pulsatrix::NormalizeTransform Class Reference

Per-channel normalization: pixel = (pixel - mean[c]) / std[c]. In-place, no backend needed (same shape in and out). More...

#include <image_transforms.hpp>

Inheritance diagram for pulsatrix::NormalizeTransform:

Collaboration diagram for pulsatrix::NormalizeTransform:

Public Member Functions
	NormalizeTransform (std::vector< float > mean, std::vector< float > std)
Sample	apply (Sample sample) const override
	Applies this transform to a sample.
Public Member Functions inherited from pulsatrix::Transform
virtual	~Transform ()=default

Detailed Description

Per-channel normalization: pixel = (pixel - mean[c]) / std[c]. In-place, no backend needed (same shape in and out).

Exceptions

std::invalid_argument

if mean/std size doesn't match the image's channel count.

Constructor & Destructor Documentation

NormalizeTransform()

pulsatrix::NormalizeTransform::NormalizeTransform ( std::vector< float >  mean, std::vector< float >  std  )

inline

Member Function Documentation

apply()

Sample pulsatrix::NormalizeTransform::apply ( Sample  sample ) const

overridevirtual

Applies this transform to a sample.

Parameters

sample

Input sample.

Returns

The transformed sample.

Implements pulsatrix::Transform.

---

The documentation for this class was generated from the following file:

• include/pulsatrix/image_transforms.hpp