mindspore 2.0.0rc1__cp38-none-any.whl → 2.2.0__cp38-none-any.whl

mindspore/dataset/utils/line_reader.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # ==============================================================================
-"""Efficient line based file reading.
+"""Efficient line-based file reading.
 """
 import os
 
@@ -22,24 +22,27 @@ from ..core.validator_helpers import check_filename, check_uint64, check_value
 
 class LineReader:
     """
-    Efficient file line reader.
+    Line-based file reader.
 
-    This class is used to hold the line offsets of line based file.
-
-    The following functionality is provided:
-
-    - len() - return the number of lines in the file
-
-    - readline(line) - open file handle (if not opened yet), and read a line in the file
-
-    - close() - close the file handle opened in readline
+    Cache the line-based meta data of the file in advance to achieve random-access reading of each file line.
 
     Args:
-        filename (str): line based file to be loaded.
+        filename (str): Filename to be read.
 
     Raises:
-        TypeError: Parameter `filename` is wrong.
-        RuntimeError: The input file does not exist or is not a regular file.
+        TypeError: If `filename` is not of type int.
+        RuntimeError: If `filename` does not exist or is not a regular file.
+
+    Examples:
+        >>> from mindspore.dataset import LineReader
+        >>>
+        >>> reader = LineReader("/path/to/txt/or/csv/file")
+        >>> # Read the first line of csv file
+        >>> reader.readline(1)
+        >>> # Return the row size in csv file
+        >>> reader.len()
+        >>> # Close the handle
+        >>> reader.close()
     """
 
     def __init__(self, filename):
@@ -79,22 +82,22 @@ class LineReader:
         self.close()
 
     def len(self):
-        """Get the total number of lines in the file"""
+        """Get the total number of lines in the current file."""
         return len(self.offsets)
 
     def readline(self, line):
         """
-        Read specified line content.
+        Reads the contents of the specified line.
 
         Args:
-            line (int): the line number to be read, starting at 1.
+            line (int): The line number to be read, with a starting line number of 1.
 
         Returns:
-            str, line content (until line break character).
+            str, the contents of the corresponding line, without line break characters.
 
         Raises:
-            TypeError: Parameter `line` is the wrong type.
-            ValueError: Parameter `line` exceeds the file range.
+            TypeError: If `line` is not of type int.
+            ValueError: If `line` exceeds the total number of lines in the file.
         """
         check_uint64(line, "line")
         check_value(line, [1, len(self.offsets)], "line")
@@ -114,7 +117,7 @@ class LineReader:
         return content
 
     def close(self):
-        """Close the file"""
+        """Close the file handle."""
         if self.fo_handle is None:
             return
         self.fo_handle.close()

mindspore/dataset/vision/__init__.py

@@ -32,7 +32,7 @@ Note: Legacy c_transforms and py_transforms are deprecated but can still be impo
     import mindspore.dataset.vision.py_transforms as py_vision
 
 See `Vision Transforms
-<https://www.mindspore.cn/tutorials/en/r2.0/beginner/transforms.html#vision-transforms>`_ tutorial for more details.
+<https://www.mindspore.cn/tutorials/en/r2.2/beginner/transforms.html#vision-transforms>`_ tutorial for more details.
 
 Descriptions of common data processing terms are as follows:
 
@@ -42,32 +42,11 @@ Descriptions of common data processing terms are as follows:
 
 The data transform operation can be executed in the data processing pipeline or in the eager mode:
 
-- Pipeline mode is generally used to process datasets. For examples, please refer to
-  `introduction to data processing pipeline <https://www.mindspore.cn/docs/en/r2.0/api_python/
+- Pipeline mode is generally used to process big datasets. Examples refer to
+  `introduction to data processing pipeline <https://www.mindspore.cn/docs/en/r2.2/api_python/
   mindspore.dataset.html#introduction-to-data-processing-pipeline>`_ .
-- Eager mode is generally used for scattered samples. Examples of image preprocessing are as follows:
-
-  .. code-block::
-
-      import numpy as np
-      import mindspore.dataset.vision as vision
-      from PIL import Image,ImageFont,ImageDraw
-
-      # draw circle
-      img = Image.new("RGB", (300, 300), (255, 255, 255))
-      draw = ImageDraw.Draw(img)
-      draw.ellipse(((0, 0), (100, 100)), fill=(255, 0, 0), outline=(255, 0, 0), width=5)
-      img.save("./1.jpg")
-      with open("./1.jpg", "rb") as f:
-          data = f.read()
-
-      data_decoded = vision.Decode()(data)
-      data_croped = vision.RandomCrop(size=(250, 250))(data_decoded)
-      data_resized = vision.Resize(size=(224, 224))(data_croped)
-      data_normalized = vision.Normalize(mean=[0.485 * 255, 0.456 * 255, 0.406 * 255],
-                                         std=[0.229 * 255, 0.224 * 255, 0.225 * 255])(data_resized)
-      data_hwc2chw = vision.HWC2CHW()(data_normalized)
-      print("data: {}, shape: {}".format(data_hwc2chw, data_hwc2chw.shape), flush=True)
+- Eager mode is more like a function call to process data. Examples refer to
+  `Lightweight Data Processing <https://www.mindspore.cn/tutorials/en/r2.2/advanced/dataset/eager.html>`_ .
 """
 from . import c_transforms
 from . import py_transforms