the same as operator
     LJForce(), and the PME direct part is within PME method.
 
-    Agrs:
+    Args:
         atom_numbers(int32): the number of atoms, N.
         cutoff_square(float32): the square value of cutoff.
         pme_beta(float32): PME beta parameter, same as operator PMEReciprocalForce().