mindspore 2.0.0a0__cp39-cp39-win_amd64.whl → 2.0.0rc1__cp39-cp39-win_amd64.whl

mindspore/dataset/vision/transforms.py

@@ -98,18 +98,18 @@ class ImageTensorOperation(TensorOperation):
 
 
 class AdjustBrightness(ImageTensorOperation, PyTensorOperation):
-    r"""
-    Apdjust brightness of input image. Input image is expected to be in [H, W, C] format.
+    """
+    Adjust the brightness of the input image.
 
     Args:
-        brightness_factor (float): How much to adjust the brightness. Can be any non negative number.
+        brightness_factor (float): How much to adjust the brightness, must be non negative.
             0 gives a black image, 1 gives the original image,
             while 2 increases the brightness by a factor of 2.
 
     Raises:
         TypeError: If `brightness_factor` is not of type float.
         ValueError: If `brightness_factor` is less than 0.
-        RuntimeError: If given tensor shape is not <H, W, C>.
+        RuntimeError: If shape of the input image is not <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -142,18 +142,18 @@ class AdjustBrightness(ImageTensorOperation, PyTensorOperation):
 
 
 class AdjustContrast(ImageTensorOperation, PyTensorOperation):
-    r"""
-    Adjust contrast of input image. Input image is expected to be in [H, W, C] format.
+    """
+    Adjust the contrast of the input image.
 
     Args:
-        contrast_factor (float): How much to adjust the contrast. Can be any non negative number.
+        contrast_factor (float): How much to adjust the contrast, must be non negative.
             0 gives a solid gray image, 1 gives the original image,
             while 2 increases the contrast by a factor of 2.
 
     Raises:
         TypeError: If `contrast_factor` is not of type float.
         ValueError: If `contrast_factor` is less than 0.
-        RuntimeError: If given tensor shape is not <H, W, C>.
+        RuntimeError: If shape of the input image is not <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -187,7 +187,7 @@ class AdjustContrast(ImageTensorOperation, PyTensorOperation):
 
 class AdjustGamma(ImageTensorOperation, PyTensorOperation):
     r"""
-    Apply gamma correction on input image. Input image is expected to be in [..., H, W, C] or [H, W] format.
+    Apply gamma correction on input image. Input image is expected to be in <..., H, W, C> or <H, W> format.
 
     .. math::
         I_{\text{out}} = 255 \times \text{gain} \times \left(\frac{I_{\text{in}}}{255}\right)^{\gamma}
@@ -242,17 +242,17 @@ class AdjustGamma(ImageTensorOperation, PyTensorOperation):
 
 
 class AdjustHue(ImageTensorOperation, PyTensorOperation):
-    r"""
-    Adjust hue of input image. Input image is expected to be in [H, W, C] format.
+    """
+    Adjust the hue of the input image.
 
     Args:
         hue_factor (float): How much to add to the hue channel,
-            must be in the interval [-0.5, 0.5].
+            must be in range of [-0.5, 0.5].
 
     Raises:
         TypeError: If `hue_factor` is not of type float.
         ValueError: If `hue_factor` is not in the interval [-0.5, 0.5].
-        RuntimeError: If given tensor shape is not <H, W, C>.
+        RuntimeError: If shape of the input image is not <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -285,17 +285,18 @@ class AdjustHue(ImageTensorOperation, PyTensorOperation):
 
 
 class AdjustSaturation(ImageTensorOperation, PyTensorOperation):
-    r"""
-    Adjust saturation of input image. Input image is expected to be in [H, W, C] format.
+    """
+    Adjust the saturation of the input image.
 
     Args:
-        saturation_factor (float): How much to adjust the saturation. Can be any non negative number.
+        saturation_factor (float): How much to adjust the saturation, must be non negative.
             0 gives a black image, 1 gives the original image while 2 increases the saturation by a factor of 2.
 
     Raises:
         TypeError: If `saturation_factor` is not of type float.
         ValueError: If `saturation_factor` is less than 0.
-        RuntimeError: If given tensor shape is not <H, W, C> or channel is not 3.
+        RuntimeError: If shape of the input image is not <H, W, C>.
+        RuntimeError: If channel of the input image is not 3.
 
     Supported Platforms:
         ``CPU``
@@ -328,18 +329,18 @@ class AdjustSaturation(ImageTensorOperation, PyTensorOperation):
 
 
 class AdjustSharpness(ImageTensorOperation):
-    r"""
-    Adjust sharpness of input image. Input image is expected to be in [H, W, C] or [H, W] format.
+    """
+    Adjust the sharpness of the input image.
 
     Args:
-        sharpness_factor (float): How much to adjust the sharpness, should be a
-            non negative number. 0 gives a blurred image, 1 gives the
-            original image while 2 increases the Sharpness by a factor of 2.
+        sharpness_factor (float): How much to adjust the sharpness, must be
+            non negative. 0 gives a blurred image, 1 gives the
+            original image while 2 increases the sharpness by a factor of 2.
 
     Raises:
         TypeError: If `sharpness_factor` is not of type float.
         ValueError: If `sharpness_factor` is less than 0.
-        RuntimeError: If given tensor shape is not <H, W, C> or <H, W>.
+        RuntimeError: If shape of the input image is not <H, W> or <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -366,13 +367,11 @@ class Affine(ImageTensorOperation):
 
     Args:
         degrees (float): Rotation angle in degrees between -180 and 180, clockwise direction.
-        translate (Sequence): The horizontal and vertical translations, must be a sequence of size 2.
+        translate (Sequence[float, float]): The horizontal and vertical translations, must be a sequence of size 2.
         scale (float): Scaling factor, which must be positive.
-        shear (Union[float, Sequence]): Shear angle value in degrees between -180 to 180.
-            If a number is provided, a shearing parallel to X axis with a factor selected from
-            ( `-shear` , `shear` ) will be applied.
-            If a sequence is provided, a shearing parallel to X axis with a factor selected
-            from ( `shear` [0], `shear` [1]) will be applied.
+        shear (Union[float, Sequence[float, float]]): Shear angle value in degrees between -180 to 180.
+            If float is provided, shear along the x axis with this value, without shearing along the y axis;
+            If Sequence[float, float] is provided, shear along the x axis and y axis with these two values separately.
         resample (Inter, optional): An optional resampling filter. Default: Inter.NEAREST.
             It can be any of [Inter.BILINEAR, Inter.NEAREST, Inter.BICUBIC, Inter.AREA].
 
@@ -392,11 +391,11 @@ class Affine(ImageTensorOperation):
         TypeError: If `degrees` is not of type float.
         TypeError: If `translate` is not of type Sequence[float, float].
         TypeError: If `scale` is not of type float.
+        ValueError: If `scale` is non positive.
         TypeError: If `shear` is not of float or Sequence[float, float].
         TypeError: If `resample` is not of type :class:`mindspore.dataset.vision.Inter` .
         TypeError: If `fill_value` is not of type int or tuple[int, int, int].
-        ValueError: If `scale` is non positive.
-        RuntimeError: If given tensor shape is not <H, W> or <H, W, C>.
+        RuntimeError: If shape of the input image is not <H, W> or <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -567,7 +566,7 @@ class BoundingBoxAugment(ImageTensorOperation):
             Range: [0.0, 1.0]. Default: 0.3.
 
     Raises:
-        TypeError: If `transform` is an image processing operation in :class:`mindspore.dataset.vision.transforms` .
+        TypeError: If `transform` is an image processing operation in `mindspore.dataset.vision` .
         TypeError: If `ratio` is not of type float.
         ValueError: If `ratio` is not in range [0.0, 1.0].
         RuntimeError: If given bounding box is invalid.
@@ -613,7 +612,7 @@ class CenterCrop(ImageTensorOperation, PyTensorOperation):
     Raises:
         TypeError: If `size` is not of type integer or sequence.
         ValueError: If `size` is less than or equal to 0.
-        RuntimeError: If given tensor shape is not <H, W> or <H, W, C>.
+        RuntimeError: If given tensor shape is not <H, W> or <..., H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -864,7 +863,8 @@ class Decode(ImageTensorOperation, PyTensorOperation):
     Supported image formats: JPEG, BMP, PNG, TIFF, GIF(need `to_pil=True` ), WEBP(need `to_pil=True` ).
 
     Args:
-        to_pil (bool, optional): decode to PIL Image. Default: False.
+        to_pil (bool, optional): Whether to decode the image to the PIL data type. If True, the image will be decoded
+            to the PIL data type, otherwise it will be decoded to the NumPy data type. Default: False.
 
     Raises:
         RuntimeError: If given tensor is not a 1D sequence.
@@ -972,20 +972,24 @@ class Erase(ImageTensorOperation):
         left (int): Horizontal ordinate of the upper left corner of erased region.
         height (int): Height of erased region.
         width (int): Width of erased region.
-        value (Union[int, Sequence[int]], optional): Pixel value used to pad the erased area.
-            If a single integer is provided, it will be used for all RGB channels.
-            If a sequence of length 3 is provided, it will be used for R, G, B channels respectively.
-            Default: 0.
+        value (Union[int, Sequence[int, int, int]], optional): Pixel value used to pad the erased area. Default: 0.
+            If int is provided, it will be used for all RGB channels.
+            If Sequence[int, int, int] is provided, it will be used for R, G, B channels respectively.
         inplace (bool, optional): Whether to apply erasing inplace. Default: False.
 
     Raises:
         TypeError: If `top` is not of type int.
+        ValueError: If `top` is negative.
         TypeError: If `left` is not of type int.
+        ValueError: If `left` is negative.
         TypeError: If `height` is not of type int.
+        ValueError: If `height` is not positive.
         TypeError: If `width` is not of type int.
-        TypeError: If `value` is not of type int or Sequence[int].
+        ValueError: If `width` is not positive.
+        TypeError: If `value` is not of type int or Sequence[int, int, int].
+        ValueError: If `value` is not in range of [0, 255].
         TypeError: If `inplace` is not of type bool.
-        RuntimeError: If given tensor shape is not <H, W, C>.
+        RuntimeError: If shape of the input image is not <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -1182,8 +1186,8 @@ class HsvToRgb(PyTensorOperation):
     Convert the input numpy.ndarray images from HSV to RGB.
 
     Args:
-        is_hwc (bool): If True, means the input image is in shape of (H, W, C) or (N, H, W, C).
-            Otherwise, it is in shape of (C, H, W) or (N, C, H, W). Default: False.
+        is_hwc (bool): If True, means the input image is in shape of <H, W, C> or <N, H, W, C>.
+            Otherwise, it is in shape of <C, H, W> or <N, C, H, W>. Default: False.
 
     Raises:
         TypeError: If `is_hwc` is not of type bool.
@@ -1225,7 +1229,7 @@ class HsvToRgb(PyTensorOperation):
 
 class HWC2CHW(ImageTensorOperation):
     """
-    Transpose the input image from shape (H, W, C) to (C, H, W).
+    Transpose the input image from shape <H, W, C> to <C, H, W>.
     If the input image is of shape <H, W>, it will remain unchanged.
 
     Note:
@@ -1341,7 +1345,7 @@ class LinearTransformation(PyTensorOperation):
         Execute method.
 
         Args:
-            np_img (numpy.ndarray): Image in shape of (C, H, W) to be linearly transformed.
+            np_img (numpy.ndarray): Image in shape of <C, H, W> to be linearly transformed.
 
         Returns:
             numpy.ndarray, linearly transformed image.
@@ -1353,9 +1357,9 @@ class MixUp(PyTensorOperation):
     """
     Randomly mix up a batch of numpy.ndarray images together with its labels.
 
-    Each image will be multiplied by a random weight lambda generated from the Beta distribution and then added
-    to another image multiplied by 1 - lambda. The same transformation will be applied to their labels with the
-    same value of lambda. Make sure that the labels are one-hot encoded in advance.
+    Each image will be multiplied by a random weight :math:`lambda` generated from the Beta distribution and then added
+    to another image multiplied by :math:`1 - lambda`. The same transformation will be applied to their labels with the
+    same value of :math:`lambda`. Make sure that the labels are one-hot encoded in advance.
 
     Args:
         batch_size (int): The number of images in a batch.
@@ -1485,7 +1489,7 @@ class Normalize(ImageTensorOperation):
         TypeError: If `is_hwc` is not of type bool.
         ValueError: If `mean` is not in range [0.0, 255.0].
         ValueError: If `std` is not in range (0.0, 255.0].
-        RuntimeError: If given tensor format is not <H, W> or <...,H, W, C>.
+        RuntimeError: If given tensor format is not <H, W> or <..., H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -1589,14 +1593,8 @@ class Pad(ImageTensorOperation, PyTensorOperation):
             - Border.SYMMETRIC, means it reflects the values on the edge repeating the last
               value of edge.
 
-    Note:
-        The behavior when `padding` is a sequence of length 2 will change from padding left/top with
-        the first value and right/bottom with the second, to padding left/right with the first one
-        and top/bottom with the second in the future. Or you can pass in a 4-element sequence to specify
-        left, top, right and bottom respectively.
-
     Raises:
-        TypeError: If `padding` is not of type int or Sequence[int, int], Sequence[int, int, int, int]].
+        TypeError: If `padding` is not of type int or Sequence[int, int], Sequence[int, int, int, int].
         TypeError: If `fill_value` is not of type int or tuple[int].
         TypeError: If `padding_mode` is not of type :class:`mindspore.dataset.vision.Border` .
         ValueError: If `padding` is negative.
@@ -1703,29 +1701,29 @@ class Perspective(ImageTensorOperation, PyTensorOperation):
     Apply perspective transformation on input image.
 
