mindspore 2.3.0rc1__cp37-cp37m-manylinux1_x86_64.whl → 2.3.0rc2__cp37-cp37m-manylinux1_x86_64.whl

mindspore/nn/layer/conv.py

@@ -242,11 +242,11 @@ class Conv2d(_Conv):
             distributions as well as constant ``'One'`` and ``'Zero'`` distributions are possible. Alias
             ``'xavier_uniform'`` , ``'he_uniform'`` , ``'ones'`` and ``'zeros'`` are acceptable. Uppercase and
             lowercase are both acceptable. Refer to the values of
-            `Initializer <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_,
+            `Initializer <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_,
             for more details. Default: ``None`` , weight will be initialized using ``'HeUniform'``.
         bias_init (Union[Tensor, str, Initializer, numbers.Number], optional): Initialization method of bias parameter.
             Available initialization methods are the same as 'weight_init'. Refer to the values of
-            `Initializer <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_,
+            `Initializer <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_,
             for more details. Default: ``None`` , bias will be initialized using ``'Uniform'`` .
         data_format (str, optional): The optional value for data format, is ``'NHWC'`` or ``'NCHW'`` .
             Default: ``'NCHW'`` . (NHWC is only supported in GPU now.)
@@ -458,11 +458,11 @@ class Conv1d(_Conv):
             distributions as well as constant 'One' and 'Zero' distributions are possible. Alias ``'xavier_uniform'`` ,
             ``'he_uniform'`` , ``'ones'`` and ``'zeros'`` are acceptable. Uppercase and lowercase are both acceptable.
             Refer to the values of
-            `Initializer <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_,
+            `Initializer <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_,
             for more details. Default: ``None`` , weight will be initialized using ``'HeUniform'``.
         bias_init (Union[Tensor, str, Initializer, numbers.Number], optional): Initialization method of bias parameter.
             Available initialization methods are the same as 'weight_init'. Refer to the values of
-            `Initializer <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_,
+            `Initializer <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_,
             for more details. Default: ``None`` , bias will be initialized using ``'Uniform'``.
         dtype (:class:`mindspore.dtype`): Dtype of Parameters. Default: ``mstype.float32`` .
 
@@ -691,11 +691,11 @@ class Conv3d(_Conv):
             distributions as well as constant ``'One'`` and ``'Zero'`` distributions are possible. Alias
             ``'xavier_uniform'`` , ``'he_uniform'`` , ``'ones'`` and ``'zeros'`` are acceptable. Uppercase and
             lowercase are both acceptable. Refer to the values of
-            `Initializer <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_,
+            `Initializer <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_,
             for more details. Default: ``None`` , weight will be initialized using ``'HeUniform'``.
         bias_init (Union[Tensor, str, Initializer, numbers.Number], optional): Initialization method of bias parameter.
             Available initialization methods are the same as 'weight_init'. Refer to the values of
-            `Initializer <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_,
+            `Initializer <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_,
             for more details. Default: ``None`` , bias will be initialized using ``'Uniform'`` .
         data_format (str, optional): The optional value for data format. Currently only support ``'NCDHW'`` .
         dtype (:class:`mindspore.dtype`): Dtype of Parameters. Default: ``mstype.float32`` .

mindspore/nn/layer/embedding.py

@@ -66,7 +66,7 @@ class Embedding(Cell):
         use_one_hot (bool): Specifies whether to apply one_hot encoding form. Default: ``False`` .
         embedding_table (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the embedding_table.
             Refer to class `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             for the values of string when a string is specified. Default: ``'normal'`` .
         dtype (:class:`mindspore.dtype`): Data type of `x`. Default: ``mstype.float32`` .
         padding_idx (int, None): When the padding_idx encounters index, the output embedding vector of this index

mindspore/nn/layer/normalization.py

@@ -21,7 +21,6 @@ import numbers
 import hashlib
 
 from mindspore.ops import operations as P
-from mindspore.ops import functional as F
 from mindspore.ops.operations import _inner_ops as inner
 from mindspore.common.parameter import Parameter
 from mindspore.common.initializer import initializer, Initializer
@@ -36,6 +35,7 @@ from mindspore.common import dtype as mstype
 from mindspore.parallel._utils import _is_in_auto_parallel_mode
 from mindspore.nn.cell import Cell
 from mindspore import log as logger
+from mindspore.ops import group_norm
 
