ambiser
/
human
mirror of https://github.com/vladmandic/human
9
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

switch to async data reads

pull/193/head
Vladimir Mandic 2021-08-12 09:31:16 -04:00
parent 86abe96b81
commit 85ac90c4e9
26 changed files with 127 additions and 104 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
CHANGELOG.md
View File

@ -1,6 +1,6 @@
# @vladmandic/human # @vladmandic/human
Version: **2.1.2** Version: **2.1.3**
Description: **Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gesture Recognition** Description: **Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gesture Recognition**
Author: **Vladimir Mandic <mandic00@live.com>** Author: **Vladimir Mandic <mandic00@live.com>**
@ -9,7 +9,10 @@ Repository: **<git+https://github.com/vladmandic/human.git>**
## Changelog ## Changelog
### **HEAD -> main** 2021/08/09 mandic00@live.com ### **2.1.3** 2021/08/12 mandic00@live.com
### **origin/main** 2021/08/11 mandic00@live.com
- minor update - minor update
- replace movenet with lightning-v4 - replace movenet with lightning-v4

41
TODO.md
View File

@ -21,31 +21,50 @@ WebGL shader optimizations for faster load and initial detection
- Optical Flow: <https://docs.opencv.org/3.3.1/db/d7f/tutorial_js_lucas_kanade.html> - Optical Flow: <https://docs.opencv.org/3.3.1/db/d7f/tutorial_js_lucas_kanade.html>
- TFLite Models: <https://js.tensorflow.org/api_tflite/0.0.1-alpha.4/> - TFLite Models: <https://js.tensorflow.org/api_tflite/0.0.1-alpha.4/>
<br>
## Known Issues ## Known Issues
### Object Detection <br>
Object detection using CenterNet or NanoDet models is not working when using WASM backend due to missing kernel ops in TFJS
*Target: `Human` v2.2 with `TFJS` v3.9*
- CenterNet with WASM: <https://github.com/tensorflow/tfjs/issues/5110>
- NanoDet with WASM: <https://github.com/tensorflow/tfjs/issues/4824>
### Face Detection ### Face Detection
Enhanced rotation correction for face detection is not working in NodeJS due to missing kernel op in TFJS Enhanced rotation correction for face detection is not working in NodeJS due to missing kernel op in TFJS
Feature is automatically disabled in NodeJS without user impact Feature is automatically disabled in NodeJS without user impact
*Target: `Human` v2.2 with `TFJS` v3.9*
- BlazeFace rotation correction in NodeJS: <https://github.com/tensorflow/tfjs/issues/4066> - Backend NodeJS missing kernel op `FlipLeftRight`
<https://github.com/tensorflow/tfjs/issues/4066>
*Target: `Human` v2.2 with `TFJS` v3.9*
- Backend NodeJS missing kernel op `RotateWithOffset`
<https://github.com/tensorflow/tfjs/issues/5473>
*Target: N/A*
<br>
### Hand Detection ### Hand Detection
Enhanced rotation correction for hand detection is not working in NodeJS due to missing kernel op in TFJS Enhanced rotation correction for hand detection is not working in NodeJS due to missing kernel op in TFJS
Feature is automatically disabled in NodeJS without user impact Feature is automatically disabled in NodeJS without user impact
*Target: `Human` v2.2 with `TFJS` v3.9*
- HandPose rotation correction in NodeJS: <https://github.com/tensorflow/tfjs/issues/4066> - Backend NodeJS missing kernel op `FlipLeftRight`
<https://github.com/tensorflow/tfjs/issues/4066>
*Target: `Human` v2.2 with `TFJS` v3.9*
- Backend NodeJS missing kernel op `RotateWithOffset`
<https://github.com/tensorflow/tfjs/issues/5473>
*Target: N/A*
Hand detection using WASM backend has reduced precision due to math rounding errors in backend Hand detection using WASM backend has reduced precision due to math rounding errors in backend
*Target: N/A* *Target: N/A*
<br>
### Object Detection
Object detection using CenterNet or NanoDet models is not working when using WASM backend due to missing kernel ops in TFJS
- Backend WASM missing kernel op `Mod`
<https://github.com/tensorflow/tfjs/issues/5110>
*Target: `Human` v2.2 with `TFJS` v3.9*
- Backend WASM missing kernel op `SparseToDense`
<https://github.com/tensorflow/tfjs/issues/4824>
*Target: `Human` v2.2 with `TFJS` v3.9*

2
demo/nodejs/node.js
View File

@ -121,7 +121,7 @@ async function detect(input) {
if (result && result.hand && result.hand.length > 0) { if (result && result.hand && result.hand.length > 0) {
for (let i = 0; i < result.hand.length; i++) { for (let i = 0; i < result.hand.length; i++) {
const hand = result.hand[i]; const hand = result.hand[i];
log.data(` Hand: #${i} score:${hand.score}`); log.data(` Hand: #${i} score:${hand.score} keypoints:${hand.keypoints?.length}`);
} }
} else { } else {
log.data(' Hand: N/A'); log.data(' Hand: N/A');