     Args:
-        start_points (Sequence[Sequence[int, int]]): List containing four lists of two integers corresponding to four
-            corners [top-left, top-right, bottom-right, bottom-left] of the original image.
-        end_points (Sequence[Sequence[int, int]]): List containing four lists of two integers corresponding to four
-            corners [top-left, top-right, bottom-right, bottom-left] of the transformed image.
+        start_points (Sequence[Sequence[int, int]]): Sequence of the starting point coordinates, containing four
+            two-element subsequences, corresponding to [top-left, top-right, bottom-right, bottom-left] of the
+            quadrilateral in the original image.
+        end_points (Sequence[Sequence[int, int]]): Sequence of the ending point coordinates, containing four
+            two-element subsequences, corresponding to [top-left, top-right, bottom-right, bottom-left] of the
+            quadrilateral in the target image.
         interpolation (Inter, optional): Method of interpolation. It can be Inter.BILINEAR, Inter.LINEAR,
             Inter.NEAREST, Inter.AREA, Inter.PILCUBIC, Inter.CUBIC or Inter.BICUBIC. Default: Inter.BILINEAR.
 
             - Inter.BILINEAR, bilinear interpolation.
-            - Inter.LINEAR, bilinear interpolation, here is the same as Inter.BILINEAR.
+            - Inter.LINEAR, linear interpolation, the same as Inter.BILINEAR.
             - Inter.NEAREST, nearest-neighbor interpolation.
             - Inter.BICUBIC, bicubic interpolation.
-            - Inter.CUBIC: means the interpolation method is bicubic interpolation, here is the same as Inter.BICUBIC.
-            - Inter.PILCUBIC, means interpolation method is bicubic interpolation like implemented in pillow, input
-              should be in 3 channels format.(PIL input is not supported)
-            - Inter.AREA, pixel area interpolation.(PIL input is not supported)
+            - Inter.CUBIC, cubic interpolation, the same as Inter.BICUBIC.
+            - Inter.PILCUBIC, cubic interpolation based on the implementation of Pillow,
+              only numpy.ndarray input is supported.
+            - Inter.AREA, pixel area interpolation, only numpy.ndarray input is supported.
 
     Raises:
-        TypeError: If `start_points` is not of type Sequence[Sequence[int, int]] of length 4.
-        TypeError: If element in `start_points` is not of type Sequence[int, int] of length 2.
-        TypeError: If `end_points` is not of type Sequence[Sequence[int, int]] of length 4.
-        TypeError: If element in `end_points` is not of type Sequence[int, int] of length 2.
+        TypeError: If `start_points` is not of type Sequence[Sequence[int, int]].
+        TypeError: If `end_points` is not of type Sequence[Sequence[int, int]].
         TypeError: If `interpolation` is not of type :class:`mindspore.dataset.vision.Inter` .
-        RuntimeError: If given tensor shape is not <H, W> or <H, W, C>.
+        RuntimeError: If shape of the input image is not <H, W> or <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -1760,7 +1758,7 @@ class Perspective(ImageTensorOperation, PyTensorOperation):
             raise TypeError("Current Interpolation is not supported with NumPy input.")
         return cde.PerspectiveOperation(self.start_points, self.end_points, Inter.to_c_type(self.interpolation))
 
-    def execute_py(self, img):
+    def _execute_py(self, img):
         """
         Execute method.
 
@@ -1777,7 +1775,8 @@ class Perspective(ImageTensorOperation, PyTensorOperation):
 
 class Posterize(ImageTensorOperation):
     """
-    Posterize an image by reducing the number of bits for each color channel.
+    Reduce the bit depth of the color channels of image to create a high contrast and vivid color effect,
+    similar to that seen in posters or printed materials.
 
     Args:
         bits (int): The number of bits to keep for each channel, should be in range of [0, 8].
@@ -1785,7 +1784,7 @@ class Posterize(ImageTensorOperation):
     Raises:
         TypeError: If `bits` is not of type int.
         ValueError: If `bits` is not in range [0, 8].
-        RuntimeError: If given tensor shape is not <H, W> or <H, W, C>.
+        RuntimeError: If shape of the input image is not <H, W> or <H, W, C>.
     """
 
     @check_posterize
@@ -1800,39 +1799,42 @@ class Posterize(ImageTensorOperation):
 
 class RandAugment(ImageTensorOperation):
     """
-    Apply RandAugment data augmentation method based on
-    `RandAugment: Learning Augmentation Strategies from Data <https://arxiv.org/pdf/1909.13719.pdf>`_ .
-    This operation works only with 3-channel RGB images.
+    Apply RandAugment data augmentation method on the input image.
 
