codelab

package module

v0.0.0-...-efabd05 Latest Latest Go to latest Published: May 10, 2018 License: MIT Imports: 5 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

Shows how to load a model and run inference in Go. Slides: http://vmarkovtsev.github.io/codelab-2018-aalborg/

To be used in:

This section is empty.

View Source

var ImagenetClasses = [1001]string{}/* 1001 elements not displayed */

ImagenetClasses holds the Imagenet class names. Source github.com/tensorflow/models/research/slim/datasets/imagenet.py

func GetInputShape(graph *tf.Graph) (width, height int)

GetInputShape finds the input image dimensions.

func LoadImage(path string, width, height int) ([][][3]float32, error)

LoadImage reads an image from FS and converts it to [-1, 1] RGB float32 format.

func RunInference(graph *tf.Graph, session *tf.Session, image [][][3]float32) ([]float32, error)

RunInference executes the model and returns the logits.

type Confidence struct {
	Value float32
	Index int
}

Confidence is a pair of logit value and the corresponding class index.

func SelectTopN(confs []float32, n int) []Confidence

SelectTopN chooses the biggest n logits.