Class NormalizePad

Inheritance Relationships

Base Type

Class Documentation

class NormalizePad : public mindspore::dataset::TensorTransform

Normalize the input image with respect to mean and standard deviation and pads an extra channel with value zero.

Public Functions

inline NormalizePad(const std::vector<float> &mean, const std::vector<float> &std, const std::string &dtype = "float32", bool is_hwc = true)

Constructor.

Parameters

  • mean – [in] A vector of mean values for each channel, with respect to channel order. The mean values must be in range [0.0, 255.0].

  • std – [in] A vector of standard deviations for each channel, with respect to channel order. The standard deviation values must be in range (0.0, 255.0].

  • dtype – [in] The output datatype of Tensor. The standard deviation values must be “float32” or “float16”（default = “float32”）.

  • is_hwc – [in] A boolean to indicate whether the input image is in HWC format (true) or CHW format (false) (default = true).

样例
/* Define operations */
auto decode_op = vision::Decode();
auto normalize_pad_op = vision::NormalizePad({121.0, 115.0, 100.0}, {70.0, 68.0, 71.0});

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

Destructor.