Update normalization description at nn/layer/normalization.py

mindspore/ccsrc/minddata/dataset/api/execute.cc

@@ -564,7 +564,7 @@ std::string Execute::AippCfgGenerator() {
 
     std::vector<uint32_t> aipp_size = AippSizeFilter(resize_paras, crop_paras);
 
-    // Process normalization parameters to find out the final normalization parameters for Aipp module
+    // Process Normalization parameters to find out the final Normalization parameters for Aipp module
     std::vector<uint32_t> normalize_paras;
     if (info_->aipp_cfg_.find(vision::kDvppNormalizeOperation) != info_->aipp_cfg_.end()) {
       for (auto pos = info_->aipp_cfg_.equal_range(vision::kDvppNormalizeOperation); pos.first != pos.second;

mindspore/ccsrc/minddata/dataset/kernels/image/normalize_op.cc

@@ -39,7 +39,7 @@ NormalizeOp::NormalizeOp(float mean_r, float mean_g, float mean_b, float std_r,
 
 Status NormalizeOp::Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *output) {
   IO_CHECK(input, output);
-  // Doing the normalization
+  // Doing the Normalization
   return Normalize(input, output, mean_, std_);
 }
 

mindspore/ccsrc/minddata/dataset/kernels/image/normalize_pad_op.cc

@@ -37,7 +37,7 @@ NormalizePadOp::NormalizePadOp(float mean_r, float mean_g, float mean_b, float s
 
 Status NormalizePadOp::Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *output) {
   IO_CHECK(input, output);
-  // Doing the normalization + pad
+  // Doing the Normalization + pad
   return NormalizePad(input, output, mean_, std_, dtype_);
 }
 

mindspore/nn/acc/less_batch_normalization.py

@@ -27,7 +27,7 @@ __all__ = ["LessBN"]
 
 class CommonHeadLastFN(Cell):
     r"""
-    The last full normalization layer.
+    The last full Normalization layer.
 
     This layer implements the operation as:
 

mindspore/nn/layer/normalization.py

@@ -538,12 +538,12 @@ class BatchNorm3d(Cell):
 
 class GlobalBatchNorm(_BatchNorm):
     r"""
-    Global normalization layer over a N-dimension input.
+    Global Batch Normalization layer over a N-dimension input.
 
-    Global Normalization is cross device synchronized Batch Normalization. The implementation of Batch Normalization
-    only normalizes the data within each device. Global normalization will normalize the input within the group.
-    It has been described in the paper `Batch Normalization: Accelerating Deep Network Training by
-    Reducing Internal Covariate Shift <https://arxiv.org/abs/1502.03167>`_. It rescales and recenters the
+    Global Batch Normalization is cross device synchronized Batch Normalization. The implementation of
+    Batch Normalization only normalizes the data within each device. Global Normalization will normalize
+    the input within the group.It has been described in the paper `Batch Normalization: Accelerating Deep Network
+    Training by Reducing Internal Covariate Shift <https://arxiv.org/abs/1502.03167>`_. It rescales and recenters the
     feature using a mini-batch of data and the learned parameters which can be described in the following formula.
 
     .. math::
@@ -1003,9 +1003,9 @@ class GroupNorm(Cell):
     r"""
     Group Normalization over a mini-batch of inputs.
 
-    Group normalization is widely used in recurrent neural networks. It applies
+    Group Normalization is widely used in recurrent neural networks. It applies
     normalization on a mini-batch of inputs for each single training case as described
-    in the paper `Group Normalization <https://arxiv.org/pdf/1803.08494.pdf>`_. Group normalization
+    in the paper `Group Normalization <https://arxiv.org/pdf/1803.08494.pdf>`_. Group Normalization
     divides the channels into groups and computes within each group the mean and variance for normalization,
     and it performs very stable over a wide range of batch size. It can be described using the following formula.
 

mindspore/nn/metrics/confusion_matrix.py

@@ -32,7 +32,7 @@ class ConfusionMatrix(Metric):
         num_classes (int): Number of classes in the dataset.
         normalize (str): The parameter of calculating ConfusionMatrix supports four Normalization modes, Choose from:
 
-            - **'no_norm'** (None) - No normalization is used. Default: None.
+            - **'no_norm'** (None) - No Normalization is used. Default: None.
             - **'target'** (str) - Normalization based on target value.
             - **'prediction'** (str) - Normalization based on predicted value.
             - **'all'** (str) - Normalization over the whole matrix.

mindspore/numpy/math_ops.py

@@ -2300,9 +2300,9 @@ def cov(m, y=None, rowvar=True, bias=False, ddof=None, fweights=None, aweights=N
             a variable, with observations in the columns. Otherwise, the relationship
             is transposed: each column represents a variable, while the rows contain
             observations.
-        bias (bool, optional): Default normalization (``False``) is by :math:`(N - 1)`, where
+        bias (bool, optional): Default Normalization (``False``) is by :math:`(N - 1)`, where
             :math:`N` is the number of observations given (unbiased estimate). If bias is
-            ``True``, then normalization is by `N`. These values can be overridden by
+            ``True``, then Normalization is by `N`. These values can be overridden by
             using the keyword `ddof`.
         ddof (int, optional): If not ``None``, the default value implied by `bias` is
             overridden. Note that :math:`ddof=1` will return the unbiased estimate, even
@@ -2364,7 +2364,7 @@ def cov(m, y=None, rowvar=True, bias=False, ddof=None, fweights=None, aweights=N
 
     avg = average(m, axis=1, weights=w)
 
-    # Determine the normalization
+    # Determine the Normalization
     if w is None:
         fact = m.shape[1] - ddof
     else:

mindspore/ops/operations/_grad_ops.py

@@ -1141,7 +1141,7 @@ class L2NormalizeGrad(PrimitiveWithInfer):
 
 class LayerNormGrad(Primitive):
     """
-    Applies the layer normalization to the input array.
+    Applies the layer Normalization to the input array.
 