 __all__ = ['BatchNorm1d', 'BatchNorm2d', 'BatchNorm3d', 'LayerNorm', 'GroupNorm',
            'SyncBatchNorm', 'InstanceNorm1d', 'InstanceNorm2d', 'InstanceNorm3d']
@@ -206,19 +206,19 @@ class BatchNorm1d(_BatchNorm):
             Default: ``True`` .
         gamma_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the :math:`\gamma` weight.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'ones'`` .
         beta_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the :math:`\beta` weight.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'``, etc. Default: ``'zeros'`` .
         moving_mean_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the moving mean.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'zeros'`` .
         moving_var_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the moving variance.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'ones'`` .
         use_batch_statistics (bool): If ``true`` , use the mean value and variance value of current batch data. If
             ``false`` , use the mean value and variance value of specified value. If ``None`` , the training process
@@ -302,19 +302,19 @@ class BatchNorm2d(_BatchNorm):
             Default: ``True`` .
         gamma_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the :math:`\gamma` weight.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'ones'`` .
         beta_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the :math:`\beta` weight.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'zeros'`` .
         moving_mean_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the moving mean.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'zeros'`` .
         moving_var_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the moving variance.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'ones'`` .
         use_batch_statistics (bool): Default: ``None`` .
 
@@ -391,19 +391,19 @@ class BatchNorm3d(Cell):
         affine (bool): A bool value. When set to ``True`` , gamma and beta can be learned. Default: ``True`` .
         gamma_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the gamma weight.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'ones'`` .
         beta_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the beta weight.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'zeros'`` .
         moving_mean_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the moving mean.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'zeros'`` .
         moving_var_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the moving variance.
             The values of str refer to the function `mindspore.common.initializer
-            <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.common.initializer.html>`_
+            <https://www.mindspore.cn/docs/en/master/api_python/mindspore.common.initializer.html>`_
             including ``'zeros'`` , ``'ones'`` , etc. Default: ``'ones'`` .
         use_batch_statistics (bool): If true, use the mean value and variance value of current batch data. If
             ``false``, use the mean value and variance value of specified value. If ``None`` , the training process
@@ -558,14 +558,14 @@ class SyncBatchNorm(_BatchNorm):
 
             For the Ascend devices, users need to prepare the rank table, set rank_id and device_id.
             Please see the `Ascend tutorial
-            <https://www.mindspore.cn/tutorials/experts/en/r2.3.q1/parallel/rank_table.html>`_
+            <https://www.mindspore.cn/tutorials/experts/en/master/parallel/rank_table.html>`_
             for more details.
 
             For the GPU devices, users need to prepare the host file and mpi, please see the `mpirun Startup
-            <https://www.mindspore.cn/tutorials/experts/en/r2.3.q1/parallel/mpirun.html>`_ .
+            <https://www.mindspore.cn/tutorials/experts/en/master/parallel/mpirun.html>`_ .
 
             For the CPU device, users need to write a dynamic cluster startup script, please see the `Dynamic Cluster
-            Startup <https://www.mindspore.cn/tutorials/experts/en/r2.3.q1/parallel/dynamic_cluster.html>`_ .
+            Startup <https://www.mindspore.cn/tutorials/experts/en/master/parallel/dynamic_cluster.html>`_ .
 
             This example should be run with multiple devices.
 
@@ -1100,7 +1100,8 @@ class GroupNorm(Cell):
         dtype (:class:`mindspore.dtype`): Dtype of Parameters. Default: ``mstype.float32`` .
 
     Inputs:
-        - **x** (Tensor) - The input feature with shape :math:`(N, C, H, W)` .
+        - **x** (Tensor) - The input feature with shape :math:`(N, C, *)`, where :math:`*` means, any number of
+          additional dimensions.
 