-    Args:
-        num_ops (int, optional): Number of augmentation transformations to apply sequentially. Default: 2.
-        magnitude (int, optional): Magnitude for all the transformations and its value should be smaller than the value
-            of num_magnitude_bins. Default: 9.
-        num_magnitude_bins (int, optional): The number of different magnitude values. The number of different magnitude
-            values, must be greater than or equal to 2. Default: 31.
-        interpolation (Inter, optional): Image interpolation mode for Resize operation.
-            It can be any of [Inter.NEAREST, Inter.BILINEAR, Inter.BICUBIC, Inter.AREA]. Default: Inter.NEAREST.
+    Refer to `RandAugment: Learning Augmentation Strategies from Data <https://arxiv.org/pdf/1909.13719.pdf>`_ .
 
-            - Inter.NEAREST: means interpolation method is nearest-neighbor interpolation.
+    Only support 3-channel RGB image.
 
-            - Inter.BILINEAR: means interpolation method is bilinear interpolation.
-
-            - Inter.BICUBIC: means the interpolation method is bicubic interpolation.
+    Args:
+        num_ops (int, optional): Number of augmentation transformations to apply sequentially. Default: 2.
+        magnitude (int, optional): Magnitude for all the transformations, must be smaller than
+            `num_magnitude_bins`. Default: 9.
+        num_magnitude_bins (int, optional): The number of different magnitude values,
+            must be no less than 2. Default: 31.
+        interpolation (Inter, optional): Image interpolation method. Default: Inter.NEAREST.
+            It can be Inter.NEAREST, Inter.BILINEAR, Inter.BICUBIC or Inter.AREA.
 
-            - Inter.AREA: means the interpolation method is pixel area interpolation.
+            - Inter.NEAREST, nearest-neighbor interpolation.
+            - Inter.BILINEAR, bilinear interpolation.
+            - Inter.BICUBIC, bicubic interpolation.
+            - Inter.AREA, pixel area interpolation.
 
-        fill_value (Union[int, tuple[int, int, int]], optional): Pixel fill value for the area outside the transformed
-            image. It can be an int or a 3-tuple. If it is a 3-tuple, it is used to fill R, G, B channels respectively.
-            If it is an integer, it is used for all RGB channels. The fill_value values must be in range [0, 255].
-            Default: 0.
+        fill_value (Union[int, tuple[int, int, int]], optional): Pixel fill value for the area outside the
+            transformed image, must be in range of [0, 255]. Default: 0.
+            If int is provided, pad all RGB channels with this value.
+            If tuple[int, int, int] is provided, pad R, G, B channels respectively.
 
     Raises:
         TypeError: If `num_ops` is not of type int.
+        ValueError: If `num_ops` is negative.
         TypeError: If `magnitude` is not of type int.
+        ValueError: If `magnitude` is not positive.
         TypeError: If `num_magnitude_bins` is not of type int.
+        ValueError: If `num_magnitude_bins` is less than 2.
         TypeError: If `interpolation` not of type :class:`mindspore.dataset.vision.Inter` .
-        TypeError: If `fill_value` is not an int or a tuple of length 3.
-        RuntimeError: If given tensor shape is not <H, W, C>.
+        TypeError: If `fill_value` is not of type int or tuple[int, int, int].
+        ValueError: If `fill_value` is not in range of [0, 255].
+        RuntimeError: If shape of the input image is not <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -2266,7 +2268,7 @@ class RandomCrop(ImageTensorOperation, PyTensorOperation):
         ValueError: If `size` is not positive.
         ValueError: If `padding` is negative.
         ValueError: If `fill_value` is not in range [0, 255].
-        RuntimeError: If given tensor shape is not <H, W> or <H, W, C>.
+        RuntimeError: If given tensor shape is not <H, W> or <..., H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -2435,12 +2437,6 @@ class RandomCropWithBBox(ImageTensorOperation):
 
               value of edge.
 
-    Note:
-        The behavior when `padding` is a sequence of length 2 will change from padding left/top with
-        the first value and right/bottom with the second, to padding left/right with the first one
-        and top/bottom with the second in the future. Or you can pass in a 4-element sequence to specify
-        left, top, right and bottom respectively.
-
     Raises:
         TypeError: If `size` is not of type int or Sequence[int].
         TypeError: If `padding` is not of type int or Sequence[int].
@@ -2587,7 +2583,7 @@ class RandomErasing(PyTensorOperation):
         Execute method.
 
         Args:
-            np_img (numpy.ndarray): image in shape of (C, H, W) to be randomly erased.
+            np_img (numpy.ndarray): image in shape of <C, H, W> to be randomly erased.
 
         Returns:
             numpy.ndarray, erased image.
@@ -2870,6 +2866,9 @@ class RandomPerspective(PyTensorOperation):
 
 class RandomPosterize(ImageTensorOperation):
     """
+    Reduce the bit depth of the color channels of image with a given probability
+    to create a high contrast and vivid color image.
+
     Reduce the number of bits for each color channel to posterize the input image randomly with a given probability.
 
     Args:
@@ -2951,7 +2950,6 @@ class RandomResizedCrop(ImageTensorOperation, PyTensorOperation):
         ValueError: If `scale` is negative.
         ValueError: If `ratio` is negative.
         ValueError: If `max_attempts` is not positive.
-        RuntimeError: If given tensor shape is not <H, W> or <..., H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -3476,7 +3474,7 @@ class Rescale(ImageTensorOperation):
         TypeError: If `shift` is not of type float.
 
     Supported Platforms:
-        ``CPU`` ``Ascend`` ``GPU``
+        ``Ascend`` ``GPU`` ``CPU``
 
     Examples:
         >>> transforms_list = [vision.Decode(), vision.Rescale(1.0 / 255.0, -1.0)]
@@ -3519,7 +3517,7 @@ class Resize(ImageTensorOperation, PyTensorOperation):
 
     Raises:
         TypeError: If `size` is not of type int or Sequence[int].
-        TypeError: If `interpolation` is not of type Inter.
+        TypeError: If `interpolation` is not of type :class:`mindspore.dataset.vision.Inter` .
         ValueError: If `size` is not positive.
         RuntimeError: If given tensor shape is not <H, W> or <H, W, C>.
 
@@ -3571,38 +3569,39 @@ class Resize(ImageTensorOperation, PyTensorOperation):
 
 class ResizedCrop(ImageTensorOperation):
     """
-    Crop the input image at a specific location, and resize the cropped image using a selected interpolation mode.
+    Crop the input image at a specific region and resize it to desired size.
 
     Args:
-        top (int): Horizontal ordinate of the upper left corner of the crop image.
-        left (int): Vertical ordinate of the upper left corner of the crop image.
-        height (int): Height of cropped image.
-        width (int): Width of cropped image.
-        size (Union[int, Sequence[int]]): The output size of the resized image. The size value(s) must be positive.
-            If size is an integer, a square of size (size, size) will be cropped with this value.
-            If size is a sequence of length 2, an image of size (height, width) will be cropped.
-        interpolation (Inter, optional): Image interpolation mode. Default: Inter.LINEAR.
-            It can be any of [Inter.LINEAR, Inter.NEAREST, Inter.BICUBIC, Inter.AREA, Inter.PILCUBIC].
-
-            - Inter.LINEAR, means interpolation method is bilinear interpolation.
-
-            - Inter.NEAREST, means interpolation method is nearest-neighbor interpolation.
-
-            - Inter.BICUBIC, means interpolation method is bicubic interpolation.
-
-            - Inter.AREA, means interpolation method is pixel area interpolation.
-
-            - Inter.PILCUBIC, means interpolation method is bicubic interpolation like implemented in pillow, input
-              should be in 3 channels format.
+        top (int): Horizontal ordinate of the upper left corner of the crop region.
+        left (int): Vertical ordinate of the upper left corner of the crop region.
+        height (int): Height of the crop region.
+        width (int): Width of the cropp region.
+        size (Union[int, Sequence[int, int]]): The size of the output image.
+            If int is provided, the smaller edge of the image will be resized to this value,
+            keeping the image aspect ratio the same.
+            If Sequence[int, int] is provided, it should be (height, width).
+        interpolation (Inter, optional): Image interpolation method. Default: Inter.BILINEAR.
+            It can be Inter.LINEAR, Inter.NEAREST, Inter.BICUBIC, Inter.AREA or Inter.PILCUBIC.
+
+            - Inter.LINEAR, bilinear interpolation.
+            - Inter.NEAREST, nearest-neighbor interpolation.
+            - Inter.BICUBIC, bicubic interpolation.
+            - Inter.AREA, pixel area interpolation.
+            - Inter.PILCUBIC, cubic interpolation based on the implementation of Pillow
 
     Raises:
         TypeError: If `top` is not of type int.
+        ValueError: If `top` is negative.
         TypeError: If `left` is not of type int.
+        ValueError: If `left` is negative.
         TypeError: If `height` is not of type int.
+        ValueError: If `height` is not positive.
         TypeError: If `width` is not of type int.
-        TypeError: If `size` is not of type int or Sequence[int].
+        ValueError: If `width` is not positive.
+        TypeError: If `size` is not of type int or Sequence[int, int].
+        ValueError: If `size` is not posotive.
         TypeError: If `interpolation` is not of type :class:`mindspore.dataset.vision.Inter` .
-        RuntimeError: If given tensor shape is not <H, W> or <H, W, C>.
+        RuntimeError: If shape of the input image is not <H, W> or <H, W, C>.
 
     Supported Platforms:
         ``CPU``
@@ -3653,7 +3652,7 @@ class ResizeWithBBox(ImageTensorOperation):
 
     Raises:
         TypeError: If `size` is not of type int or Sequence[int].
-        TypeError: If `interpolation` is not of type Inter.
+        TypeError: If `interpolation` is not of type :class:`mindspore.dataset.vision.Inter` .
         ValueError: If `size` is not positive.
         RuntimeError: If given tensor shape is not <H, W> or <H, W, C>.
 
@@ -3688,8 +3687,8 @@ class RgbToHsv(PyTensorOperation):
     Convert the input numpy.ndarray images from RGB to HSV.
 
     Args:
-        is_hwc (bool): If True, means the input image is in shape of (H, W, C) or (N, H, W, C).
-            Otherwise, it is in shape of (C, H, W) or (N, C, H, W). Default: False.
+        is_hwc (bool): If True, means the input image is in shape of <H, W, C> or <N, H, W, C>.
+            Otherwise, it is in shape of <C, H, W> or <N, C, H, W>. Default: False.
 
     Raises:
         TypeError: If `is_hwc` is not of type bool.
@@ -3756,7 +3755,7 @@ class Rotate(ImageTensorOperation):
 
     Raises:
         TypeError: If `degrees` is not of type integer, float or sequence.
-        TypeError: If `resample` is not of type Inter.
+        TypeError: If `resample` is not of type :class:`mindspore.dataset.vision.Inter` .
         TypeError: If `expand` is not of type bool.
         TypeError: If `center` is not of type tuple.
         TypeError: If `fill_value` is not of type int or tuple[int].
@@ -3808,11 +3807,11 @@ class SlicePatches(ImageTensorOperation):
     Args:
         num_height (int, optional): The number of patches in vertical direction, which must be positive. Default: 1.
         num_width (int, optional): The number of patches in horizontal direction, which must be positive. Default: 1.
-        slice_mode (Inter, optional): A mode represents pad or drop. Default: SliceMode.PAD.
+        slice_mode (SliceMode, optional): A mode represents pad or drop. Default: SliceMode.PAD.
             It can be any of [SliceMode.PAD, SliceMode.DROP].
         fill_value (int, optional): The border width in number of pixels in
             right and bottom direction if slice_mode is set to be SliceMode.PAD.
-            The fill_value must be in range [0, 255]. Default: 0.
+            The `fill_value` must be in range [0, 255]. Default: 0.
 
     Raises:
         TypeError: If `num_height` is not of type integer.
@@ -3860,7 +3859,7 @@ class Solarize(ImageTensorOperation):
     Args:
         threshold (Union[float, Sequence[float, float]]): Range of solarize threshold, should always
             be in (min, max) format, where min and max are integers in range of [0, 255], and min <= max.
-            If min=max, then invert all pixel values above min(max).
+            If a single value is provided or min=max, then invert all pixel values above min(max).
 
     Raises:
         TypeError: If `threshold` is not of type float or Sequence[float, float].
@@ -3987,10 +3986,10 @@ class ToPIL(PyTensorOperation):
     Convert the input decoded numpy.ndarray image to PIL Image.
 
     Note:
-        The conversion mode will be determined by the data type using :class:`PIL.Image.fromarray` .
+        The conversion mode will be determined by the data type using `PIL.Image.fromarray` .
 
     Raises:
-        TypeError: If the input image is not of type :class:`numpy.ndarray` or :class:`PIL.Image.Image` .
+        TypeError: If the input image is not of type :class:`numpy.ndarray` or `PIL.Image.Image` .
 
