update hand landmarks model

demo/typescript/index.js

@@ -9,9 +9,15 @@ import Human from "../../dist/human.esm.js";
 var config = {
   modelBasePath: "../../models",
   backend: "humangl",
-  async: true
+  async: true,
+  face: { enabled: true },
+  body: { enabled: true },
+  hand: { enabled: true },
+  object: { enabled: false },
+  gesture: { enabled: true }
 };
 var human = new Human(config);
+human.env.perfadd = false;
 var result;
 var dom = {
   video: document.getElementById("video"),
@@ -80,7 +86,6 @@ async function drawLoop() {
 async function main() {
   log("human version:", human.version, "tfjs:", human.tf.version_core);
   log("platform:", human.env.platform, "agent:", human.env.agent);
-  human.env.perfadd = true;
   status("loading...");
   await human.load();
   status("initializing...");

demo/typescript/index.ts

@@ -7,15 +7,23 @@
  * @license MIT
  */
 
+/// <reference path="../../types/src//human.d.ts" />
+
 import Human from '../../dist/human.esm.js'; // equivalent of @vladmandic/human
 
 const config = {
   modelBasePath: '../../models',
   backend: 'humangl',
   async: true,
+  face: { enabled: true },
+  body: { enabled: true },
+  hand: { enabled: true },
+  object: { enabled: false },
+  gesture: { enabled: true },
 };
 
 const human = new Human(config);
+human.env.perfadd = false;
 let result;
 
 const dom = {
@@ -88,7 +96,6 @@ async function drawLoop() {
 async function main() {
   log('human version:', human.version, 'tfjs:', human.tf.version_core);
   log('platform:', human.env.platform, 'agent:', human.env.agent);
-  human.env.perfadd = true;
   status('loading...');
   await human.load();
   status('initializing...');

src/config.ts

@@ -348,7 +348,7 @@ const config: Config = {
       modelPath: 'handtrack.json',
     },
     skeleton: {
-      modelPath: 'handskeleton.json',
+      modelPath: 'handlandmark-full.json',
     },
   },
   object: {

src/hand/handtrack.ts

@@ -156,7 +156,7 @@ async function detectFingers(input: Tensor, h: HandDetectResult, config: Config)
     t.crop = tf.image.cropAndResize(input, [h.boxCrop], [0], [inputSize[1][0], inputSize[1][1]], 'bilinear');
     t.cast = tf.cast(t.crop, 'float32');
     t.div = tf.div(t.cast, 255);
-    [t.score, t.keypoints] = models[1].execute(t.div) as Tensor[];
+    [t.score, t.keypoints] = models[1].execute(t.div, ['Identity_1', 'Identity']) as Tensor[];
     const rawScore = (await t.score.data())[0];
     const score = (100 - Math.trunc(100 / (1 + Math.exp(rawScore)))) / 100; // reverse sigmoid value
     if (score >= (config.hand.minConfidence || 0)) {