     This operator will calculate the input gradients of layernorm.
 

mindspore/ops/operations/nn_ops.py

@@ -816,7 +816,7 @@ class FusedBatchNormEx(PrimitiveWithCheck):
 
 class InstanceNorm(PrimitiveWithInfer):
     r"""
-    Instance normalization over a 4D input.
+    Instance Normalization over a 4D input.
 
     This operator applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with
     additional channel dimension) as described in the paper `Instance Normalization: The Missing Ingredient for

model_zoo/official/nlp/bert/src/CRF.py

@@ -74,7 +74,7 @@ class CRF(nn.Cell):
 
     def log_sum_exp(self, logits):
         '''
-        Compute the log_sum_exp score for normalization factor.
+        Compute the log_sum_exp score for Normalization factor.
         '''
         max_score = self.reduce_max(logits, -1)  #16 5 5
         score = self.log(self.reduce_sum(self.exp(logits - max_score), -1))

model_zoo/research/audio/deepspeech2/src/dataset.py

@@ -86,7 +86,7 @@ class ASRDataset(LoadAudioAndTranscript):
             audio_conf: Config containing the sample rate, window and the window length/stride in seconds
             manifest_filepath (str): manifest_file path.
             labels (list): List containing all the possible characters to map to
-            normalize: Apply standard mean and deviation normalization to audio tensor
+            normalize: Apply standard mean and deviation Normalization to audio tensor
             batch_size (int): Dataset batch size (default=32)
         """
     def __init__(self, audio_conf=None,
@@ -195,7 +195,7 @@ def create_dataset(audio_conf, manifest_filepath, labels, normalize, batch_size,
         audio_conf: Config containing the sample rate, window and the window length/stride in seconds
         manifest_filepath (str): manifest_file path.
         labels (list): list containing all the possible characters to map to
-        normalize: Apply standard mean and deviation normalization to audio tensor
+        normalize: Apply standard mean and deviation Normalization to audio tensor
         train_mode (bool): Whether dataset is use for train or eval (default=True).
         batch_size (int): Dataset batch size
         rank (int): The shard ID within num_shards (default=None).

model_zoo/research/audio/wavenet/README.md

@@ -75,13 +75,13 @@ Dataset used: [The LJ Speech Dataset](<https://keithito.com/LJ-Speech-Dataset>)
         ├──egs                             // Note the egs folder should be downloaded from the above link  
         ├──utils                           // Note the utils folder should be downloaded from the above link  
         ├── audio.py                       // Audio utils. Note this script should be downloaded from the above link
-        ├── compute-meanvar-stats.py       // Compute mean-variance normalization stats. Note this script should be downloaded from the above link
+        ├── compute-meanvar-stats.py       // Compute mean-variance Normalization stats. Note this script should be downloaded from the above link
         ├── evaluate.py                    // Evaluation
         ├── export.py                      // Convert mindspore model to air model  
         ├── hparams.py                     // Hyper-parameter configuration. Note this script should be downloaded from the above link
         ├── mksubset.py                    // Make subset of dataset. Note this script should be downloaded from the above link
         ├── preprocess.py                  // Preprocess dataset. Note this script should be downloaded from the above link
-        ├── preprocess_normalize.py        // Perform meanvar normalization to preprocessed features. Note this script should be downloaded from the above link
+        ├── preprocess_normalize.py        // Perform meanvar Normalization to preprocessed features. Note this script should be downloaded from the above link
         ├── README.md                      // Descriptions about WaveNet
         ├── train.py                       // Training scripts
         ├── train_pytorch.py               // Note this script should be downloaded from the above link. The initial name of this script is train.py in the project from the link

tests/st/networks/models/bert/src/CRF.py

@@ -30,7 +30,7 @@ class CRF(nn.Cell):
     Args:
         tag_to_index: The dict for tag to index mapping with extra "<START>" and "<STOP>"sign.
         batch_size: Batch size, i.e., the length of the first dimension.
-        seq_length: Sequence length, i.e., the length of the second dimention.
+        seq_length: Sequence length, i.e., the length of the second dimension.
         is_training: Specifies whether to use training mode.
     Returns:
         Training mode: Tensor, total loss.
@@ -74,7 +74,7 @@ class CRF(nn.Cell):
 
     def log_sum_exp(self, logits):
         '''
-        Compute the log_sum_exp score for normalization factor.
+        Compute the log_sum_exp score for Normalization factor.
         '''
         max_score = self.reduce_max(logits, -1)  #16 5 5
         score = self.log(self.reduce_sum(self.exp(logits - max_score), -1))

tests/ut/python/dataset/test_normalizeOp.py

@@ -31,7 +31,7 @@ GENERATE_GOLDEN = False
 
 def normalize_np(image, mean, std):
     """
-    Apply the normalization
+    Apply the Normalization
     """
     #  DE decodes the image in RGB by default, hence
     #  the values here are in RGB