12
dist/human.esm-nobundle.js vendored
View File

File diff suppressed because one or more lines are too long

4
dist/human.esm-nobundle.js.map vendored
View File

File diff suppressed because one or more lines are too long

6
dist/human.esm.js vendored
View File

File diff suppressed because one or more lines are too long

4
dist/human.esm.js.map vendored
View File

File diff suppressed because one or more lines are too long

6
dist/human.js vendored
View File

File diff suppressed because one or more lines are too long

20
dist/human.node-gpu.js vendored
View File

@ -4306,7 +4306,7 @@ async function predict3(image18, config3, idx, count2) {
const obj = []; const obj = [];
if (config3.face.emotion.enabled) { if (config3.face.emotion.enabled) {
const emotionT = await model2.predict(normalize); const emotionT = await model2.predict(normalize);
const data = emotionT.dataSync(); const data = await emotionT.data();
tf7.dispose(emotionT); tf7.dispose(emotionT);
for (let i = 0; i < data.length; i++) { for (let i = 0; i < data.length; i++) {
if (data[i] > config3.face.emotion.minConfidence) if (data[i] > config3.face.emotion.minConfidence)
@ -7704,7 +7704,7 @@ var HandDetector = class {
const predictions = tf10.squeeze(batched); const predictions = tf10.squeeze(batched);
tf10.dispose(batched); tf10.dispose(batched);
const scoresT = tf10.tidy(() => tf10.squeeze(tf10.sigmoid(tf10.slice(predictions, [0, 0], [-1, 1])))); const scoresT = tf10.tidy(() => tf10.squeeze(tf10.sigmoid(tf10.slice(predictions, [0, 0], [-1, 1]))));
const scores = scoresT.dataSync(); const scores = await scoresT.data();
const rawBoxes = tf10.slice(predictions, [0, 1], [-1, 4]); const rawBoxes = tf10.slice(predictions, [0, 1], [-1, 4]);
const boxes = this.normalizeBoxes(rawBoxes); const boxes = this.normalizeBoxes(rawBoxes);
tf10.dispose(rawBoxes); tf10.dispose(rawBoxes);
@ -7736,7 +7736,7 @@ var HandDetector = class {
if (!predictions || predictions.length === 0) if (!predictions || predictions.length === 0)
return hands; return hands;
for (const prediction of predictions) { for (const prediction of predictions) {
const boxes = prediction.box.dataSync(); const boxes = await prediction.box.data();
const startPoint = boxes.slice(0, 2); const startPoint = boxes.slice(0, 2);
const endPoint = boxes.slice(2, 4); const endPoint = boxes.slice(2, 4);
const palmLandmarks = await prediction.palmLandmarks.array(); const palmLandmarks = await prediction.palmLandmarks.array();
@ -8125,7 +8125,6 @@ async function load7(config3) {
return model4; return model4;
} }
async function predict6(image18, config3) { async function predict6(image18, config3) {
var _a;
if (!model4) if (!model4)
return []; return [];
if (!config3.body.enabled) if (!config3.body.enabled)
@ -8135,7 +8134,8 @@ async function predict6(image18, config3) {
const normalize = tf13.div(resize, [255]); const normalize = tf13.div(resize, [255]);
tf13.dispose(resize); tf13.dispose(resize);
const resT = await model4.predict(normalize); const resT = await model4.predict(normalize);
const points = ((_a = resT.find((t) => t.size === 195 || t.size === 155)) == null ? void 0 : _a.dataSync()) || []; const findT = resT.find((t) => t.size === 195 || t.size === 155);
const points = await (findT == null ? void 0 : findT.data()) || [];
resT.forEach((t) => tf13.dispose(t)); resT.forEach((t) => tf13.dispose(t));
tf13.dispose(normalize); tf13.dispose(normalize);
const keypoints3 = []; const keypoints3 = [];
@ -8516,7 +8516,7 @@ async function process2(res, inputSize, outputShape, config3) {
let nmsIdx = []; let nmsIdx = [];
if (nmsBoxes && nmsBoxes.length > 0) { if (nmsBoxes && nmsBoxes.length > 0) {
const nms = await tf16.image.nonMaxSuppressionAsync(nmsBoxes, nmsScores, config3.object.maxDetected, config3.object.iouThreshold, config3.object.minConfidence); const nms = await tf16.image.nonMaxSuppressionAsync(nmsBoxes, nmsScores, config3.object.maxDetected, config3.object.iouThreshold, config3.object.minConfidence);
nmsIdx = nms.dataSync(); nmsIdx = await nms.data();
tf16.dispose(nms); tf16.dispose(nms);
} }
results = results.filter((_val, idx) => nmsIdx.includes(idx)).sort((a, b) => b.score - a.score); results = results.filter((_val, idx) => nmsIdx.includes(idx)).sort((a, b) => b.score - a.score);
@ -8583,7 +8583,7 @@ async function process3(res, inputSize, outputShape, config3) {
tf17.dispose(boxesT); tf17.dispose(boxesT);
tf17.dispose(scoresT); tf17.dispose(scoresT);
tf17.dispose(classesT); tf17.dispose(classesT);
const nms = nmsT.dataSync(); const nms = await nmsT.data();
tf17.dispose(nmsT); tf17.dispose(nmsT);
let i = 0; let i = 0;
for (const id of nms) { for (const id of nms) {
@ -9527,7 +9527,7 @@ async function predict11(input) {
resizeOutput = tf19.image.resizeBilinear(squeeze7, [width, height]); resizeOutput = tf19.image.resizeBilinear(squeeze7, [width, height]);
} }
if (typeof document === "undefined") if (typeof document === "undefined")
return resizeOutput.dataSync(); return resizeOutput.data();
const overlay = typeof OffscreenCanvas !== "undefined" ? new OffscreenCanvas(width, height) : document.createElement("canvas"); const overlay = typeof OffscreenCanvas !== "undefined" ? new OffscreenCanvas(width, height) : document.createElement("canvas");
overlay.width = width; overlay.width = width;
overlay.height = height; overlay.height = height;
@ -11331,7 +11331,7 @@ lBhEMohlFerLlBjEMohMVTEARDKCITsAk2AEgAAAkAAAAAAAAAAAAAAAAAAAAAAAASAAAAAAAAD/
2Q==`; 2Q==`;
// package.json // package.json
var version = "2.1.2"; var version = "2.1.3";
// src/human.ts // src/human.ts
var _numTensors, _analyzeMemoryLeaks, _checkSanity, _firstRun, _lastInputSum, _lastCacheDiff, _sanity, _checkBackend, _skipFrame, _warmupBitmap, _warmupCanvas, _warmupNode; var _numTensors, _analyzeMemoryLeaks, _checkSanity, _firstRun, _lastInputSum, _lastCacheDiff, _sanity, _checkBackend, _skipFrame, _warmupBitmap, _warmupCanvas, _warmupNode;
@ -11427,7 +11427,7 @@ var Human = class {
return false; return false;
const resizeFact = 32; const resizeFact = 32;
const reduced = tf21.image.resizeBilinear(input, [Math.trunc(input.shape[1] / resizeFact), Math.trunc(input.shape[2] / resizeFact)]); const reduced = tf21.image.resizeBilinear(input, [Math.trunc(input.shape[1] / resizeFact), Math.trunc(input.shape[2] / resizeFact)]);
const reducedData = reduced.dataSync(); const reducedData = await reduced.data();
let sum = 0; let sum = 0;
for (let i = 0; i < reducedData.length / 3; i++) for (let i = 0; i < reducedData.length / 3; i++)
sum += reducedData[3 * i + 2]; sum += reducedData[3 * i + 2];

