mindspore.nn.CentralCrop

class mindspore.nn.CentralCrop(central_fraction)[source]

Crops the centeral region of the images with the central_fraction.

Parameters

central_fraction (float) – Fraction of size to crop. It must be float and in range (0.0, 1.0].

Inputs:
  • image (Tensor) - A 3-D tensor of shape [C, H, W], or a 4-D tensor of shape [N, C, H, W].

Outputs:

Tensor, 3-D or 4-D float tensor, according to the input.

Raises
  • TypeError – If central_fraction is not a float.

  • ValueError – If central_fraction is not in range (0, 1.0].

Supported Platforms:

Ascend GPU CPU

Examples

>>> net = nn.CentralCrop(central_fraction=0.5)
>>> image = Tensor(np.random.random((4, 3, 4, 4)), mindspore.float32)
>>> output = net(image)
>>> print(output.shape)
(4, 3, 2, 2)