     Outputs:
         Tensor, the normalized and scaled offset tensor, has the same shape and data type as the `x`.
@@ -1145,34 +1146,13 @@ class GroupNorm(Cell):
         self.affine = validator.check_bool(affine, arg_name="affine", prim_name=self.cls_name)
 
         self.gamma = Parameter(initializer(
-            gamma_init, num_channels, dtype=dtype), name="gamma", requires_grad=affine)
+            gamma_init, self.num_channels, dtype=dtype), name="gamma", requires_grad=affine)
         self.beta = Parameter(initializer(
-            beta_init, num_channels, dtype=dtype), name="beta", requires_grad=affine)
-        self.reduce_mean = P.ReduceMean(keep_dims=True)
-        self.reduce_sum = P.ReduceSum(keep_dims=True)
-        self.shape = F.shape
-        self.reshape = F.reshape
-        self.square = F.square
-        self.sqrt = P.Sqrt()
+            beta_init, self.num_channels, dtype=dtype), name="beta", requires_grad=affine)
 
     def _cal_output(self, x):
         """calculate groupnorm output"""
-        batch, channel, height, width = F.shape(x)
-        self._channel_check(channel, self.num_channels, self.cls_name)
-        x = F.reshape(x, (batch, self.num_groups, -1))
-        mean = self.reduce_mean(x, 2)
-        var = F.div(self.reduce_sum(F.square(F.sub(x, mean)), 2), (channel * height * width / self.num_groups))
-        std = self.sqrt(var + self.eps)
-        x = F.div(F.sub(x, mean), std)
-        x = F.reshape(x, (batch, channel, height, width))
-        output = F.add(x * F.reshape(self.gamma, (-1, 1, 1)), F.reshape(self.beta, (-1, 1, 1)))
-        return output
-
-    @staticmethod
-    @_primexpr
-    def _check_input_dim(shape, cls_name):
-        dim = len(shape)
-        _check_dim(dim, 4, cls_name)
+        return group_norm(x, self.num_groups, self.gamma, self.beta, self.eps)
 
     @staticmethod
     @_primexpr
@@ -1193,7 +1173,5 @@ class GroupNorm(Cell):
         return 'num_groups={}, num_channels={}'.format(self.num_groups, self.num_channels)
 
     def construct(self, x):
-        self._check_input_dim(F.shape(x), self.cls_name)
-        self._check_dtype(x.dtype, [mstype.float16, mstype.float32], self.cls_name)
         output = self._cal_output(x)
         return output

mindspore/nn/layer/padding.py

@@ -630,6 +630,10 @@ class ZeroPad2d(_ConstantPadNd):
             The remaining dimensions of the output are consistent with those of the input.
             Only support non-negative value while running in Ascend.
 
+    Inputs:
+        - **x** (Tensor) - shape is :math:`(N, *)`, where :math:`*` means, any number of additional dimensions.
+          It is not supported that the size of dimensions is greater than 5 while running in Ascend.
+
     Returns:
         Tensor, the tensor after padding.
 

mindspore/nn/optim/ada_grad.py

@@ -126,7 +126,7 @@ class Adagrad(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         update_slots (bool): Whether the :math:`h` will be updated. Default: ``True`` .
@@ -168,7 +168,7 @@ class Adagrad(Optimizer):
         >>> import mindspore.nn as nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.Adagrad(params=net.trainable_params())

mindspore/nn/optim/adadelta.py

@@ -106,7 +106,7 @@ class Adadelta(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         rho (float): Decay rate, must be in range [0.0, 1.0]. Default: ``0.9`` .

mindspore/nn/optim/adafactor.py

@@ -264,7 +264,7 @@ class AdaFactor(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) Parameters use the default learning rate with None and weight decay with 0.
         >>> optim = nn.AdaFactor(params=net.trainable_params())

mindspore/nn/optim/adam.py

@@ -579,7 +579,7 @@ class Adam(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         beta1 (float): The exponential decay rate for the 1st moment estimations. Should be in range (0.0, 1.0).
@@ -652,7 +652,7 @@ class Adam(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.Adam(params=net.trainable_params())
@@ -906,7 +906,7 @@ class AdamWeightDecay(Optimizer):
         There is usually no connection between a optimizer and mixed precision. But when `FixedLossScaleManager` is used
         and `drop_overflow_update` in `FixedLossScaleManager` is set to False, optimizer needs to set the 'loss_scale'.
         As this optimizer has no argument of `loss_scale`, so `loss_scale` needs to be processed by other means, refer
-        document `LossScale <https://www.mindspore.cn/tutorials/en/r2.3.q1/advanced/mixed_precision.html>`_ to
+        document `LossScale <https://www.mindspore.cn/tutorials/en/master/advanced/mixed_precision.html>`_ to
         process `loss_scale` correctly.
 
         If parameters are not grouped, the `weight_decay` in optimizer will be applied on the network parameters without
@@ -950,7 +950,7 @@ class AdamWeightDecay(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         beta1 (float): The exponential decay rate for the 1st moment estimations. Default: ``0.9`` .
@@ -992,7 +992,7 @@ class AdamWeightDecay(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.AdamWeightDecay(params=net.trainable_params())
@@ -1150,7 +1150,7 @@ class AdamOffload(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         beta1 (float): The exponential decay rate for the 1st moment estimations. Should be in range (0.0, 1.0).
@@ -1205,7 +1205,7 @@ class AdamOffload(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.AdamOffload(params=net.trainable_params())

mindspore/nn/optim/adamax.py

@@ -115,7 +115,7 @@ class AdaMax(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         beta1 (float): The exponential decay rate for the 1st moment estimations. Should be in range (0.0, 1.0).
@@ -163,7 +163,7 @@ class AdaMax(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.AdaMax(params=net.trainable_params())

mindspore/nn/optim/adasum.py

@@ -445,7 +445,7 @@ class AdaSumByGradWrapCell(Cell):
         >>> import mindspore as ms
         >>> from mindspore import nn
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> optim = nn.AdaSumByGradWrapCell(nn.Momentum(params=net.trainable_params(), learning_rate=0.1, momentum=0.9))
         >>> loss = nn.SoftmaxCrossEntropyWithLogits()
@@ -514,7 +514,7 @@ class AdaSumByDeltaWeightWrapCell(Cell):
         >>> import mindspore as ms
         >>> from mindspore import nn
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> optim = nn.AdaSumByDeltaWeightWrapCell(nn.Momentum(params=net.trainable_params(),
         ...                                                 learning_rate=0.1, momentum=0.9))

mindspore/nn/optim/asgd.py

@@ -94,7 +94,7 @@ class ASGD(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         lambd (float): The decay term. Default: ``1e-4`` .
@@ -130,7 +130,7 @@ class ASGD(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.ASGD(params=net.trainable_params())

mindspore/nn/optim/ftrl.py

@@ -275,7 +275,7 @@ class FTRL(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.FTRL(params=net.trainable_params())

mindspore/nn/optim/lamb.py

@@ -132,7 +132,7 @@ class Lamb(Optimizer):
         There is usually no connection between a optimizer and mixed precision. But when `FixedLossScaleManager` is used
         and `drop_overflow_update` in `FixedLossScaleManager` is set to False, optimizer needs to set the 'loss_scale'.
         As this optimizer has no argument of `loss_scale`, so `loss_scale` needs to be processed by other means. Refer
-        document `LossScale <https://www.mindspore.cn/tutorials/en/r2.3.q1/advanced/mixed_precision.html>`_ to
+        document `LossScale <https://www.mindspore.cn/tutorials/en/master/advanced/mixed_precision.html>`_ to
         process `loss_scale` correctly.
 