20
dist/human.node-wasm.js vendored
View File

@ -4307,7 +4307,7 @@ async function predict3(image18, config3, idx, count2) {
const obj = []; const obj = [];
if (config3.face.emotion.enabled) { if (config3.face.emotion.enabled) {
const emotionT = await model2.predict(normalize); const emotionT = await model2.predict(normalize);
const data = emotionT.dataSync(); const data = await emotionT.data();
tf7.dispose(emotionT); tf7.dispose(emotionT);
for (let i = 0; i < data.length; i++) { for (let i = 0; i < data.length; i++) {
if (data[i] > config3.face.emotion.minConfidence) if (data[i] > config3.face.emotion.minConfidence)
@ -7705,7 +7705,7 @@ var HandDetector = class {
const predictions = tf10.squeeze(batched); const predictions = tf10.squeeze(batched);
tf10.dispose(batched); tf10.dispose(batched);
const scoresT = tf10.tidy(() => tf10.squeeze(tf10.sigmoid(tf10.slice(predictions, [0, 0], [-1, 1])))); const scoresT = tf10.tidy(() => tf10.squeeze(tf10.sigmoid(tf10.slice(predictions, [0, 0], [-1, 1]))));
const scores = scoresT.dataSync(); const scores = await scoresT.data();
const rawBoxes = tf10.slice(predictions, [0, 1], [-1, 4]); const rawBoxes = tf10.slice(predictions, [0, 1], [-1, 4]);
const boxes = this.normalizeBoxes(rawBoxes); const boxes = this.normalizeBoxes(rawBoxes);
tf10.dispose(rawBoxes); tf10.dispose(rawBoxes);
@ -7737,7 +7737,7 @@ var HandDetector = class {
if (!predictions || predictions.length === 0) if (!predictions || predictions.length === 0)
return hands; return hands;
for (const prediction of predictions) { for (const prediction of predictions) {
const boxes = prediction.box.dataSync(); const boxes = await prediction.box.data();
const startPoint = boxes.slice(0, 2); const startPoint = boxes.slice(0, 2);
const endPoint = boxes.slice(2, 4); const endPoint = boxes.slice(2, 4);
const palmLandmarks = await prediction.palmLandmarks.array(); const palmLandmarks = await prediction.palmLandmarks.array();
@ -8126,7 +8126,6 @@ async function load7(config3) {
return model4; return model4;
} }
async function predict6(image18, config3) { async function predict6(image18, config3) {
var _a;
if (!model4) if (!model4)
return []; return [];
if (!config3.body.enabled) if (!config3.body.enabled)
@ -8136,7 +8135,8 @@ async function predict6(image18, config3) {
const normalize = tf13.div(resize, [255]); const normalize = tf13.div(resize, [255]);
tf13.dispose(resize); tf13.dispose(resize);
const resT = await model4.predict(normalize); const resT = await model4.predict(normalize);
const points = ((_a = resT.find((t) => t.size === 195 || t.size === 155)) == null ? void 0 : _a.dataSync()) || []; const findT = resT.find((t) => t.size === 195 || t.size === 155);
const points = await (findT == null ? void 0 : findT.data()) || [];
resT.forEach((t) => tf13.dispose(t)); resT.forEach((t) => tf13.dispose(t));
tf13.dispose(normalize); tf13.dispose(normalize);
const keypoints3 = []; const keypoints3 = [];
@ -8517,7 +8517,7 @@ async function process2(res, inputSize, outputShape, config3) {
let nmsIdx = []; let nmsIdx = [];
if (nmsBoxes && nmsBoxes.length > 0) { if (nmsBoxes && nmsBoxes.length > 0) {
const nms = await tf16.image.nonMaxSuppressionAsync(nmsBoxes, nmsScores, config3.object.maxDetected, config3.object.iouThreshold, config3.object.minConfidence); const nms = await tf16.image.nonMaxSuppressionAsync(nmsBoxes, nmsScores, config3.object.maxDetected, config3.object.iouThreshold, config3.object.minConfidence);
nmsIdx = nms.dataSync(); nmsIdx = await nms.data();
tf16.dispose(nms); tf16.dispose(nms);
} }
results = results.filter((_val, idx) => nmsIdx.includes(idx)).sort((a, b) => b.score - a.score); results = results.filter((_val, idx) => nmsIdx.includes(idx)).sort((a, b) => b.score - a.score);
@ -8584,7 +8584,7 @@ async function process3(res, inputSize, outputShape, config3) {
tf17.dispose(boxesT); tf17.dispose(boxesT);
tf17.dispose(scoresT); tf17.dispose(scoresT);
tf17.dispose(classesT); tf17.dispose(classesT);
const nms = nmsT.dataSync(); const nms = await nmsT.data();
tf17.dispose(nmsT); tf17.dispose(nmsT);
let i = 0; let i = 0;
for (const id of nms) { for (const id of nms) {
@ -9528,7 +9528,7 @@ async function predict11(input) {
resizeOutput = tf19.image.resizeBilinear(squeeze7, [width, height]); resizeOutput = tf19.image.resizeBilinear(squeeze7, [width, height]);
} }
if (typeof document === "undefined") if (typeof document === "undefined")
return resizeOutput.dataSync(); return resizeOutput.data();
const overlay = typeof OffscreenCanvas !== "undefined" ? new OffscreenCanvas(width, height) : document.createElement("canvas"); const overlay = typeof OffscreenCanvas !== "undefined" ? new OffscreenCanvas(width, height) : document.createElement("canvas");
overlay.width = width; overlay.width = width;
overlay.height = height; overlay.height = height;
@ -11332,7 +11332,7 @@ lBhEMohlFerLlBjEMohMVTEARDKCITsAk2AEgAAAkAAAAAAAAAAAAAAAAAAAAAAAASAAAAAAAAD/
2Q==`; 2Q==`;
// package.json // package.json
var version = "2.1.2"; var version = "2.1.3";
// src/human.ts // src/human.ts
var _numTensors, _analyzeMemoryLeaks, _checkSanity, _firstRun, _lastInputSum, _lastCacheDiff, _sanity, _checkBackend, _skipFrame, _warmupBitmap, _warmupCanvas, _warmupNode; var _numTensors, _analyzeMemoryLeaks, _checkSanity, _firstRun, _lastInputSum, _lastCacheDiff, _sanity, _checkBackend, _skipFrame, _warmupBitmap, _warmupCanvas, _warmupNode;
@ -11428,7 +11428,7 @@ var Human = class {
return false; return false;
const resizeFact = 32; const resizeFact = 32;
const reduced = tf21.image.resizeBilinear(input, [Math.trunc(input.shape[1] / resizeFact), Math.trunc(input.shape[2] / resizeFact)]); const reduced = tf21.image.resizeBilinear(input, [Math.trunc(input.shape[1] / resizeFact), Math.trunc(input.shape[2] / resizeFact)]);
const reducedData = reduced.dataSync(); const reducedData = await reduced.data();
let sum = 0; let sum = 0;
for (let i = 0; i < reducedData.length / 3; i++) for (let i = 0; i < reducedData.length / 3; i++)
sum += reducedData[3 * i + 2]; sum += reducedData[3 * i + 2];

