mindspore 2.0.0a0__cp38-cp38-win_amd64.whl → 2.0.0rc1__cp38-cp38-win_amd64.whl

mindspore/dataset/engine/datasets_audio.py

@@ -34,9 +34,9 @@ from ..core.validator_helpers import replace_none
 
 class CMUArcticDataset(MappableDataset, AudioBaseDataset):
     """
-    A source dataset that reads and parses CMUArctic dataset.
+    CMU Arctic dataset.
 
-    The generated dataset has four columns: :py:obj:`["waveform", "sample_rate", "transcript", "utterance_id"]` .
+    The generated dataset has four columns: :py:obj:`[waveform, sample_rate, transcript, utterance_id]` .
     The tensor of column :py:obj:`waveform` is of the float32 type.
     The tensor of column :py:obj:`sample_rate` is of a scalar of uint32 type.
     The tensor of column :py:obj:`transcript` is of a scalar of string type.
@@ -46,63 +46,63 @@ class CMUArcticDataset(MappableDataset, AudioBaseDataset):
         dataset_dir (str): Path to the root directory that contains the dataset.
         name (str, optional): Part of this dataset, can be 'aew', 'ahw', 'aup', 'awb', 'axb', 'bdl',
             'clb', 'eey', 'fem', 'gka', 'jmk', 'ksp', 'ljm', 'lnh', 'rms', 'rxr', 'slp' or 'slt'.
-            Default: None, equal 'aew'.
+            Default: None, means 'aew'.
         num_samples (int, optional): The number of audio to be included in the dataset.
             Default: None, will read all audio.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, will use value set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (bool, optional): Whether or not to perform shuffle on the dataset.
             Default: None, expected order behavior shown in the table below.
         sampler (Sampler, optional): Object used to choose samples from the
             dataset. Default: None, expected order behavior shown in the table below.
-        num_shards (int, optional): Number of shards that the dataset will be divided into. Default: None.
+        num_shards (int, optional): Number of shards that the dataset will be divided into. Default: None, no dividing.
             When this argument is specified, `num_samples` reflects the max sample number of per shard.
-        shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
+        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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
-        RuntimeError: If source raises an exception during execution.
         RuntimeError: If `dataset_dir` does not contain data files.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `sampler` and `shuffle` are specified at the same time.
         RuntimeError: If `sampler` and `num_shards`/`shard_id` are specified at the same time.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Note:
-        - CMUArctic dataset doesn't support PKSampler.
+        - Not support `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'
+    .. 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
+       * - 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
 
     Examples:
         >>> cmu_arctic_dataset_directory = "/path/to/cmu_arctic_dataset_directory"
@@ -115,7 +115,7 @@ class CMUArcticDataset(MappableDataset, AudioBaseDataset):
 
     About CMUArctic dataset:
 
-    The CMU arctic databases are designed for the purpose of speech synthesis research.
+    The CMU Arctic databases are designed for the purpose of speech synthesis research.
     These single speaker speech databases have been carefully recorded under studio conditions
     and consist of approximately 1200 phonetically balanced English utterances. In addition to wavefiles,
     the databases provide complete support for the Festival Speech Synthesis System, including pre-built
@@ -172,9 +172,9 @@ class CMUArcticDataset(MappableDataset, AudioBaseDataset):
 
 class GTZANDataset(MappableDataset, AudioBaseDataset):
     """
-    A source dataset that reads and parses GTZAN dataset.
+    GTZAN dataset.
 
-    The generated dataset has three columns: :py:obj:`["waveform", "sample_rate", "label"]` .
+    The generated dataset has three columns: :py:obj:`[waveform, sample_rate, label]` .
     The tensor of column :py:obj:`waveform` is of the float32 type.
     The tensor of column :py:obj:`sample_rate` is of a scalar of uint32 type.
     The tensor of column :py:obj:`label` is of a scalar of string type.
@@ -182,11 +182,12 @@ class GTZANDataset(MappableDataset, AudioBaseDataset):
     Args:
         dataset_dir (str): Path to the root directory that contains the dataset.
         usage (str, optional): Usage of this dataset, can be 'train', 'valid', 'test' or 'all'.
-            Default: None, all samples.
+            Default: None, will read all samples.
         num_samples (int, optional): The number of audio to be included in the dataset.
             Default: None, will read all audio.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, will use value set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (bool, optional): Whether or not to perform shuffle on the dataset.
             Default: None, expected order behavior shown in the table below.
         sampler (Sampler, optional): Object used to choose samples from the
@@ -196,25 +197,24 @@ 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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
-        RuntimeError: If source raises an exception during execution.
         RuntimeError: If `dataset_dir` does not contain data files.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `sampler` and `shuffle` are specified at the same time.
         RuntimeError: If `sampler` and `num_shards`/`shard_id` are specified at the same time.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Note:
-        - GTZAN doesn't support PKSampler.
+        - Not support `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'
+    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
        :widths: 25 25 50
        :header-rows: 1
 
