mindspore 2.5.0__cp310-cp310-win_amd64.whl → 2.6.0rc1__cp310-cp310-win_amd64.whl

mindspore/dataset/text/transforms.py

@@ -595,7 +595,7 @@ class SentencePieceTokenizer(TextTensorOperation):
         >>> numpy_slices_dataset = numpy_slices_dataset.map(operations=tokenizer)
         >>> for item in numpy_slices_dataset.create_dict_iterator(num_epochs=1, output_numpy=True):
         ...     print(item["text"])
-        ['▁H' 'e' 'l' 'lo' '▁w' 'o' 'r' 'l' 'd']
+        ['▁H' 'el' 'lo' '▁' 'w' 'or' 'l' 'd']
         >>>
         >>> # Use the transform in eager mode
         >>> data = "Hello world"
@@ -603,7 +603,7 @@ class SentencePieceTokenizer(TextTensorOperation):
         ...                                           SentencePieceModel.UNIGRAM, {})
         >>> output = text.SentencePieceTokenizer(vocab, out_type=SPieceTokenizerOutType.STRING)(data)
         >>> print(output)
-        ['▁' 'H' 'e' 'l' 'l' 'o' '▁' 'w' 'o' 'r' 'l' 'd']
+        ['▁' 'H' 'e' 'l' 'l' 'o' '▁' 'w' 'or' 'l' 'd']
 
     Tutorial Examples:
         - `Illustration of text transforms
@@ -623,11 +623,11 @@ class SentencePieceTokenizer(TextTensorOperation):
 
 class SlidingWindow(TextTensorOperation):
     """
-    Construct a tensor from given data (only support 1-D for now), where each element in the dimension axis
+    Construct a tensor from given data (only support 1-D for now), where each element in the dimension `axis`
     is a slice of data starting at the corresponding position, with a specified width.
 
     Args:
-        width (int): The width of the window. It must be an integer and greater than zero.
+        width (int): The width of the window. Must be greater than zero.
         axis (int, optional): The axis along which the sliding window is computed. Default: ``0``.
 
     Raises:
@@ -1332,7 +1332,8 @@ if platform.system().lower() != 'windows':
 
     class FilterWikipediaXML(TextTensorOperation):
         """
-        Filter Wikipedia XML dumps to "clean" text consisting only of lowercase letters (a-z, converted from A-Z),
+        Filter the text in the format of Wikipedia XML dumps to "clean" text
+        consisting only of lowercase letters (a-z, converted from A-Z),
         and spaces (never consecutive).
 
         Note:

mindspore/dataset/text/utils.py

@@ -49,7 +49,7 @@ class CharNGram(cde.CharNGram):
                 this value can limit the size of the loaded set. Default: ``None``, no upper limit.
 
         Returns:
-            CharNGram, CharNGram pre-training vectors.
+            CharNGram, pre-training vectors.
 
         Raises:
             TypeError: If `file_path` is not of type str.
@@ -92,7 +92,7 @@ class FastText(cde.FastText):
                 this value can limit the size of the loaded set. Default: ``None``, no upper limit.
 
         Returns:
-            FastText, FastText pre-training vectors.
+            FastText, pre-training vectors.
 
         Raises:
             TypeError: If `file_path` is not of type str.
@@ -133,7 +133,7 @@ class GloVe(cde.GloVe):
                 this value can limit the size of the loaded set. Default: ``None``, no upper limit.
 
         Returns:
-            GloVe, GloVe pre-training vectors.
+            GloVe, pre-training vectors.
 
