mindspore 2.2.14__cp39-cp39-win_amd64.whl → 2.4.0__cp39-cp39-win_amd64.whl

mindspore/dataset/engine/datasets_audio.py

@@ -63,7 +63,7 @@ class CMUArcticDataset(MappableDataset, AudioBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None``, will use ``0``. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None``, which means no cache is used.
 
     Raises:
@@ -77,7 +77,7 @@ class CMUArcticDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - Not support :class:`mindspore.dataset.PKSampler` for `sampler` parameter yet.
@@ -180,7 +180,7 @@ class GTZANDataset(MappableDataset, AudioBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -194,7 +194,7 @@ class GTZANDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - Not support :class:`mindspore.dataset.PKSampler` for `sampler` parameter yet.
@@ -298,7 +298,7 @@ class LibriTTSDataset(MappableDataset, AudioBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -312,7 +312,7 @@ class LibriTTSDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - Not support :class:`mindspore.dataset.PKSampler` for `sampler` parameter yet.
@@ -425,7 +425,7 @@ class LJSpeechDataset(MappableDataset, AudioBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -439,7 +439,7 @@ class LJSpeechDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - The parameters `num_samples` , `shuffle` , `num_shards` , `shard_id` can be used to control the sampler
@@ -548,7 +548,7 @@ class SpeechCommandsDataset(MappableDataset, AudioBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` .
             This argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -562,7 +562,7 @@ class SpeechCommandsDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - The parameters `num_samples` , `shuffle` , `num_shards` , `shard_id` can be used to control the sampler
@@ -661,7 +661,7 @@ class TedliumDataset(MappableDataset, AudioBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -675,7 +675,7 @@ class TedliumDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - The parameters `num_samples` , `shuffle` , `num_shards` , `shard_id` can be used to control the sampler
@@ -841,7 +841,7 @@ class YesNoDataset(MappableDataset, AudioBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This argument can only
             be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -855,7 +855,7 @@ class YesNoDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - The parameters `num_samples` , `shuffle` , `num_shards` , `shard_id` can be used to control the sampler

mindspore/dataset/engine/datasets_standard_format.py

@@ -33,6 +33,7 @@ from .datasets import UnionBaseDataset, SourceDataset, MappableDataset, Shuffle,
 from .datasets_user_defined import GeneratorDataset
 from .obs.obs_mindrecord_dataset import MindRecordFromOBS
 from .validators import check_csvdataset, check_minddataset, check_tfrecorddataset, check_obsminddataset
+from ...mindrecord.config import _get_enc_key, _get_dec_mode, _get_hash_mode, decrypt, verify_file_hash
 
 
 from ..core.validator_helpers import replace_none
@@ -76,7 +77,7 @@ class CSVDataset(SourceDataset, UnionBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None``. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None``, which means no cache is used.
 
     Raises:
@@ -155,7 +156,7 @@ class MindDataset(MappableDataset, UnionBaseDataset):
         num_samples (int, optional): The number of samples to be included in the dataset.
             Default: ``None`` , all samples.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -165,6 +166,52 @@ class MindDataset(MappableDataset, UnionBaseDataset):
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
         ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
+    Note:
+        - When sharding MindRecord (by configuring `num_shards` and `shard_id`), there are two strategies to implement
+          the data sharding logic. This API uses the strategy 2.
+
+        .. list-table:: Data sharding strategy 1
+            :widths: 50 50 50 50
+            :header-rows: 1
+
+            * - rank 0
+              - rank 1
+              - rank 2
+              - rank 3
+            * - 0
+              - 1
+              - 2
+              - 3
+            * - 4
+              - 5
+              - 6
+              - 7
+            * - 8
+              - 9
+              - 10
+              - 11
+
+        .. list-table:: Data sharding strategy 2
+            :widths: 50 50 50 50
+            :header-rows: 1
+
+            * - rank 0
+              - rank 1
+              - rank 2
+              - rank 3
+            * - 0
+              - 3
+              - 6
+              - 9
+            * - 1
+              - 4
+              - 7
+              - 10
+            * - 2
+              - 5
+              - 8
+              - 11
+
     Note:
         - The parameters `num_samples` , `shuffle` , `num_shards` , `shard_id` can be used to control the sampler
           used in the dataset, and their effects when combined with parameter `sampler` are as follows.
@@ -205,6 +252,35 @@ class MindDataset(MappableDataset, UnionBaseDataset):
             else:
                 self.dataset_files = dataset_files.replace("\\", "/")
 
+        # do decrypt & integrity check
+        if not isinstance(self.dataset_files, list):
+            if _get_enc_key() is not None or _get_hash_mode() is not None:
+                logger.warning("When a single mindrecord file which is generated by " +
+                               "`mindspore.mindrecord.FileWriter` with `shard_num` > 1 is used as the input, " +
+                               "enabling decryption/integrity check may fail. Please use file list as the input.")
+
+            # decrypt the data file and index file
+            index_file_name = self.dataset_files + ".db"
+            self.dataset_files = decrypt(self.dataset_files, _get_enc_key(), _get_dec_mode())
+            decrypt(index_file_name, _get_enc_key(), _get_dec_mode())
+
+            # verify integrity check
+            verify_file_hash(self.dataset_files)
+            verify_file_hash(self.dataset_files + ".db")
+        else:
+            file_tuple = []
+            for item in self.dataset_files:
+                # decrypt the data file and index file
+                index_file_name = item + ".db"
+                decrypt_filename = decrypt(item, _get_enc_key(), _get_dec_mode())
+                file_tuple.append(decrypt_filename)
+                decrypt(index_file_name, _get_enc_key(), _get_dec_mode())
+
+                # verify integrity check
+                verify_file_hash(decrypt_filename)
+                verify_file_hash(decrypt_filename + ".db")
+            self.dataset_files = file_tuple
+
         self.columns_list = replace_none(columns_list, [])
 
         if sampler is not None:
@@ -277,7 +353,7 @@ class TFRecordDataset(SourceDataset, UnionBaseDataset):
             When `compression_type` is not ``None``, and `num_samples` or numRows (parsed from `schema` ) is provided,
             `shard_equal_rows` will be implied as ``True``.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
         compression_type (str, optional): The type of compression used for all files, must be either ``''``,
             ``'GZIP'``, or ``'ZLIB'``. Default: ``None`` , as in empty string. It is highly recommended to
@@ -353,6 +429,10 @@ class OBSMindDataset(GeneratorDataset):
 
     The columns of generated dataset depend on the source MindRecord files.
 
+    Note:
+        - This interface accesses the `/cache` directory for node synchronization and requires the user to ensure
+          access to the `/cache` directory.
+
     Args:
         dataset_files (list[str]): List of files in cloud storage to be read and file path is in
             the format of s3://bucketName/objectKey.

mindspore/dataset/engine/datasets_text.py

@@ -70,7 +70,7 @@ class AGNewsDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . This
             argument can only be specified when `num_shards` is also specified. Default: ``None``.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None``, which means no cache is used.
 
     Raises:
@@ -81,7 +81,7 @@ class AGNewsDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -178,7 +178,7 @@ class AmazonReviewDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -189,7 +189,7 @@ class AmazonReviewDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -276,7 +276,7 @@ class CLUEDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     The generated dataset with different task setting has different output columns:
@@ -433,7 +433,7 @@ class CLUEDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -522,7 +522,7 @@ class CoNLL2000Dataset(SourceDataset, TextBaseDataset):
             Default: ``None`` , will use global default workers(8), it can be set
             by :func:`mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -533,7 +533,7 @@ class CoNLL2000Dataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -621,7 +621,7 @@ class DBpediaDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -633,7 +633,7 @@ class DBpediaDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -720,7 +720,7 @@ class EnWik9Dataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -731,7 +731,7 @@ class EnWik9Dataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -763,7 +763,7 @@ class EnWik9Dataset(SourceDataset, TextBaseDataset):
 
         @NetworkResource{Hutter_prize,
         author    = {English Wikipedia},
-        url       = "https://cs.fit.edu/~mmahoney/compression/textdata.html",
+        url       = "https://mattmahoney.net/dc/textdata.html",
         month     = {March},
         year      = {2006}
         }
@@ -808,7 +808,7 @@ class IMDBDataset(MappableDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -822,7 +822,7 @@ class IMDBDataset(MappableDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - The shape of the test column.
@@ -947,7 +947,7 @@ class IWSLT2016Dataset(SourceDataset, TextBaseDataset):
             Default: ``None`` , will use global default workers(8), it can be set
             by :func:`mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -958,7 +958,7 @@ class IWSLT2016Dataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1079,7 +1079,7 @@ class IWSLT2017Dataset(SourceDataset, TextBaseDataset):
             Default: ``None`` , will use global default workers(8), it can be set
             by :func:`mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1090,7 +1090,7 @@ class IWSLT2017Dataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1184,7 +1184,7 @@ class Multi30kDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1199,7 +1199,7 @@ class Multi30kDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1293,7 +1293,7 @@ class PennTreebankDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1304,7 +1304,7 @@ class PennTreebankDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1395,7 +1395,7 @@ class SogouNewsDataset(SourceDataset, TextBaseDataset):
             Default: ``None`` , will use global default workers(8), it can be set
             by :func:`mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1406,7 +1406,7 @@ class SogouNewsDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1493,7 +1493,7 @@ class SQuADDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1505,7 +1505,7 @@ class SQuADDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1611,7 +1611,7 @@ class SST2Dataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards`. This argument can only be specified when
             `num_shards` is also specified. Default: ``None`` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1623,7 +1623,7 @@ class SST2Dataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1714,7 +1714,7 @@ class TextFileDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1726,7 +1726,7 @@ class TextFileDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1781,7 +1781,7 @@ class UDPOSDataset(SourceDataset, TextBaseDataset):
             Default: ``None`` , will use global default workers(8), it can be set
             by :func:`mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1792,7 +1792,7 @@ class UDPOSDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -1864,7 +1864,7 @@ class WikiTextDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1877,7 +1877,7 @@ class WikiTextDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     About WikiTextDataset dataset:
 
@@ -1961,7 +1961,7 @@ class YahooAnswersDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: ``None`` . This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -1973,7 +1973,7 @@ class YahooAnswersDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -2064,7 +2064,7 @@ class YelpReviewDataset(SourceDataset, TextBaseDataset):
             Default: ``None`` , will use global default workers(8), it can be set
             by :func:`mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/docs/en/master/model_train/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -2075,7 +2075,7 @@ class YelpReviewDataset(SourceDataset, TextBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/master/api_python/samples/dataset/dataset_gallery.html>`_
 
     Examples:
         >>> import mindspore.dataset as ds