20
dist/human.node.js vendored
View File

@ -4306,7 +4306,7 @@ async function predict3(image18, config3, idx, count2) {
const obj = []; const obj = [];
if (config3.face.emotion.enabled) { if (config3.face.emotion.enabled) {
const emotionT = await model2.predict(normalize); const emotionT = await model2.predict(normalize);
const data = emotionT.dataSync(); const data = await emotionT.data();
tf7.dispose(emotionT); tf7.dispose(emotionT);
for (let i = 0; i < data.length; i++) { for (let i = 0; i < data.length; i++) {
if (data[i] > config3.face.emotion.minConfidence) if (data[i] > config3.face.emotion.minConfidence)
@ -7704,7 +7704,7 @@ var HandDetector = class {
const predictions = tf10.squeeze(batched); const predictions = tf10.squeeze(batched);
tf10.dispose(batched); tf10.dispose(batched);
const scoresT = tf10.tidy(() => tf10.squeeze(tf10.sigmoid(tf10.slice(predictions, [0, 0], [-1, 1])))); const scoresT = tf10.tidy(() => tf10.squeeze(tf10.sigmoid(tf10.slice(predictions, [0, 0], [-1, 1]))));
const scores = scoresT.dataSync(); const scores = await scoresT.data();
const rawBoxes = tf10.slice(predictions, [0, 1], [-1, 4]); const rawBoxes = tf10.slice(predictions, [0, 1], [-1, 4]);
const boxes = this.normalizeBoxes(rawBoxes); const boxes = this.normalizeBoxes(rawBoxes);
tf10.dispose(rawBoxes); tf10.dispose(rawBoxes);
@ -7736,7 +7736,7 @@ var HandDetector = class {
if (!predictions || predictions.length === 0) if (!predictions || predictions.length === 0)
return hands; return hands;
for (const prediction of predictions) { for (const prediction of predictions) {
const boxes = prediction.box.dataSync(); const boxes = await prediction.box.data();
const startPoint = boxes.slice(0, 2); const startPoint = boxes.slice(0, 2);
const endPoint = boxes.slice(2, 4); const endPoint = boxes.slice(2, 4);
const palmLandmarks = await prediction.palmLandmarks.array(); const palmLandmarks = await prediction.palmLandmarks.array();
@ -8125,7 +8125,6 @@ async function load7(config3) {
return model4; return model4;
} }
async function predict6(image18, config3) { async function predict6(image18, config3) {
var _a;
if (!model4) if (!model4)
return []; return [];
if (!config3.body.enabled) if (!config3.body.enabled)
@ -8135,7 +8134,8 @@ async function predict6(image18, config3) {
const normalize = tf13.div(resize, [255]); const normalize = tf13.div(resize, [255]);
tf13.dispose(resize); tf13.dispose(resize);
const resT = await model4.predict(normalize); const resT = await model4.predict(normalize);
const points = ((_a = resT.find((t) => t.size === 195 || t.size === 155)) == null ? void 0 : _a.dataSync()) || []; const findT = resT.find((t) => t.size === 195 || t.size === 155);
const points = await (findT == null ? void 0 : findT.data()) || [];
resT.forEach((t) => tf13.dispose(t)); resT.forEach((t) => tf13.dispose(t));
tf13.dispose(normalize); tf13.dispose(normalize);
const keypoints3 = []; const keypoints3 = [];
@ -8516,7 +8516,7 @@ async function process2(res, inputSize, outputShape, config3) {
let nmsIdx = []; let nmsIdx = [];
if (nmsBoxes && nmsBoxes.length > 0) { if (nmsBoxes && nmsBoxes.length > 0) {
const nms = await tf16.image.nonMaxSuppressionAsync(nmsBoxes, nmsScores, config3.object.maxDetected, config3.object.iouThreshold, config3.object.minConfidence); const nms = await tf16.image.nonMaxSuppressionAsync(nmsBoxes, nmsScores, config3.object.maxDetected, config3.object.iouThreshold, config3.object.minConfidence);
nmsIdx = nms.dataSync(); nmsIdx = await nms.data();
tf16.dispose(nms); tf16.dispose(nms);
} }
results = results.filter((_val, idx) => nmsIdx.includes(idx)).sort((a, b) => b.score - a.score); results = results.filter((_val, idx) => nmsIdx.includes(idx)).sort((a, b) => b.score - a.score);
@ -8583,7 +8583,7 @@ async function process3(res, inputSize, outputShape, config3) {
tf17.dispose(boxesT); tf17.dispose(boxesT);
tf17.dispose(scoresT); tf17.dispose(scoresT);
tf17.dispose(classesT); tf17.dispose(classesT);
const nms = nmsT.dataSync(); const nms = await nmsT.data();
tf17.dispose(nmsT); tf17.dispose(nmsT);
let i = 0; let i = 0;
for (const id of nms) { for (const id of nms) {
@ -9527,7 +9527,7 @@ async function predict11(input) {
resizeOutput = tf19.image.resizeBilinear(squeeze7, [width, height]); resizeOutput = tf19.image.resizeBilinear(squeeze7, [width, height]);
} }
if (typeof document === "undefined") if (typeof document === "undefined")
return resizeOutput.dataSync(); return resizeOutput.data();
const overlay = typeof OffscreenCanvas !== "undefined" ? new OffscreenCanvas(width, height) : document.createElement("canvas"); const overlay = typeof OffscreenCanvas !== "undefined" ? new OffscreenCanvas(width, height) : document.createElement("canvas");
overlay.width = width; overlay.width = width;
overlay.height = height; overlay.height = height;
@ -11331,7 +11331,7 @@ lBhEMohlFerLlBjEMohMVTEARDKCITsAk2AEgAAAkAAAAAAAAAAAAAAAAAAAAAAAASAAAAAAAAD/
2Q==`; 2Q==`;
// package.json // package.json
var version = "2.1.2"; var version = "2.1.3";
// src/human.ts // src/human.ts
var _numTensors, _analyzeMemoryLeaks, _checkSanity, _firstRun, _lastInputSum, _lastCacheDiff, _sanity, _checkBackend, _skipFrame, _warmupBitmap, _warmupCanvas, _warmupNode; var _numTensors, _analyzeMemoryLeaks, _checkSanity, _firstRun, _lastInputSum, _lastCacheDiff, _sanity, _checkBackend, _skipFrame, _warmupBitmap, _warmupCanvas, _warmupNode;
@ -11427,7 +11427,7 @@ var Human = class {
return false; return false;
const resizeFact = 32; const resizeFact = 32;
const reduced = tf21.image.resizeBilinear(input, [Math.trunc(input.shape[1] / resizeFact), Math.trunc(input.shape[2] / resizeFact)]); const reduced = tf21.image.resizeBilinear(input, [Math.trunc(input.shape[1] / resizeFact), Math.trunc(input.shape[2] / resizeFact)]);
const reducedData = reduced.dataSync(); const reducedData = await reduced.data();
let sum = 0; let sum = 0;
for (let i = 0; i < reducedData.length / 3; i++) for (let i = 0; i < reducedData.length / 3; i++)
sum += reducedData[3 * i + 2]; sum += reducedData[3 * i + 2];

44
server/build.log
View File

@ -1,22 +1,22 @@
2021-08-11 18:57:35 INFO:  @vladmandic/human version 2.1.2 2021-08-12 09:29:51 INFO:  @vladmandic/human version 2.1.3
2021-08-11 18:57:35 INFO:  User: vlado Platform: linux Arch: x64 Node: v16.5.0 2021-08-12 09:29:51 INFO:  User: vlado Platform: linux Arch: x64 Node: v16.5.0
2021-08-11 18:57:35 INFO:  Toolchain: {"tfjs":"3.8.0","esbuild":"0.12.19","typescript":"4.3.5","typedoc":"0.21.5","eslint":"7.32.0"} 2021-08-12 09:29:51 INFO:  Toolchain: {"tfjs":"3.8.0","esbuild":"0.12.19","typescript":"4.3.5","typedoc":"0.21.5","eslint":"7.32.0"}
2021-08-11 18:57:35 INFO:  Clean: ["dist/*","types/*","typedoc/*"] 2021-08-12 09:29:51 INFO:  Clean: ["dist/*","types/*","typedoc/*"]
2021-08-11 18:57:35 INFO:  Build: file startup all type: production config: {"minifyWhitespace":true,"minifyIdentifiers":true,"minifySyntax":true} 2021-08-12 09:29:51 INFO:  Build: file startup all type: production config: {"minifyWhitespace":true,"minifyIdentifiers":true,"minifySyntax":true}
2021-08-11 18:57:35 STATE: target: node type: tfjs: {"imports":1,"importBytes":102,"outputBytes":1303,"outputFiles":"dist/tfjs.esm.js"} 2021-08-12 09:29:51 STATE: target: node type: tfjs: {"imports":1,"importBytes":102,"outputBytes":1303,"outputFiles":"dist/tfjs.esm.js"}
2021-08-11 18:57:35 STATE: target: node type: node: {"imports":42,"importBytes":436067,"outputBytes":377952,"outputFiles":"dist/human.node.js"} 2021-08-12 09:29:51 STATE: target: node type: node: {"imports":42,"importBytes":436279,"outputBytes":377971,"outputFiles":"dist/human.node.js"}
2021-08-11 18:57:35 STATE: target: nodeGPU type: tfjs: {"imports":1,"importBytes":110,"outputBytes":1311,"outputFiles":"dist/tfjs.esm.js"} 2021-08-12 09:29:51 STATE: target: nodeGPU type: tfjs: {"imports":1,"importBytes":110,"outputBytes":1311,"outputFiles":"dist/tfjs.esm.js"}
2021-08-11 18:57:35 STATE: target: nodeGPU type: node: {"imports":42,"importBytes":436075,"outputBytes":377956,"outputFiles":"dist/human.node-gpu.js"} 2021-08-12 09:29:51 STATE: target: nodeGPU type: node: {"imports":42,"importBytes":436287,"outputBytes":377975,"outputFiles":"dist/human.node-gpu.js"}
2021-08-11 18:57:35 STATE: target: nodeWASM type: tfjs: {"imports":1,"importBytes":149,"outputBytes":1378,"outputFiles":"dist/tfjs.esm.js"} 2021-08-12 09:29:51 STATE: target: nodeWASM type: tfjs: {"imports":1,"importBytes":149,"outputBytes":1378,"outputFiles":"dist/tfjs.esm.js"}
2021-08-11 18:57:35 STATE: target: nodeWASM type: node: {"imports":42,"importBytes":436142,"outputBytes":378028,"outputFiles":"dist/human.node-wasm.js"} 2021-08-12 09:29:51 STATE: target: nodeWASM type: node: {"imports":42,"importBytes":436354,"outputBytes":378047,"outputFiles":"dist/human.node-wasm.js"}
2021-08-11 18:57:35 STATE: target: browserNoBundle type: tfjs: {"imports":1,"importBytes":2168,"outputBytes":1242,"outputFiles":"dist/tfjs.esm.js"} 2021-08-12 09:29:51 STATE: target: browserNoBundle type: tfjs: {"imports":1,"importBytes":2168,"outputBytes":1242,"outputFiles":"dist/tfjs.esm.js"}
2021-08-11 18:57:35 STATE: target: browserNoBundle type: esm: {"imports":42,"importBytes":436006,"outputBytes":248005,"outputFiles":"dist/human.esm-nobundle.js"} 2021-08-12 09:29:51 STATE: target: browserNoBundle type: esm: {"imports":42,"importBytes":436218,"outputBytes":248008,"outputFiles":"dist/human.esm-nobundle.js"}
2021-08-11 18:57:36 STATE: target: browserBundle type: tfjs: {"modules":1170,"moduleBytes":4145868,"imports":7,"importBytes":2168,"outputBytes":2334701,"outputFiles":"dist/tfjs.esm.js"} 2021-08-12 09:29:51 STATE: target: browserBundle type: tfjs: {"modules":1170,"moduleBytes":4145868,"imports":7,"importBytes":2168,"outputBytes":2334701,"outputFiles":"dist/tfjs.esm.js"}
2021-08-11 18:57:36 STATE: target: browserBundle type: iife: {"imports":42,"importBytes":2769465,"outputBytes":1378447,"outputFiles":"dist/human.js"} 2021-08-12 09:29:52 STATE: target: browserBundle type: iife: {"imports":42,"importBytes":2769677,"outputBytes":1378450,"outputFiles":"dist/human.js"}
2021-08-11 18:57:36 STATE: target: browserBundle type: esm: {"imports":42,"importBytes":2769465,"outputBytes":1378439,"outputFiles":"dist/human.esm.js"} 2021-08-12 09:29:52 STATE: target: browserBundle type: esm: {"imports":42,"importBytes":2769677,"outputBytes":1378442,"outputFiles":"dist/human.esm.js"}
2021-08-11 18:57:36 INFO:  Running Linter: ["server/","src/","tfjs/","test/","demo/"] 2021-08-12 09:29:52 INFO:  Running Linter: ["server/","src/","tfjs/","test/","demo/"]
2021-08-11 18:57:59 INFO:  Linter complete: files: 75 errors: 0 warnings: 0 2021-08-12 09:30:14 INFO:  Linter complete: files: 75 errors: 0 warnings: 0
2021-08-11 18:57:59 INFO:  Generate ChangeLog: ["/home/vlado/dev/human/CHANGELOG.md"] 2021-08-12 09:30:14 INFO:  Generate ChangeLog: ["/home/vlado/dev/human/CHANGELOG.md"]
2021-08-11 18:57:59 INFO:  Generate Typings: ["src/human.ts"] outDir: ["types"] 2021-08-12 09:30:14 INFO:  Generate Typings: ["src/human.ts"] outDir: ["types"]
2021-08-11 18:58:13 INFO:  Generate TypeDocs: ["src/human.ts"] outDir: ["typedoc"] 2021-08-12 09:30:29 INFO:  Generate TypeDocs: ["src/human.ts"] outDir: ["typedoc"]
2021-08-11 18:58:27 INFO:  Documentation generated at /home/vlado/dev/human/typedoc 1 2021-08-12 09:30:43 INFO:  Documentation generated at /home/vlado/dev/human/typedoc 1

2
src/age/age.ts
View File

@ -45,7 +45,7 @@ export async function predict(image: Tensor, config: Config | any) {
tf.dispose(enhance); tf.dispose(enhance);
if (ageT) { if (ageT) {
const data = ageT.dataSync(); const data = await ageT.data();
obj.age = Math.trunc(10 * data[0]) / 10; obj.age = Math.trunc(10 * data[0]) / 10;
} }
tf.dispose(ageT); tf.dispose(ageT);

2
src/blazeface/blazeface.ts
View File

@ -57,7 +57,7 @@ export class BlazeFaceModel {
} }
const boxesOut = decodeBounds(batchOut, this.anchors, [this.inputSize, this.inputSize]); const boxesOut = decodeBounds(batchOut, this.anchors, [this.inputSize, this.inputSize]);
const logits = tf.slice(batchOut, [0, 0], [-1, 1]); const logits = tf.slice(batchOut, [0, 0], [-1, 1]);
const scoresOut = tf.squeeze(tf.sigmoid(logits)).dataSync(); const scoresOut = tf.squeeze(tf.sigmoid(logits)).dataSync(); // inside tf.tidy
return [batchOut, boxesOut, scoresOut]; return [batchOut, boxesOut, scoresOut];
}); });

4
src/blazeface/facepipeline.ts
View File

@ -234,7 +234,7 @@ export class Pipeline {
} }
const [, confidence, contourCoords] = this.meshDetector.execute(face) as Array<Tensor>; // The first returned tensor represents facial contours which are already included in the coordinates. const [, confidence, contourCoords] = this.meshDetector.execute(face) as Array<Tensor>; // The first returned tensor represents facial contours which are already included in the coordinates.
const faceConfidence = confidence.dataSync()[0] as number; const faceConfidence = confidence.dataSync()[0] as number; // inside tf.tidy
if (faceConfidence < config.face.detector.minConfidence) { if (faceConfidence < config.face.detector.minConfidence) {
this.storedBoxes[i].confidence = faceConfidence; // reset confidence of cached box this.storedBoxes[i].confidence = faceConfidence; // reset confidence of cached box
return null; // if below confidence just exit return null; // if below confidence just exit
@ -246,7 +246,7 @@ export class Pipeline {
const { box: leftEyeBox, boxSize: leftEyeBoxSize, crop: leftEyeCrop } = this.getEyeBox(rawCoords, face, eyeLandmarks.leftBounds[0], eyeLandmarks.leftBounds[1], true); const { box: leftEyeBox, boxSize: leftEyeBoxSize, crop: leftEyeCrop } = this.getEyeBox(rawCoords, face, eyeLandmarks.leftBounds[0], eyeLandmarks.leftBounds[1], true);
const { box: rightEyeBox, boxSize: rightEyeBoxSize, crop: rightEyeCrop } = this.getEyeBox(rawCoords, face, eyeLandmarks.rightBounds[0], eyeLandmarks.rightBounds[1]); const { box: rightEyeBox, boxSize: rightEyeBoxSize, crop: rightEyeCrop } = this.getEyeBox(rawCoords, face, eyeLandmarks.rightBounds[0], eyeLandmarks.rightBounds[1]);
const eyePredictions = this.irisModel.predict(tf.concat([leftEyeCrop, rightEyeCrop])) as Tensor; const eyePredictions = this.irisModel.predict(tf.concat([leftEyeCrop, rightEyeCrop])) as Tensor;
const eyePredictionsData = eyePredictions.dataSync(); const eyePredictionsData = eyePredictions.dataSync(); // inside tf.tidy
const leftEyeData = eyePredictionsData.slice(0, irisLandmarks.numCoordinates * 3); const leftEyeData = eyePredictionsData.slice(0, irisLandmarks.numCoordinates * 3);
const { rawCoords: leftEyeRawCoords, iris: leftIrisRawCoords } = this.getEyeCoords(leftEyeData, leftEyeBox, leftEyeBoxSize, true); const { rawCoords: leftEyeRawCoords, iris: leftIrisRawCoords } = this.getEyeCoords(leftEyeData, leftEyeBox, leftEyeBoxSize, true);
const rightEyeData = eyePredictionsData.slice(irisLandmarks.numCoordinates * 3); const rightEyeData = eyePredictionsData.slice(irisLandmarks.numCoordinates * 3);

