Config | @vladmandic/human

Configuration interface definition for Human library

Contains all configurable parameters

Hierarchy

Config

Index

Properties

async

async: boolean

Perform model loading and inference concurrently or sequentially

backend

Backend used for TFJS operations Valid build-in backends are:

Browser: cpu, wasm, webgl, humangl
NodeJS: cpu, wasm, tensorflow

Experimental:

Browser: webgpu - requires custom build of tfjs-backend-webgpu

Defaults: humangl for browser and tensorflow for nodejs

body

body: Partial<BodyConfig>

BodyConfig

cacheSensitivity

cacheSensitivity: number

Cache sensitivity

values 0..1 where 0.01 means reset cache if input changed more than 1%
set to 0 to disable caching

debug

debug: boolean

Print debug statements to console

face

face: Partial<FaceConfig>

FaceConfig

filter

filter: Partial<FilterConfig>

Run input through image filters before inference

image filters run with near-zero latency as they are executed on the GPU

FilterConfig

gesture

gesture: Partial<GestureConfig>

GestureConfig

hand

hand: Partial<HandConfig>

HandConfig

modelBasePath

modelBasePath: string

Base model path (typically starting with file://, http:// or https://) for all models

individual modelPath values are relative to this path

object

object: Partial<ObjectConfig>

ObjectConfig

segmentation

segmentation: Partial<SegmentationConfig>

SegmentationConfig

skipFrame

skipFrame: boolean

Internal Variable

warmup

warmup: "face" | "body" | "none" | "full"

What to use for human.warmup()

warmup pre-initializes all models for faster inference but can take significant time on startup

wasmPath

wasmPath: string

Path to *.wasm files if backend is set to wasm

if not set, auto-detects to link to CDN jsdelivr when running in browser