mindspore 2.1.0__cp39-cp39-win_amd64.whl → 2.2.10__cp39-cp39-win_amd64.whl

mindspore/dataset/engine/datasets_audio.py

@@ -1,4 +1,4 @@
-# Copyright 2019-2022 Huawei Technologies Co., Ltd
+# Copyright 2019-2023 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None``, which means no cache is used.
 
     Raises:
@@ -77,38 +77,14 @@ class CMUArcticDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.1/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - Not support :class:`mindspore.dataset.PKSampler` for `sampler` parameter yet.
-        - This dataset can take in a `sampler` . `sampler` and `shuffle` are mutually exclusive.
-          The table below shows what input arguments are allowed and their expected behavior.
-
-    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
-       :widths: 25 25 50
-       :header-rows: 1
-
-       * - Parameter `sampler`
-         - Parameter `shuffle`
-         - Expected Order Behavior
-       * - None
-         - None
-         - random order
-       * - None
-         - True
-         - random order
-       * - None
-         - False
-         - sequential order
-       * - Sampler object
-         - None
-         - order defined by sampler
-       * - Sampler object
-         - True
-         - not allowed
-       * - Sampler object
-         - False
-         - not allowed
+        - 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.
+
+    .. include:: mindspore.dataset.sampler.txt
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -204,7 +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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -218,38 +194,14 @@ class GTZANDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.1/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - Not support :class:`mindspore.dataset.PKSampler` for `sampler` parameter yet.
-        - This dataset can take in a `sampler` . `sampler` and `shuffle` are mutually exclusive.
-          The table below shows what input arguments are allowed and their expected behavior.
-
-    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
-       :widths: 25 25 50
-       :header-rows: 1
-
-       * - Parameter `sampler`
-         - Parameter `shuffle`
-         - Expected Order Behavior
-       * - None
-         - None
-         - random order
-       * - None
-         - True
-         - random order
-       * - None
-         - False
-         - sequential order
-       * - Sampler object
-         - None
-         - order defined by sampler
-       * - Sampler object
-         - True
-         - not allowed
-       * - Sampler object
-         - False
-         - not allowed
+        - 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.
+
+    .. include:: mindspore.dataset.sampler.txt
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -346,7 +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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -360,38 +312,14 @@ class LibriTTSDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.1/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
         - Not support :class:`mindspore.dataset.PKSampler` for `sampler` parameter yet.
-        - This dataset can take in a `sampler` . `sampler` and `shuffle` are mutually exclusive.
-          The table below shows what input arguments are allowed and their expected behavior.
-
-    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
-       :widths: 25 25 50
-       :header-rows: 1
-
-       * - Parameter `sampler`
-         - Parameter `shuffle`
-         - Expected Order Behavior
-       * - None
-         - None
-         - random order
-       * - None
-         - True
-         - random order
-       * - None
-         - False
-         - sequential order
-       * - Sampler object
-         - None
-         - order defined by sampler
-       * - Sampler object
-         - True
-         - not allowed
-       * - Sampler object
-         - False
-         - not allowed
+        - 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.
+
+    .. include:: mindspore.dataset.sampler.txt
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -497,7 +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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -511,37 +439,13 @@ class LJSpeechDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.1/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
-        - This dataset can take in a `sampler` . `sampler` and `shuffle` are mutually exclusive.
-          The table below shows what input arguments are allowed and their expected behavior.
-
-    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
-       :widths: 25 25 50
-       :header-rows: 1
-
-       * - Parameter `sampler`
-         - Parameter `shuffle`
-         - Expected Order Behavior
-       * - None
-         - None
-         - random order
-       * - None
-         - True
-         - random order
-       * - None
-         - False
-         - sequential order
-       * - Sampler object
-         - None
-         - order defined by sampler
-       * - Sampler object
-         - True
-         - not allowed
-       * - Sampler object
-         - False
-         - not allowed
+        - 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.
+
+    .. include:: mindspore.dataset.sampler.txt
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -644,7 +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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -658,37 +562,13 @@ class SpeechCommandsDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.1/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
-        - This dataset can take in a `sampler` . `sampler` and `shuffle` are mutually exclusive.
-          The table below shows what input arguments are allowed and their expected behavior.
-
-    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
-       :widths: 25 25 50
-       :header-rows: 1
-
-       * - Parameter `sampler`
-         - Parameter `shuffle`
-         - Expected Order Behavior
-       * - None
-         - None
-         - random order
-       * - None
-         - True
-         - random order
-       * - None
-         - False
-         - sequential order
-       * - Sampler object
-         - None
-         - order defined by sampler
-       * - Sampler object
-         - True
-         - not allowed
-       * - Sampler object
-         - False
-         - not allowed
+        - 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.
+
+    .. include:: mindspore.dataset.sampler.txt
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -781,7 +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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -795,37 +675,13 @@ class TedliumDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.1/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
-        - This dataset can take in a `sampler` . `sampler` and `shuffle` are mutually exclusive.
-          The table below shows what input arguments are allowed and their expected behavior.
-
-    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
-       :widths: 25 25 50
-       :header-rows: 1
-
-       * - Parameter `sampler`
-         - Parameter `shuffle`
-         - Expected Order Behavior
-       * - None
-         - None
-         - random order
-       * - None
-         - True
-         - random order
-       * - None
-         - False
-         - sequential order
-       * - Sampler object
-         - None
-         - order defined by sampler
-       * - Sampler object
-         - True
-         - not allowed
-       * - Sampler object
-         - False
-         - not allowed
+        - 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.
+
+    .. include:: mindspore.dataset.sampler.txt
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -985,7 +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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -999,37 +855,13 @@ class YesNoDataset(MappableDataset, AudioBaseDataset):
 
     Tutorial Examples:
         - `Load & Process Data With Dataset Pipeline
-          <https://www.mindspore.cn/docs/en/r2.1/api_python/samples/dataset/dataset_gallery.html>`_
+          <https://www.mindspore.cn/docs/en/r2.2/api_python/samples/dataset/dataset_gallery.html>`_
 
     Note:
-        - This dataset can take in a `sampler` . `sampler` and `shuffle` are mutually exclusive.
-          The table below shows what input arguments are allowed and their expected behavior.
-
-    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
-       :widths: 25 25 50
-       :header-rows: 1
-
-       * - Parameter `sampler`
-         - Parameter `shuffle`
-         - Expected Order Behavior
-       * - None
-         - None
-         - random order
-       * - None
-         - True
-         - random order
-       * - None
-         - False
-         - sequential order
-       * - Sampler object
-         - None
-         - order defined by sampler
-       * - Sampler object
-         - True
-         - not allowed
-       * - Sampler object
-         - False
-         - not allowed
+        - 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.
+
+    .. include:: mindspore.dataset.sampler.txt
 
     Examples:
         >>> import mindspore.dataset as ds

mindspore/dataset/engine/datasets_standard_format.py

@@ -76,7 +76,7 @@ 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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None``, which means no cache is used.
 
     Raises:
@@ -149,13 +149,13 @@ class MindDataset(MappableDataset, UnionBaseDataset):
             :class:`mindspore.dataset.PKSampler`, :class:`mindspore.dataset.RandomSampler`,
             :class:`mindspore.dataset.SequentialSampler`, :class:`mindspore.dataset.DistributedSampler`.
         padded_sample (dict, optional): Samples will be appended to dataset, where
-            keys are the same as column_list. Default: ``None``.
+            keys are the same as columns_list. Default: ``None``.
         num_padded (int, optional): Number of padding samples. Dataset size
             plus num_padded should be divisible by num_shards. Default: ``None``.
         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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/dataset/cache.html>`_ .
             Default: ``None`` , which means no cache is used.
 
     Raises:
@@ -166,34 +166,10 @@ class MindDataset(MappableDataset, UnionBaseDataset):
         ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Note:
-        - This dataset can take in a `sampler` . `sampler` and `shuffle` are mutually exclusive.
-          The table below shows what input arguments are allowed and their expected behavior.
-
-    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
-       :widths: 25 25 50
-       :header-rows: 1
-
-       * - Parameter `sampler`
-         - Parameter `shuffle`
-         - Expected Order Behavior
-       * - None
-         - None
-         - random order
-       * - None
-         - True
-         - random order
-       * - None
-         - False
-         - sequential order
-       * - Sampler object
-         - None
-         - order defined by sampler
-       * - Sampler object
-         - True
-         - not allowed
-       * - Sampler object
-         - False
-         - not allowed
+        - 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.
+
+    .. include:: mindspore.dataset.sampler.txt
 
     Examples:
         >>> import mindspore.dataset as ds
@@ -256,6 +232,9 @@ class TFRecordDataset(SourceDataset, UnionBaseDataset):
 
     The columns of generated dataset depend on the source TFRecord files.
 
+    Note:
+        'TFRecordDataset' is not support on Windows platform yet.
+
     Args:
         dataset_files (Union[str, list[str]]): String or list of files to be read or glob strings to search for a
             pattern of files. The list will be sorted in lexicographical order.
@@ -298,7 +277,7 @@ 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/r2.1/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.2/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
@@ -342,6 +321,8 @@ class TFRecordDataset(SourceDataset, UnionBaseDataset):
                  cache=None, compression_type=None):
         super().__init__(num_parallel_workers=num_parallel_workers, num_samples=num_samples, shuffle=shuffle,
                          num_shards=num_shards, shard_id=shard_id, cache=cache)
+        if platform.system().lower() == "windows":
+            raise NotImplementedError("TFRecordDataset is not supported for windows.")
         self.dataset_files = self._find_files(dataset_files)
         self.dataset_files.sort()
 
@@ -376,11 +357,11 @@ class OBSMindDataset(GeneratorDataset):
         dataset_files (list[str]): List of files in cloud storage to be read and file path is in
             the format of s3://bucketName/objectKey.
         server (str): Endpoint for accessing cloud storage.
-            If it's OBS Service of Huawei Cloud，the endpoint is
+            If it's OBS Service of Huawei Cloud, the endpoint is
             like ``<obs.cn-north-4.myhuaweicloud.com>`` (Region cn-north-4).
             If it's Minio which starts locally, the endpoint is like ``<https://127.0.0.1:9000>``.
-        ak (str): Access key ID of cloud storage.
-        sk (str): Secret key ID of cloud storage.
+        ak (str): The access key ID used to access the OBS data.
+        sk (str): The secret access key used to access the OBS data.
         sync_obs_path (str): Remote dir path used for synchronization, users need to
             create it on cloud storage in advance. Path is in the format of s3://bucketName/objectKey.
         columns_list (list[str], optional): List of columns to be read. Default: ``None`` , read all columns.