Class AutoContrast
Defined in File vision.h
Inheritance Relationships
Base Type
public mindspore::dataset::TensorTransform
(Class TensorTransform)
Class Documentation
-
class AutoContrast : public mindspore::dataset::TensorTransform
Apply automatic contrast on the input image.
Public Functions
-
explicit AutoContrast(float cutoff = 0.0, const std::vector<uint32_t> &ignore = {})
Constructor.
- Example
/* Define operations */ auto decode_op = vision::Decode(); auto autocontrast_op = vision::AutoContrast(10.0, {10, 20}); /* dataset is an instance of Dataset object */ dataset = dataset->Map({decode_op, autocontrast_op}, // operations {"image"}); // input columns
- Parameters
cutoff – [in] Percent of pixels to cut off from the histogram, the valid range of cutoff value is 0 to 50.
ignore – [in] Pixel values to ignore.
-
~AutoContrast() = default
Destructor.
-
explicit AutoContrast(float cutoff = 0.0, const std::vector<uint32_t> &ignore = {})