Class CenterCrop

Defined in File vision_lite.h

Inheritance Relationships

Base Type

public mindspore::dataset::TensorTransform (Class TensorTransform)

Class Documentation

class CenterCrop : public mindspore::dataset::TensorTransform 

Crop the input image at the center to the given size.

Public Functions

explicit CenterCrop(const std::vector<int32_t> &size)

Constructor.

参数

size – [in] A vector representing the output size of the cropped image. If the size is a single value, a squared crop of size (size, size) is returned. If the size has 2 values, it should be (height, width).

样例

/* Define operations */
auto decode_op = vision::Decode();
auto crop_op = vision::CenterCrop({32, 32});

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

~CenterCrop() = default: Destructor.