@@ -254,7 +254,7 @@ class GTZANDataset(MappableDataset, AudioBaseDataset):
     The GTZAN dataset appears in at least 100 published works and is the most commonly used
     public dataset for evaluation in machine listening research for music genre recognition.
     It consists of 1000 audio tracks, each of which is 30 seconds long. It contains 10 genres (blues,
-    classical, country, disco, hiphop, jazz, metal, pop, reggae and reggae), each of which is
+    classical, country, disco, hiphop, jazz, metal, pop, reggae and rock), each of which is
     represented by 100 tracks. The tracks are all 22050Hz Mono 16-bit audio files in .wav format.
 
     You can construct the following directory structure from GTZAN dataset and read by MindSpore's API.
@@ -303,10 +303,10 @@ class GTZANDataset(MappableDataset, AudioBaseDataset):
 
 class LibriTTSDataset(MappableDataset, AudioBaseDataset):
     """
-    A source dataset that reads and parses the LibriTTS dataset.
+    LibriTTS dataset.
 
-    The generated dataset has seven columns :py:obj:`['waveform', 'sample_rate', 'original_text', 'normalized_text',
-    'speaker_id', 'chapter_id', 'utterance_id']` .
+    The generated dataset has seven columns :py:obj:`[waveform, sample_rate, original_text, normalized_text,
+    speaker_id, chapter_id, utterance_id]` .
     The tensor of column :py:obj:`waveform` is of the float32 type.
     The tensor of column :py:obj:`sample_rate` is of a scalar of uint32 type.
     The tensor of column :py:obj:`original_text` is of a scalar of string type.
@@ -318,11 +318,12 @@ class LibriTTSDataset(MappableDataset, AudioBaseDataset):
     Args:
         dataset_dir (str): Path to the root directory that contains the dataset.
         usage (str, optional): Part of this dataset, can be 'dev-clean', 'dev-other', 'test-clean', 'test-other',
-            'train-clean-100', 'train-clean-360', 'train-other-500', or 'all'. Default: None, equal 'all'.
+            'train-clean-100', 'train-clean-360', 'train-other-500', or 'all'. Default: None, means 'all'.
         num_samples (int, optional): The number of images to be included in the dataset.
             Default: None, will read all audio.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, will use value set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (bool, optional): Whether or not to perform shuffle on the dataset.
             Default: None, expected order behavior shown in the table below.
         sampler (Sampler, optional): Object used to choose samples from the
@@ -332,25 +333,24 @@ 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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
-        RuntimeError: If source raises an exception during execution.
         RuntimeError: If `dataset_dir` does not contain data files.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `sampler` and `shuffle` are specified at the same time.
         RuntimeError: If `sampler` and `num_shards`/`shard_id` are specified at the same time.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Note:
-        - LibriTTS dataset doesn't support PKSampler.
+        - Not support `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'
+    .. list-table:: Expected Order Behavior of Using `sampler` and `shuffle`
        :widths: 25 25 50
        :header-rows: 1
 
@@ -454,7 +454,7 @@ class LibriTTSDataset(MappableDataset, AudioBaseDataset):
 
 class LJSpeechDataset(MappableDataset, AudioBaseDataset):
     """
-    A source dataset that reads and parses LJSpeech dataset.
+    LJSpeech dataset.
 
     The generated dataset has four columns :py:obj:`[waveform, sample_rate, transcription, normalized_transcript]` .
     The column :py:obj:`waveform` is a tensor of the float32 type.
@@ -466,8 +466,9 @@ class LJSpeechDataset(MappableDataset, AudioBaseDataset):
         dataset_dir (str): Path to the root directory that contains the dataset.
         num_samples (int, optional): The number of audios to be included in the dataset.
             Default: None, all audios.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (bool, optional): Whether to perform shuffle on the dataset. Default: None, expected
             order behavior shown in the table below.
         sampler (Sampler, optional): Object used to choose samples from the dataset.
@@ -478,7 +479,7 @@ 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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -488,7 +489,7 @@ class LJSpeechDataset(MappableDataset, AudioBaseDataset):
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        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.
@@ -591,7 +592,7 @@ class LJSpeechDataset(MappableDataset, AudioBaseDataset):
 
 class SpeechCommandsDataset(MappableDataset, AudioBaseDataset):
     """
-    A source dataset that reads and parses the SpeechCommands dataset.
+    Speech Commands dataset.
 
     The generated dataset has five columns :py:obj:`[waveform, sample_rate, label, speaker_id, utterance_number]` .
     The tensor of column :py:obj:`waveform` is a vector of the float32 type.
@@ -607,8 +608,9 @@ class SpeechCommandsDataset(MappableDataset, AudioBaseDataset):
             test samples and 'all' will read from all 105,829 samples. Default: None, will read all samples.
         num_samples (int, optional): The number of samples to be included in the dataset.
             Default: None, will read all samples.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, will use value set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (bool, optional): Whether or not to perform shuffle on the dataset.
             Default: None, expected order behavior shown in the table below.
         sampler (Sampler, optional): Object used to choose samples from the dataset.
@@ -618,7 +620,7 @@ 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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -628,7 +630,7 @@ class SpeechCommandsDataset(MappableDataset, AudioBaseDataset):
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        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.
@@ -714,7 +716,7 @@ class SpeechCommandsDataset(MappableDataset, AudioBaseDataset):
 
 class TedliumDataset(MappableDataset, AudioBaseDataset):
     """
-    A source dataset that reads and parses Tedlium dataset.
+    Tedlium dataset.
     The columns of generated dataset depend on the source SPH files and the corresponding STM files.
 
     The generated dataset has six columns :py:obj:`[waveform, sample_rate, transcript, talk_id, speaker_id,
@@ -737,8 +739,9 @@ class TedliumDataset(MappableDataset, AudioBaseDataset):
             Default: None, ".sph".
         num_samples (int, optional): The number of audio samples to be included in the dataset.
             Default: None, all samples.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (bool, optional): Whether to perform shuffle on the dataset. Default: None, expected
             order behavior shown in the table below.
         sampler (Sampler, optional): Object used to choose samples from the
@@ -749,7 +752,7 @@ 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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -759,7 +762,7 @@ class TedliumDataset(MappableDataset, AudioBaseDataset):
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        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.
@@ -925,7 +928,7 @@ class TedliumDataset(MappableDataset, AudioBaseDataset):
 
 class YesNoDataset(MappableDataset, AudioBaseDataset):
     """
-    A source dataset that reads and parses the YesNo dataset.
+    YesNo dataset.
 
     The generated dataset has three columns :py:obj:`[waveform, sample_rate, labels]` .
     The tensor of column :py:obj:`waveform` is a vector of the float32 type.
@@ -936,8 +939,9 @@ class YesNoDataset(MappableDataset, AudioBaseDataset):
         dataset_dir (str): Path to the root directory that contains the dataset.
         num_samples (int, optional): The number of images to be included in the dataset.
             Default: None, will read all images.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, will use value set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (bool, optional): Whether or not to perform shuffle on the dataset.
             Default: None, expected order behavior shown in the table below.
         sampler (Sampler, optional): Object used to choose samples from the
@@ -947,7 +951,7 @@ 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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -957,7 +961,7 @@ class YesNoDataset(MappableDataset, AudioBaseDataset):
         RuntimeError: If `sampler` and `num_shards`/`shard_id` are specified at the same time.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        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.

mindspore/dataset/engine/datasets_standard_format.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.
@@ -26,6 +26,7 @@ import platform
 import numpy as np
 
 import mindspore._c_dataengine as cde
+from mindspore import log as logger
 
 from .datasets import UnionBaseDataset, SourceDataset, MappableDataset, Shuffle, Schema, \
     shuffle_to_shuffle_mode, shuffle_to_bool
@@ -56,8 +57,9 @@ class CSVDataset(SourceDataset, UnionBaseDataset):
             is not provided, infers the column_names from the first row of CSV file.
         num_samples (int, optional): The number of samples to be included in the dataset.
             Default: None, will include all images.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Default: Shuffle.GLOBAL. Bool type and Shuffle enum are both supported to pass in.
             If shuffle is False, no shuffling will be performed.
@@ -73,7 +75,7 @@ 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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -82,7 +84,7 @@ class CSVDataset(SourceDataset, UnionBaseDataset):
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Examples:
         >>> csv_dataset_dir = ["/path/to/csv_dataset_file"] # contains 1 or multiple csv files
@@ -116,8 +118,10 @@ class MindDataset(MappableDataset, UnionBaseDataset):
             a file name of one component of a mindrecord source, other files with identical source
             in the same path will be found and loaded automatically. If dataset_file is a list,
             it represents for a list of dataset files to be read directly.
-        columns_list (list[str], optional): List of columns to be read. Default: None.
-        num_parallel_workers (int, optional): The number of readers. Default: None.
+        columns_list (list[str], optional): List of columns to be read. Default: None, read all columns.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Default: None, performs global shuffle. Bool type and Shuffle enum are both supported to pass in.
             If shuffle is False, no shuffling will be performed.
@@ -131,7 +135,7 @@ class MindDataset(MappableDataset, UnionBaseDataset):
             - Shuffle.INFILE: Keep the file sequence the same but shuffle the data within each file.
 
         num_shards (int, optional): Number of shards that the dataset will be divided into. Default: None.
-            When this argument is specified, 'num_samples' reflects the maximum sample number of per shard.
+            When this argument is specified, `num_samples` reflects the maximum sample number of per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         sampler (Sampler, optional): Object used to choose samples from the
@@ -145,7 +149,7 @@ 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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -153,7 +157,7 @@ class MindDataset(MappableDataset, UnionBaseDataset):
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        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.
@@ -247,56 +251,60 @@ class TFRecordDataset(SourceDataset, UnionBaseDataset):
 
     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 a lexicographical order.
+            pattern of files. The list will be sorted in lexicographical order.
         schema (Union[str, Schema], optional): Data format policy, which specifies the data types and shapes of the data
             column to be read. Both JSON file path and objects constructed by mindspore.dataset.Schema are acceptable.
             Default: None.
         columns_list (list[str], optional): List of columns to be read. Default: None, read all columns.
-        num_samples (int, optional): The number of samples (rows) to be included in the dataset. Default: None.
-            If num_samples is None and numRows(parsed from schema) does not exist, read the full dataset;
-            If num_samples is None and numRows(parsed from schema) is greater than 0, read numRows rows;
-            If both num_samples and numRows(parsed from schema) are greater than 0, read num_samples rows.
-            If `compression_type` is not None, then num_samples is a mandatory parameter and it is
-            for the number of rows that is be read per shard from the compressed files.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_samples (int, optional): The number of samples (rows) to be included in the dataset.
+            Default: None.
+            Processing priority for `num_samples` is as the following:
+            1. If `num_samples` is greater than 0, read `num_samples` rows.
+            2. Otherwise, if numRows (parsed from `schema` ) is greater than 0, read numRows rows.
+            3. Otherwise, read the full dataset.
+            `num_samples` or numRows (parsed from `schema` ) will be interpreted as number of rows per shard.
+            It is highly recommended to provide `num_samples` or numRows (parsed from `schema` )
+            when `compression_type` is "GZIP" or "ZLIB" to avoid performance degradation due to multiple
+            decompressions of the same file to obtain the file size.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Default: Shuffle.GLOBAL. Bool type and Shuffle enum are both supported to pass in.
-            If shuffle is False, no shuffling will be performed.
-            If shuffle is True, performs global shuffle.
+            If `shuffle` is False, no shuffling will be performed.
+            If `shuffle` is True, perform global shuffle.
             There are three levels of shuffling, desired shuffle enum defined by mindspore.dataset.Shuffle.
 
-            - Shuffle.GLOBAL: Shuffle both the files and samples, same as setting shuffle to True.
+            - Shuffle.GLOBAL: Shuffle both the files and samples, same as setting `shuffle` to True.
 