     Supported Platforms:
         ``CPU``
@@ -4028,14 +4027,14 @@ class ToPIL(PyTensorOperation):
 class ToTensor(ImageTensorOperation):
     """
     Convert the input PIL Image or numpy.ndarray to numpy.ndarray of the desired dtype, rescale the pixel value
-    range from [0, 255] to [0.0, 1.0] and change the shape from (H, W, C) to (C, H, W).
+    range from [0, 255] to [0.0, 1.0] and change the shape from <H, W, C> to <C, H, W>.
 
     Args:
         output_type (Union[mindspore.dtype, numpy.dtype], optional): The desired dtype of the output image.
-            Default: :class:`numpy.float32` .
+            Default: `numpy.float32` .
 
     Raises:
-        TypeError: If the input image is not of type :class:`PIL.Image.Image` or :class:`numpy.ndarray` .
+        TypeError: If the input image is not of type `PIL.Image.Image` or :class:`numpy.ndarray` .
         TypeError: If dimension of the input image is not 2 or 3.
 
     Supported Platforms:
@@ -4079,13 +4078,13 @@ class ToType(TypeCast):
 
     Args:
         data_type (Union[mindspore.dtype, numpy.dtype]): The desired data type of the output image,
-            such as :class:`numpy.float32` .
+            such as `numpy.float32` .
 
     Raises:
         TypeError: If `data_type` is not of type :class:`mindspore.dtype` or :class:`numpy.dtype` .
 
     Supported Platforms:
-        ``CPU`` ``Ascend`` ``GPU``
+        ``Ascend`` ``GPU`` ``CPU``
 
     Examples:
         >>> import numpy as np
@@ -4103,36 +4102,36 @@ class ToType(TypeCast):
 
 class TrivialAugmentWide(ImageTensorOperation):
     """
-    Apply TrivialAugmentWide data augmentation method based on
+    Apply TrivialAugmentWide data augmentation method on the input image.
+
+    Refer to
     `TrivialAugmentWide: Tuning-free Yet State-of-the-Art Data Augmentation <https://arxiv.org/abs/2103.10158>`_ .
-    This operation works only with 3-channel RGB images.
+
+    Only support 3-channel RGB image.
 
     Args:
         num_magnitude_bins (int, optional): The number of different magnitude values,
             must be greater than or equal to 2. Default: 31.
-        interpolation (Inter, optional): Image interpolation mode for Resize operation. Default: Inter.NEAREST.
-            It can be any of [Inter.NEAREST, Inter.BILINEAR, Inter.BICUBIC, Inter.AREA].
-
-            - Inter.NEAREST: means interpolation method is nearest-neighbor interpolation.
+        interpolation (Inter, optional): Image interpolation method. Default: Inter.NEAREST.
+            It can be Inter.NEAREST, Inter.BILINEAR, Inter.BICUBIC or Inter.AREA.
 
-            - Inter.BILINEAR: means interpolation method is bilinear interpolation.
-
-            - Inter.BICUBIC: means the interpolation method is bicubic interpolation.
-
-            - Inter.AREA: means the interpolation method is pixel area interpolation.
+            - Inter.NEAREST, nearest-neighbor interpolation.
+            - Inter.BILINEAR, bilinear interpolation.
+            - Inter.BICUBIC, bicubic interpolation.
+            - Inter.AREA, pixel area interpolation.
 
-        fill_value (Union[int, tuple[int, int, int]], optional): Pixel fill value for the area outside
-            the transformed image.
-            It can be an int or a 3-tuple. If it is a 3-tuple, it is used to fill R, G, B channels respectively.
-            If it is an integer, it is used for all RGB channels. The fill_value values must be in range [0, 255]
-            Default: 0.
+        fill_value (Union[int, tuple[int, int, int]], optional): Pixel fill value for the area outside the
+            transformed image, must be in range of [0, 255]. Default: 0.
+            If int is provided, pad all RGB channels with this value.
+            If tuple[int, int, int] is provided, pad R, G, B channels respectively.
 
     Raises:
         TypeError: If `num_magnitude_bins` is not of type int.
         ValueError: If `num_magnitude_bins` is less than 2.
-        TypeError: If `interpolation` is not of type Inter.
-        TypeError: If `fill_value` is not an integer or a tuple of length 3.
-        RuntimeError: If given tensor shape is not <H, W, C>.
+        TypeError: If `interpolation` not of type :class:`mindspore.dataset.vision.Inter` .
+        TypeError: If `fill_value` is not of type int or tuple[int, int, int].
+        ValueError: If `fill_value` is not in range of [0, 255].
+        RuntimeError: If shape of the input image is not <H, W, C>.
 
     Supported Platforms:
         ``CPU``