         If parameters are not grouped, the `weight_decay` in optimizer will be applied on the network parameters without
@@ -184,7 +184,7 @@ class Lamb(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         beta1 (float): The exponential decay rate for the 1st moment estimations. Default: ``0.9`` .
@@ -226,7 +226,7 @@ class Lamb(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.Lamb(params=net.trainable_params(), learning_rate=0.1)

mindspore/nn/optim/lars.py

@@ -109,7 +109,7 @@ class LARS(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> loss = nn.SoftmaxCrossEntropyWithLogits()
         >>> opt = nn.Momentum(net.trainable_params(), 0.1, 0.9)

mindspore/nn/optim/lazyadam.py

@@ -334,7 +334,7 @@ class LazyAdam(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         beta1 (float): The exponential decay rate for the 1st moment estimations. Should be in range (0.0, 1.0).
@@ -390,7 +390,7 @@ class LazyAdam(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.LazyAdam(params=net.trainable_params())

mindspore/nn/optim/momentum.py

@@ -116,7 +116,7 @@ class Momentum(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         momentum (float): Hyperparameter of type float, means momentum for the moving average.
@@ -161,7 +161,7 @@ class Momentum(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.Momentum(params=net.trainable_params(), learning_rate=0.1, momentum=0.9)

mindspore/nn/optim/optimizer.py

@@ -96,7 +96,7 @@ class Optimizer(Cell):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate
               of current step.
 
@@ -774,7 +774,7 @@ class Optimizer(Cell):
         Examples:
             >>> from mindspore import nn
             >>> # Define the network structure of LeNet5. Refer to
-            >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+            >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
             >>> net = LeNet5()
             >>> conv_params = list(filter(lambda x: 'conv' in x.name, net.trainable_params()))
             >>> no_conv_params = list(filter(lambda x: 'conv' not in x.name, net.trainable_params()))

mindspore/nn/optim/proximal_ada_grad.py

@@ -122,7 +122,7 @@ class ProximalAdagrad(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of the current step.
 
         l1 (float): l1 regularization strength, must be greater than or equal to zero. Default: ``0.0`` .
@@ -165,7 +165,7 @@ class ProximalAdagrad(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.ProximalAdagrad(params=net.trainable_params())

mindspore/nn/optim/rmsprop.py

@@ -137,7 +137,7 @@ class RMSProp(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of the current step.
 
         decay (float): Decay rate. Should be equal to or greater than 0. Default: ``0.9`` .
@@ -186,7 +186,7 @@ class RMSProp(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.RMSProp(params=net.trainable_params(), learning_rate=0.1)

mindspore/nn/optim/rprop.py

@@ -96,7 +96,7 @@ class Rprop(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         etas (tuple[float, float]): The factor of multiplicative increasing or
@@ -137,7 +137,7 @@ class Rprop(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.Rprop(params=net.trainable_params())

mindspore/nn/optim/sgd.py

@@ -103,7 +103,7 @@ class SGD(Optimizer):
 
             - LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of
               `LearningRateSchedule
-              <https://www.mindspore.cn/docs/en/r2.3.q1/api_python/mindspore.nn.html#learningrateschedule-class>`_
+              <https://www.mindspore.cn/docs/en/master/api_python/mindspore.nn.html#learningrateschedule-class>`_
               with step as the input to get the learning rate of current step.
 
         momentum (float): A floating point value the momentum. must be at least 0.0. Default: ``0.0`` .
@@ -134,7 +134,7 @@ class SGD(Optimizer):
         >>> from mindspore import nn
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> #1) All parameters use the same learning rate and weight decay
         >>> optim = nn.SGD(params=net.trainable_params())

mindspore/nn/optim/thor.py

@@ -339,10 +339,10 @@ def thor(net, learning_rate, damping, momentum, weight_decay=0.0, loss_scale=1.0
         >>> from mindspore import Tensor
         >>>
         >>> # Define the network structure of LeNet5. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/lenet.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/lenet.py
         >>> net = LeNet5()
         >>> # Create the dataset taking MNIST as an example. Refer to
-        >>> # https://gitee.com/mindspore/docs/blob/r2.3.q1/docs/mindspore/code/mnist.py
+        >>> # https://gitee.com/mindspore/docs/blob/master/docs/mindspore/code/mnist.py
         >>> dataset = create_dataset()
         >>> temp = Tensor([4e-4, 1e-4, 1e-5, 1e-5], mstype.float32)
         >>> optim = nn.thor(net, learning_rate=temp, damping=temp, momentum=0.9, loss_scale=128, frequency=4)