             - Shuffle.FILES: Shuffle files only.
 
         num_shards (int, optional): Number of shards that the dataset will be divided
             into. Default: None. When this argument is specified, `num_samples` reflects
-            the maximum sample number of per shard.
+            the maximum sample number per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         shard_equal_rows (bool, optional): Get equal rows for all shards. Default: False. If `shard_equal_rows`
-            is False, number of rows of each shard may be not equal, and may lead to a failure in distributed training.
-            When the number of samples of per TFRecord file are not equal, it is suggested to set to true.
+            is False, the number of rows of each shard may not be equal, and may lead to a failure in distributed
+            training. When the number of samples per TFRecord file are not equal, it is suggested to set it to True.
             This argument should only be specified when `num_shards` is also specified.
-            When `compression_type` is provided, `shard_equal_rows` will be ignored and considered as true.
+            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/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
-        compression_type (str, optional): Type of compression used for all files, must be either '', 'GZIP', or 'ZLIB'.
-            Default: None, as in empty string.
-            This will automatically get equal rows for all shards (`shard_equal_rows` considered to be True) and thus
-            cannot have the case where `num_samples` is None.
+        compression_type (str, optional): The type of compression used for all files, must be either '', 'GZIP', or
+            'ZLIB'. Default: None, as in empty string.
 
     Raises:
         ValueError: If dataset_files are not valid or do not exist.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards` ).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
         ValueError: If `compression_type` is invalid (other than '', 'GZIP', or 'ZLIB').
-        ValueError: If `compression_type` is provided but number of dataset files < `num_shards` .
-        ValueError: If `compression_type` is provided but `num_samples` is not provided or <= 0.
+        ValueError: If `compression_type` is provided, but the number of dataset files < `num_shards` .
+        ValueError: If `num_samples` < 0.
 
     Examples:
         >>> from mindspore import dtype as mstype
@@ -313,7 +321,7 @@ class TFRecordDataset(SourceDataset, UnionBaseDataset):
         >>> schema.add_column(name='col_1d', de_type=mstype.int64, shape=[2])
         >>> dataset = ds.TFRecordDataset(dataset_files=tfrecord_dataset_dir, schema=schema)
         >>>
-        >>> # 3) Get all rows from tfrecord_dataset_dir with schema file.
+        >>> # 3) Get all rows from tfrecord_dataset_dir with the schema file.
         >>> dataset = ds.TFRecordDataset(dataset_files=tfrecord_dataset_dir, schema=tfrecord_schema_file)
     """
 
@@ -331,9 +339,14 @@ class TFRecordDataset(SourceDataset, UnionBaseDataset):
         self.shard_equal_rows = replace_none(shard_equal_rows, False)
         self.compression_type = replace_none(compression_type, "")
 
+        # Only take numRows from schema when num_samples is not provided
         if self.schema is not None and (self.num_samples is None or self.num_samples == 0):
             self.num_samples = Schema.get_num_rows(self.schema)
 
+        if self.compression_type in ['ZLIB', 'GZIP'] and (self.num_samples is None or self.num_samples == 0):
+            logger.warning("Since compression_type is set, but neither num_samples nor numRows (from schema file) " +
+                           "is provided, performance might be degraded.")
+
     def parse(self, children=None):
         schema = self.schema.cpp_schema if isinstance(self.schema, Schema) else self.schema
         return cde.TFRecordNode(self.dataset_files, schema, self.columns_list, self.num_samples, self.shuffle_flag,
@@ -375,18 +388,18 @@ class OBSMindDataset(GeneratorDataset):
         num_shards (int, optional): Number of shards that the dataset will be divided
             into. Default: None.
         shard_id (int, optional): The shard ID within num_shards. Default: None. This
-            argument can only be specified when num_shards is also specified.
+            argument can only be specified when `num_shards` is also specified.
         shard_equal_rows (bool, optional): Get equal rows for all shards. Default: True. If shard_equal_rows
             is false, number of rows of each shard may be not equal, and may lead to a failure in distributed training.
             When the number of samples of per MindRecord file are not equal, it is suggested to set to true.
-            This argument should only be specified when num_shards is also specified.
+            This argument should only be specified when `num_shards` is also specified.
 
     Raises:
         RuntimeError: If `sync_obs_path` do not exist.
         ValueError: If `columns_list` is invalid.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Note:
         - It's necessary to create a synchronization directory on cloud storage in