facenet

package

v0.0.0-...-21979d2 Latest Latest Go to latest Published: Oct 13, 2019 License: MIT Imports: 13 Imported by: 0

Details

Valid go.mod file

The Go module system was introduced in Go 1.11 and is the official dependency management solution for Go.
Redistributable license

Redistributable licenses place minimal restrictions on how software can be used, modified, and redistributed.
Tagged version

Modules with tagged versions give importers more predictable builds.
Stable version

When a project reaches major version v1 it is considered stable.
Learn more about best practices

This section is empty.

This section is empty.

func CountMean(img [][][]float32) (mean, std float32)

func TensorFromImg(img image.Image) (output *tf.Tensor, err error)

func TensorFromMat(mat gocv.Mat) (output *tf.Tensor, err error)

type Facenet struct {
	FacenetModel    *tf.Graph
	NormalizerGraph *tf.Graph
	FacenetSession  *tf.Session
}

func NewFacenet(modelfile string) (facenet Facenet, err error)

func (fnet Facenet) BeginSession(self *Facenet) (err error)

func (fnet Facenet) Close(self *Facenet) error

func (fnet Facenet) ExtractFeatures(tensor *tf.Tensor) ([]float32, error)

run the image through the model to generate embedding

func (fnet Facenet) Normalize(tensor *tf.Tensor) (tensorout *tf.Tensor, err error)

Creates a graph to decode, rezise and normalize an image

func (fnet Facenet) PrepareMat(img gocv.Mat) (output *tf.Tensor, err error)

prepares a gocv.Mat with preprocessing before generating embedding, return a tensor containing processed image

func (fnet Facenet) Preprocess(img image.Image) (output *tf.Tensor, err error)

prepares image with preprocessing before generating embedding, return a tensor containing processed image