!866 modify codes formats in quantization tutorials for master

Merge pull request !866 from lvmingfu/master

tutorials/source_en/advanced_use/quantization_aware.md

@@ -82,10 +82,10 @@ Next, the LeNet network is used as an example to describe steps 3 and 6.
 
 Define a fusion network and replace the specified operators.
 
-1. Use the `nn.Conv2dBnAct` operator to replace the two operators `nn.Conv2d` and `nn.Relu` in the original network model.
-2. Use the `nn.DenseBnAct` operator to replace the two operators `nn.Dense` and `nn.Relu` in the original network model.
+1. Use the `nn.Conv2dBnAct` operator to replace the two operators `nn.Conv2d` and `nn.ReLU` in the original network model.
+2. Use the `nn.DenseBnAct` operator to replace the two operators `nn.Dense` and `nn.ReLU` in the original network model.
 
-> Even if the `nn.Dense` and `nn.Conv2d` operators are not followed by `nn.Batchnorm` and `nn.Relu`, the preceding two replacement operations must be performed as required.
+> Even if the `nn.Dense` and `nn.Conv2d` operators are not followed by `nn.BatchNorm*` and `nn.ReLU`, the preceding two replacement operations must be performed as required.
 
 The definition of the original network model LeNet5 is as follows:
 

tutorials/source_zh_cn/advanced_use/quantization_aware.md

@@ -82,10 +82,10 @@ MindSpore的感知量化训练是在训练基础上，使用低精度数据替
 
 定义融合网络，在定义网络后，替换指定的算子。
 
-1. 使用`nn.Conv2dBnAct`算子替换原网络模型中的2个算子`nn.Conv2d`和`nn.Relu`。
-2. 使用`nn.DenseBnAct`算子替换原网络模型中的2个算子`nn.Dense`和`nn.Relu`。
+1. 使用`nn.Conv2dBnAct`算子替换原网络模型中的2个算子`nn.Conv2d`和`nn.ReLU`。
+2. 使用`nn.DenseBnAct`算子替换原网络模型中的2个算子`nn.Dense`和`nn.ReLU`。
 
-> 无论`nn.Dense`和`nn.Conv2d`算子后面有没有`nn.BatchNorm`和`nn.Relu`，都要按规定使用上述两个算子进行融合替换。
+> 无论`nn.Dense`和`nn.Conv2d`算子后面有没有`nn.BatchNorm*`和`nn.ReLU`，都要按规定使用上述两个算子进行融合替换。
 
 原网络模型LeNet5的定义如下所示：