tensor

package
v1.52.0 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Jun 28, 2026 License: MIT Imports: 11 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type Config

type Config struct {
	Skip                    bool           `yaml:"skip,omitempty"`
	ForceCpu                bool           `yaml:"forceCpu,omitempty"`
	Padding                 int            `yaml:"padding,omitempty"`
	ModelFile               string         `yaml:"modelFile,omitempty"`
	ConfigFile              string         `yaml:"configFile,omitempty"`
	DescFile                string         `yaml:"descFile,omitempty"`
	ScaleWidth              int            `yaml:"scaleWidth,omitempty"`
	MinConfidencePercentage int            `yaml:"minConfidencePercentage,omitempty"`
	MinMotionFrames         int            `yaml:"minMotionFrames,omitempty"`
	MinPercentage           int            `yaml:"minPercentage,omitempty"`
	MaxPercentage           int            `yaml:"maxPercentage,omitempty"`
	MinOverlapPercentage    int            `yaml:"minOverlapPercentage,omitempty"`
	SameOverlapPercentage   int            `yaml:"sameOverlapPercentage,omitempty"`
	AllowedList             []string       `yaml:"allowedList,omitempty"`
	PriorityList            []PriorityItem `yaml:"priorityList,omitempty"`
	HighlightColor          string         `yaml:"highlightColor,omitempty"`
	HighlightThickness      int            `yaml:"highlightThickness,omitempty"`
}

Config contains the parameters for tensor detection

func NewConfig

func NewConfig(configPath string) *Config

NewConfig creates a new Config

type PriorityItem added in v1.52.0

type PriorityItem struct {
	Description             string `yaml:"description"`
	MinConfidencePercentage int    `yaml:"minConfidencePercentage"`
}

PriorityItem defines a detection description that takes priority over other descriptions when deduplicating overlapping detections. Items earlier in the priority list outrank later ones.

type Tensor

type Tensor struct {
	Name string
	Skip bool
	// contains filtered or unexported fields
}

Tensor detects objects within images

func NewTensor

func NewTensor(name string) *Tensor

NewTensor creates a new Tensor

func (*Tensor) Run

func (t *Tensor) Run(input <-chan videosource.ProcessedImage) <-chan videosource.ProcessedImage

Run starts the tensor detection process

func (*Tensor) SetConfig

func (t *Tensor) SetConfig(config *Config)

SetConfig on tensor

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL