Class RandAugment

Inheritance Relationships

Base Type

Class Documentation

class RandAugment : public mindspore::dataset::TensorTransform

Apply RandAugment data augmentation method.

Public Functions

explicit RandAugment(int32_t num_ops = 2, int32_t magnitude = 9, int32_t num_magnitude_bins = 31, InterpolationMode interpolation = InterpolationMode::kNearestNeighbour, const std::vector<uint8_t> &fill_value = {0, 0, 0})

Constructor.

Example
/* Define operations */
auto decode_op = vision::Decode();
auto rand_augment_op = vision::RandAugment();
/* dataset is an instance of Dataset object */
dataset = dataset->Map({decode_op, rand_augment_op}, // operations
                       {"image"});                   // input columns

Parameters

  • num_ops – [in] Number of augmentation transformations to apply sequentially. Default: 2.

  • magnitude – [in] Magnitude for all the transformations. Default: 9.

  • num_magnitude_bins – [in] The number of different magnitude values. Default: 31.

  • interpolation – [in] An enum for the mode of interpolation. Default: InterpolationMode::kNearestNeighbour.

    • InterpolationMode::kLinear, Interpolation method is blinear interpolation.

    • InterpolationMode::kNearestNeighbour, Interpolation method is nearest-neighbor interpolation.

    • InterpolationMode::kCubic, Interpolation method is bicubic interpolation.

  • fill_value – [in] A vector representing the pixel intensity of the borders. Default: {0, 0, 0}.

~RandAugment() = default

Destructor.