mindspore.dataset.vision.Rescale

View Source On Gitee
class mindspore.dataset.vision.Rescale(rescale, shift)[source]

Rescale the input image with the given rescale and shift. This operation will rescale the input image with: output = image * rescale + shift.

Note

This operation is executed on the CPU by default, but it is also supported to be executed on the GPU or Ascend via heterogeneous acceleration.

Parameters

  • rescale (float) – Rescale factor.

  • shift (float) – Shift factor.

Raises

  • TypeError – If rescale is not of type float.

  • TypeError – If shift is not of type float.

Supported Platforms:

CPU GPU Ascend

Examples

>>> import numpy as np
>>> import mindspore.dataset as ds
>>> import mindspore.dataset.vision as vision
>>>
>>> # 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"])
>>> transforms_list = [vision.Rescale(1.0 / 255.0, -1.0)]
>>> 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, 100, 3) float32
>>>
>>> # Use the transform in eager mode
>>> data = np.random.randint(0, 255, size=(100, 100, 3)).astype(np.uint8)
>>> output = vision.Rescale(1.0 / 255.0, -1.0)(data)
>>> print(output.shape, output.dtype)
(100, 100, 3) float32
Tutorial Examples: