Class RandomAutoContrast

Inheritance Relationships

Base Type

Class Documentation

class RandomAutoContrast : public mindspore::dataset::TensorTransform

Automatically adjust the contrast of the image with a given probability.

Public Functions

explicit RandomAutoContrast(float cutoff = 0.0, const std::vector<uint32_t> &ignore = {}, float prob = 0.5)

Constructor.

参数
  • cutoff[in] Percent of the lightest and darkest pixels to be cut off from the histogram of the input image. The value must be in range of [0.0, 50.0) (default=0.0).

  • ignore[in] The background pixel values to be ignored, each of which must be in range of [0, 255] (default={}).

  • prob[in] A float representing the probability of AutoContrast, which must be in range of 0, 1.

样例
/* Define operations */
auto decode_op = vision::Decode();
auto random_auto_contrast_op = vision::RandomAutoContrast(5.0);

/* dataset is an instance of Dataset object */
dataset = dataset->Map({decode_op, random_auto_contrast_op},  // operations
                       {"image"});                            // input columns
~RandomAutoContrast() = default

Destructor.