mindspore.dataset.vision.NormalizePad

class mindspore.dataset.vision.NormalizePad(mean, std, dtype='float32', is_hwc=True)[source]

Normalize the input image with respect to mean and standard deviation then pad an extra channel with value zero.

Parameters

  • mean (sequence) – List or tuple of mean values for each channel, with respect to channel order. The mean values must be in range (0.0, 255.0].

  • std (sequence) – List or tuple of standard deviations for each channel, with respect to channel order. The standard deviation values must be in range (0.0, 255.0].

  • dtype (str, optional) – Set the output data type of normalized image. Default: "float32".

  • is_hwc (bool, optional) – Specify the format of input image. True - HWC format, False - CHW format. Default: True.

Raises

  • TypeError – If mean is not of type sequence.

  • TypeError – If std is not of type sequence.

  • TypeError – If dtype is not of type string.

  • TypeError – If is_hwc is not of type bool.

  • ValueError – If mean is not in range [0.0, 255.0].

  • ValueError – If mean is not in range (0.0, 255.0].

  • RuntimeError – If given tensor shape is not <H, W>, <H, W, C> or <C, H, W>.

Supported Platforms:

CPU

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"])
>>> normalize_pad_op = vision.NormalizePad(mean=[121.0, 115.0, 100.0],
...                                        std=[70.0, 68.0, 71.0],
...                                        dtype="float32")
>>> transforms_list = [normalize_pad_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, 100, 4) float32
>>>
>>> # Use the transform in eager mode
>>> data = np.random.randint(0, 255, size=(100, 100, 3)).astype(np.uint8)
>>> output = vision.NormalizePad(mean=[121.0, 115.0, 100.0], std=[70.0, 68.0, 71.0], dtype="float32")(data)
>>> print(output.shape, output.dtype)
(100, 100, 4) float32