3
src/blazepose/blazepose.ts
View File

@ -33,7 +33,8 @@ export async function predict(image: Tensor, config: Config): Promise<Body[]> {
const normalize = tf.div(resize, [255.0]); const normalize = tf.div(resize, [255.0]);
tf.dispose(resize); tf.dispose(resize);
const resT = await model.predict(normalize) as Array<Tensor>; const resT = await model.predict(normalize) as Array<Tensor>;
const points = resT.find((t) => (t.size === 195 || t.size === 155))?.dataSync() || []; // order of output tensors may change between models, full has 195 and upper has 155 items const findT = resT.find((t) => (t.size === 195 || t.size === 155));
const points = await findT?.data() || []; // order of output tensors may change between models, full has 195 and upper has 155 items
resT.forEach((t) => tf.dispose(t)); resT.forEach((t) => tf.dispose(t));
tf.dispose(normalize); tf.dispose(normalize);
const keypoints: Array<{ id, part, position: [number, number, number], positionRaw: [number, number, number], score, presence }> = []; const keypoints: Array<{ id, part, position: [number, number, number], positionRaw: [number, number, number], score, presence }> = [];

6
src/efficientpose/efficientpose.ts
View File

@ -39,12 +39,12 @@ function max2d(inputs, minScore) {
// combine all data // combine all data
const reshaped = tf.reshape(inputs, [height * width]); const reshaped = tf.reshape(inputs, [height * width]);
// get highest score // get highest score
const newScore = tf.max(reshaped, 0).dataSync()[0]; const newScore = tf.max(reshaped, 0).dataSync()[0]; // inside tf.tidy
if (newScore > minScore) { if (newScore > minScore) {
// skip coordinate calculation is score is too low // skip coordinate calculation is score is too low
const coords = tf.argMax(reshaped, 0); const coords = tf.argMax(reshaped, 0);
const x = mod(coords, width).dataSync()[0]; const x = mod(coords, width).dataSync()[0]; // inside tf.tidy
const y = tf.div(coords, tf.scalar(width, 'int32')).dataSync()[0]; const y = tf.div(coords, tf.scalar(width, 'int32')).dataSync()[0]; // inside tf.tidy
return [x, y, newScore]; return [x, y, newScore];
} }
return [0, 0, newScore]; return [0, 0, newScore];

2
src/embedding/embedding.ts
View File

@ -125,7 +125,7 @@ export async function predict(input, config): Promise<number[]> {
const reshape = tf.reshape(res, [128, 2]); // split 256 vectors into 128 x 2 const reshape = tf.reshape(res, [128, 2]); // split 256 vectors into 128 x 2
const reduce = reshape.logSumExp(1); // reduce 2nd dimension by calculating logSumExp on it const reduce = reshape.logSumExp(1); // reduce 2nd dimension by calculating logSumExp on it
const output: Array<number> = reduce.dataSync(); const output: Array<number> = reduce.dataSync(); // inside tf.tidy
return [...output]; // convert typed array to simple array return [...output]; // convert typed array to simple array
}); });
tf.dispose(image); tf.dispose(image);

2
src/emotion/emotion.ts
View File

@ -53,7 +53,7 @@ export async function predict(image: Tensor, config: Config, idx, count) {
const obj: Array<{ score: number, emotion: string }> = []; const obj: Array<{ score: number, emotion: string }> = [];
if (config.face.emotion.enabled) { if (config.face.emotion.enabled) {
const emotionT = await model.predict(normalize); // result is already in range 0..1, no need for additional activation const emotionT = await model.predict(normalize); // result is already in range 0..1, no need for additional activation
const data = emotionT.dataSync(); const data = await emotionT.data();
tf.dispose(emotionT); tf.dispose(emotionT);
for (let i = 0; i < data.length; i++) { for (let i = 0; i < data.length; i++) {
if (data[i] > config.face.emotion.minConfidence) obj.push({ score: Math.min(0.99, Math.trunc(100 * data[i]) / 100), emotion: annotations[i] }); if (data[i] > config.face.emotion.minConfidence) obj.push({ score: Math.min(0.99, Math.trunc(100 * data[i]) / 100), emotion: annotations[i] });

