mindspore.dataset.vision.AdjustGamma

class mindspore.dataset.vision.AdjustGamma(gamma, gain=1)[source]

Apply gamma correction on input image. Input image is expected to be in <…, H, W, C> or <H, W> format.

\[I_{\text{out}} = 255 \times \text{gain} \times \left(\frac{I_{\text{in}}}{255}\right)^{\gamma}\]

See Gamma Correction for more details.

Parameters

  • gamma (float) – Non negative real number. The output image pixel value is exponentially related to the input image pixel value. gamma larger than 1 make the shadows darker, while gamma smaller than 1 make dark regions lighter.

  • gain (float, optional) – The constant multiplier. Default: 1.0.

Raises

  • TypeError – If gain is not of type float.

  • TypeError – If gamma is not of type float.

  • ValueError – If gamma is less than 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")
>>> transforms_list = [vision.Decode(), vision.AdjustGamma(gamma=10.0, gain=1.0)]
>>> image_folder_dataset = image_folder_dataset.map(operations=transforms_list,
...                                                 input_columns=["image"])
Tutorial Examples: