mindspore.dataset.vision.CenterCrop

View Source On Gitee
class mindspore.dataset.vision.CenterCrop(size)[source]

Crop the input image at the center to the given size. If input image size is smaller than output size, input image will be padded with 0 before cropping.

Parameters

size (Union[int, sequence]) – The output size of the cropped image. If size is an integer, a square crop of size (size, size) is returned. If size is a sequence of length 2, it should be (height, width). The size value(s) must be larger than 0.

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>.

Supported Platforms:

CPU

Examples

>>> import mindspore.dataset as ds
>>> import mindspore.dataset.vision as vision
>>>
>>> image_folder_dataset = ds.ImageFolderDataset("/path/to/image_folder_dataset_directory")
>>>
>>> # crop image to a square
>>> transforms_list1 = [vision.Decode(), vision.CenterCrop(50)]
>>> image_folder_dataset = image_folder_dataset.map(operations=transforms_list1,
...                                                 input_columns=["image"])
>>> # crop image to portrait style
>>> transforms_list2 = [vision.Decode(), vision.CenterCrop((60, 40))]
>>> image_folder_dataset = image_folder_dataset.map(operations=transforms_list2,
...                                                 input_columns=["image"])
Tutorial Examples: