Update serializer_deserializer.py

mindspore/python/mindspore/dataset/engine/serializer_deserializer.py

@@ -25,6 +25,7 @@ from . import datasets as de
 def serialize(dataset, json_filepath=""):
     """
     Serialize dataset pipeline into a JSON file.
+    用于将数据集管道序列化为一个JSON文件。
 
     Note:
         Currently some Python objects are not supported to be serialized.
@@ -48,12 +49,14 @@ def serialize(dataset, json_filepath=""):
         >>> # serialize it to JSON file
         >>> serialized_data = ds.serialize(dataset, json_filepath="/path/to/mnist_dataset_pipeline.json")
     """
+    # 返回一个字典，其中包含序列化后的数据集图。
     return dataset.to_json(json_filepath)
 
 
 def deserialize(input_dict=None, json_filepath=None):
     """
     Construct dataset pipeline from a JSON file produced by de.serialize().
+    用于从JSON文件中构造数据集管道。
 
     Note:
         Currently Python function deserialization of map operator are not supported.
@@ -82,17 +85,24 @@ def deserialize(input_dict=None, json_filepath=None):
     """
 
     data = None
+    # 判断input_dict是否为空
     if input_dict:
+        # 将input_dict转换为de.Dataset对象
         data = de.DeserializedDataset(input_dict)
 
+    # 如果json_filepath不为空
     if json_filepath:
+        # 将json_filepath转换为de.Dataset对象
         data = de.DeserializedDataset(json_filepath)
     return data
 
 
+# 定义一个函数expand_path，用于将相对路径转换为绝对路径
 def expand_path(node_repr, key, val):
-    """Convert relative to absolute path."""
+    """Convert relative to absolute path.用于将相对路径转换为绝对路径。"""
+    # 如果val是一个列表
     if isinstance(val, list):
+        # 那么将其中的每个文件路径转换为绝对路径，并添加到node_repr字典中
         node_repr[key] = [os.path.abspath(file) for file in val]
     else:
         node_repr[key] = os.path.abspath(val)
@@ -101,6 +111,7 @@ def expand_path(node_repr, key, val):
 def show(dataset, indentation=2):
     """
     Write the dataset pipeline graph to logger.info file.
+    用于将数据集管道图形写入logger.info文件。
 
     Args:
         dataset (Dataset): The starting node.
@@ -114,14 +125,16 @@ def show(dataset, indentation=2):
         >>> dataset = dataset.batch(batch_size=10, drop_remainder=True)
         >>> ds.show(dataset)
     """
-
+    # 使用json.dumps函数将其转换为格式化的字符串
     pipeline = dataset.to_json()
+    # 写入logger.info文件
     logger.info(json.dumps(pipeline, indent=indentation))
 
 
 def compare(pipeline1, pipeline2):
     """
     Compare if two dataset pipelines are the same.
+    用于比较两个数据集管道的是否相同。
 
     Args:
         pipeline1 (Dataset): a dataset pipeline.
@@ -135,5 +148,5 @@ def compare(pipeline1, pipeline2):
         >>> pipeline2 = ds.Cifar10Dataset(cifar10_dataset_dir, num_samples=100)
         >>> res = ds.compare(pipeline1, pipeline2)
     """
-
+    # 返回一个bool值
     return pipeline1.to_json() == pipeline2.to_json()