mindspore.dataset.vision.ResizedCrop

class mindspore.dataset.vision.ResizedCrop(top, left, height, width, size, interpolation=Inter.BILINEAR)

Crop the input image at a specific region and resize it to desired size.

Supports Ascend hardware acceleration and can be enabled through the .device("Ascend") method.

Parameters

• 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 defined by Inter . Default: Inter.BILINEAR.

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.

• 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 Inter .

• RuntimeError – If shape of the input image is not <H, W> or <H, W, C>.

Supported Platforms:

CPU Ascend

Examples

>>> import numpy as np
>>> import mindspore.dataset as ds
>>> import mindspore.dataset.vision as vision
>>> from mindspore.dataset.vision import Inter
>>>
>>> # Use the transform in dataset pipeline mode
>>> transforms_list = [vision.ResizedCrop(0, 0, 64, 64, (100, 75), Inter.BILINEAR)]
>>> data = np.random.randint(0, 255, size=(1, 100, 100, 3)).astype(np.uint8)
>>> numpy_slices_dataset = ds.NumpySlicesDataset(data, ["image"])
>>> numpy_slices_dataset = numpy_slices_dataset.map(operations=transforms_list, input_columns=["image"])
>>> for item in numpy_slices_dataset.create_dict_iterator(num_epochs=1, output_numpy=True):
...     print(item["image"].shape, item["image"].dtype)
...     break
(100, 75, 3) uint8
>>>
>>> # Use the transform in eager mode
>>> data = np.random.randint(0, 255, size=(100, 100, 3)).astype(np.uint8)
>>> output = vision.ResizedCrop(0, 0, 1, 1, (5, 5), Inter.BILINEAR)(data)
>>> print(output.shape, output.dtype)
(5, 5, 3) uint8

Tutorial Examples:

• Illustration of vision transforms

device(device_target='CPU')

Set the device for the current operator execution.

When the device is Ascend, input type supports uint8 and float32, input channel supports 1 and 3. The input data has a height limit of [4, 32768] and a width limit of [6, 32768].

Parameters

device_target (str, optional) – The operator will be executed on this device. Currently supports "CPU" and "Ascend" . Default: "CPU" .

Raises

• TypeError – If device_target is not of type str.

• ValueError – If device_target is not within the valid set of ["CPU", "Ascend"].

Supported Platforms:

CPU Ascend

Examples

>>> import numpy as np
>>> import mindspore.dataset as ds
>>> import mindspore.dataset.vision as vision
>>> from mindspore.dataset.vision import Inter
>>>
>>> # Use the transform in dataset pipeline mode
>>> data = np.random.randint(0, 255, size=(1, 100, 100, 3)).astype(np.uint8)
>>> numpy_slices_dataset = ds.NumpySlicesDataset(data, ["image"])
>>> resize_crop_op = vision.ResizedCrop(0, 0, 64, 64, (100, 75)).device("Ascend")
>>> transforms_list = [resize_crop_op]
>>> numpy_slices_dataset = numpy_slices_dataset.map(operations=transforms_list, input_columns=["image"])
>>> for item in numpy_slices_dataset.create_dict_iterator(num_epochs=1, output_numpy=True):
...     print(item["image"].shape, item["image"].dtype)
...     break
(100, 75, 3) uint8
>>>
>>> # Use the transform in eager mode
>>> data = np.random.randint(0, 255, size=(100, 100, 3)).astype(np.uint8)
>>> output = vision.ResizedCrop(0, 0, 64, 64, (32, 16), Inter.BILINEAR).device("Ascend")(data)
>>> print(output.shape, output.dtype)
(32, 16, 3) uint8

Tutorial Examples:

• Illustration of vision transforms