         Raises:
             TypeError: If `file_path` is not of type str.

mindspore/dataset/transforms/__init__.py

@@ -23,19 +23,10 @@ Common imported modules in corresponding API examples are as follows:
     import mindspore.dataset as ds
     import mindspore.dataset.transforms as transforms
 
-Note: Legacy c_transforms and py_transforms are deprecated but can still be imported as follows:
-
-.. code-block::
-
-    from mindspore.dataset.transforms import c_transforms
-    from mindspore.dataset.transforms import py_transforms
-
 Descriptions of common data processing terms are as follows:
 
 - TensorOperation, the base class of all data processing operations implemented in C++.
 - PyTensorOperation, the base class of all data processing operations implemented in Python.
-
-Note: In eager mode, non-NumPy input is implicitly converted to NumPy format and sent to MindSpore.
 """
 from .. import vision
 from . import c_transforms

mindspore/dataset/transforms/transforms.py

@@ -55,7 +55,7 @@ def clean_unused_executors():
     """
     clean the unused executor object in UDF or map with PyFunc process / thread mode
     """
-    key = str(os.getpid()) + "_" + str(threading.currentThread().ident)
+    key = str(os.getpid()) + "_" + str(threading.current_thread().ident)
     if key in EXECUTORS_LIST:
         EXECUTORS_LIST.pop(key)
 
@@ -94,7 +94,7 @@ class TensorOperation:
 
         # get or create the executor from EXECUTORS_LIST
         executor = None
-        key = str(os.getpid()) + "_" + str(threading.currentThread().ident)
+        key = str(os.getpid()) + "_" + str(threading.current_thread().ident)
         try:
             if key in EXECUTORS_LIST:
                 # get the executor by process id and thread id
@@ -111,7 +111,7 @@ class TensorOperation:
         except RuntimeError as e:
             if "Create stream failed" in str(e):
                 raise RuntimeError("Cannot reset NPU device in forked subprocess.\n    "
-                                   "Note: the following sevral scenarios are not supported yet.\n"
+                                   "Note: the following several scenarios are not supported yet.\n"
                                    "    1. GeneratorDataset with num_parallel_workers>1 and "
                                    "python_multiprocessing=True.\n    2. Independent dataset mode (export "
                                    "MS_INDEPENDENT_DATASET=True):\n        1) Use the eager mode of dvpp "

mindspore/dataset/utils/browse_dataset.py

@@ -31,7 +31,7 @@ def imshow_det_bbox(image, bboxes, labels, segm=None, class_names=None, score_th
         image (numpy.ndarray): The image to be displayed, shaped :math:`<C, H, W>` or :math:`<H, W, C>`,
             formatted RGB.
         bboxes (numpy.ndarray): Bounding boxes (with scores), shaped :math:`<N, 4>` or :math:`<N, 5>`,
-            data should be ordered with <N, x, y, w, h>.
+            data should be ordered with :math:`<N,X,Y,W,H>`.
         labels (numpy.ndarray): Labels of bboxes, shaped :math:`<N, 1>`.
         segm (numpy.ndarray): The segmentation masks of image in M classes, shaped :math:`<M, H, W>`.
             Default: ``None``.

mindspore/dataset/vision/__init__.py

@@ -24,13 +24,6 @@ Common imported modules in corresponding API examples are as follows:
     import mindspore.dataset.vision as vision
     import mindspore.dataset.vision.utils as utils
 
-Note: Legacy c_transforms and py_transforms are deprecated but can still be imported as follows:
-
-.. code-block::
-
-    import mindspore.dataset.vision.c_transforms as c_vision
-    import mindspore.dataset.vision.py_transforms as py_vision
-
 Descriptions of common data processing terms are as follows:
 
 - TensorOperation, the base class of all data processing operations implemented in C++.
@@ -41,9 +34,9 @@ The data transform operation can be executed in the data processing pipeline or
 
 - Pipeline mode is generally used to process big datasets. Examples refer to
   `introduction to data processing pipeline <https://www.mindspore.cn/docs/en/master/api_python/
-  mindspore.dataset.html#introduction-to-data-processing-pipeline>`_ .
+  mindspore.dataset.loading.html#introduction-to-data-processing-pipeline>`_ .
 - Eager mode is more like a function call to process data. Examples refer to
-  `Lightweight Data Processing <https://www.mindspore.cn/docs/en/master/model_train/dataset/eager.html>`_ .
+  `Lightweight Data Processing <https://www.mindspore.cn/tutorials/en/master/dataset/eager.html>`_ .
 """
 from . import c_transforms
 from . import py_transforms