8
src/faceres/faceres.ts
View File

@ -134,21 +134,21 @@ export async function predict(image: Tensor, config: Config, idx, count) {
if (resT) { if (resT) {
tf.tidy(() => { tf.tidy(() => {
const gender = resT.find((t) => t.shape[1] === 1).dataSync(); const gender = resT.find((t) => t.shape[1] === 1).dataSync(); // inside tf.tidy
const confidence = Math.trunc(200 * Math.abs((gender[0] - 0.5))) / 100; const confidence = Math.trunc(200 * Math.abs((gender[0] - 0.5))) / 100;
if (confidence > config.face.description.minConfidence) { if (confidence > config.face.description.minConfidence) {
obj.gender = gender[0] <= 0.5 ? 'female' : 'male'; obj.gender = gender[0] <= 0.5 ? 'female' : 'male';
obj.genderScore = Math.min(0.99, confidence); obj.genderScore = Math.min(0.99, confidence);
} }
const age = tf.argMax(resT.find((t) => t.shape[1] === 100), 1).dataSync()[0]; const age = tf.argMax(resT.find((t) => t.shape[1] === 100), 1).dataSync()[0]; // inside tf.tidy
const all = resT.find((t) => t.shape[1] === 100).dataSync(); const all = resT.find((t) => t.shape[1] === 100).dataSync(); // inside tf.tidy
obj.age = Math.round(all[age - 1] > all[age + 1] ? 10 * age - 100 * all[age - 1] : 10 * age + 100 * all[age + 1]) / 10; obj.age = Math.round(all[age - 1] > all[age + 1] ? 10 * age - 100 * all[age - 1] : 10 * age + 100 * all[age + 1]) / 10;
const desc = resT.find((t) => t.shape[1] === 1024); const desc = resT.find((t) => t.shape[1] === 1024);
// const reshape = desc.reshape([128, 8]); // reshape large 1024-element descriptor to 128 x 8 // const reshape = desc.reshape([128, 8]); // reshape large 1024-element descriptor to 128 x 8
// const reduce = reshape.logSumExp(1); // reduce 2nd dimension by calculating logSumExp on it which leaves us with 128-element descriptor // const reduce = reshape.logSumExp(1); // reduce 2nd dimension by calculating logSumExp on it which leaves us with 128-element descriptor
obj.descriptor = [...desc.dataSync()]; obj.descriptor = [...desc.dataSync()]; // inside tf.tidy
}); });
resT.forEach((t) => tf.dispose(t)); resT.forEach((t) => tf.dispose(t));
} }

4
src/gender/gender.ts
View File

@ -63,7 +63,7 @@ export async function predict(image: Tensor, config: Config | any) {
if (genderT) { if (genderT) {
if (!Array.isArray(genderT)) { if (!Array.isArray(genderT)) {
const data = genderT.dataSync(); const data = await genderT.data();
if (alternative) { if (alternative) {
// returns two values 0..1, bigger one is prediction // returns two values 0..1, bigger one is prediction
if (data[0] > config.face.gender.minConfidence || data[1] > config.face.gender.minConfidence) { if (data[0] > config.face.gender.minConfidence || data[1] > config.face.gender.minConfidence) {
@ -80,7 +80,7 @@ export async function predict(image: Tensor, config: Config | any) {
} }
tf.dispose(genderT); tf.dispose(genderT);
} else { } else {
const gender = genderT[0].dataSync(); const gender = await genderT[0].data();
const confidence = Math.trunc(200 * Math.abs((gender[0] - 0.5))) / 100; const confidence = Math.trunc(200 * Math.abs((gender[0] - 0.5))) / 100;
if (confidence > config.face.gender.minConfidence) { if (confidence > config.face.gender.minConfidence) {
obj.gender = gender[0] <= 0.5 ? 'female' : 'male'; obj.gender = gender[0] <= 0.5 ? 'female' : 'male';

4
src/handpose/handdetector.ts
View File

@ -45,7 +45,7 @@ export class HandDetector {
const predictions = tf.squeeze(batched); const predictions = tf.squeeze(batched);
tf.dispose(batched); tf.dispose(batched);
const scoresT = tf.tidy(() => tf.squeeze(tf.sigmoid(tf.slice(predictions, [0, 0], [-1, 1])))); const scoresT = tf.tidy(() => tf.squeeze(tf.sigmoid(tf.slice(predictions, [0, 0], [-1, 1]))));
const scores = scoresT.dataSync(); const scores = await scoresT.data();
const rawBoxes = tf.slice(predictions, [0, 1], [-1, 4]); const rawBoxes = tf.slice(predictions, [0, 1], [-1, 4]);
const boxes = this.normalizeBoxes(rawBoxes); const boxes = this.normalizeBoxes(rawBoxes);
tf.dispose(rawBoxes); tf.dispose(rawBoxes);
@ -78,7 +78,7 @@ export class HandDetector {
const hands: Array<{ startPoint: number[]; endPoint: number[]; palmLandmarks: number[]; confidence: number }> = []; const hands: Array<{ startPoint: number[]; endPoint: number[]; palmLandmarks: number[]; confidence: number }> = [];
if (!predictions || predictions.length === 0) return hands; if (!predictions || predictions.length === 0) return hands;
for (const prediction of predictions) { for (const prediction of predictions) {
const boxes = prediction.box.dataSync(); const boxes = await prediction.box.data();
const startPoint = boxes.slice(0, 2); const startPoint = boxes.slice(0, 2);
const endPoint = boxes.slice(2, 4); const endPoint = boxes.slice(2, 4);
const palmLandmarks = await prediction.palmLandmarks.array(); const palmLandmarks = await prediction.palmLandmarks.array();

2
src/human.ts
View File

@ -367,7 +367,7 @@ export class Human {
sumT.dispose(); sumT.dispose();
*/ */
// use js loop sum, faster than uploading tensor to gpu calculating and downloading back // use js loop sum, faster than uploading tensor to gpu calculating and downloading back
const reducedData = reduced.dataSync(); // raw image rgb array const reducedData = await reduced.data(); // raw image rgb array
let sum = 0; let sum = 0;
for (let i = 0; i < reducedData.length / 3; i++) sum += reducedData[3 * i + 2]; // look only at green value of each pixel for (let i = 0; i < reducedData.length / 3; i++) sum += reducedData[3 * i + 2]; // look only at green value of each pixel

2
src/object/centernet.ts
View File

@ -42,7 +42,7 @@ async function process(res: Tensor, inputSize, outputShape, config: Config) {
tf.dispose(boxesT); tf.dispose(boxesT);
tf.dispose(scoresT); tf.dispose(scoresT);
tf.dispose(classesT); tf.dispose(classesT);
const nms = nmsT.dataSync(); const nms = await nmsT.data();
tf.dispose(nmsT); tf.dispose(nmsT);
let i = 0; let i = 0;
for (const id of nms) { for (const id of nms) {

2
src/object/nanodet.ts
View File

@ -90,7 +90,7 @@ async function process(res, inputSize, outputShape, config) {
let nmsIdx: Array<number> = []; let nmsIdx: Array<number> = [];
if (nmsBoxes && nmsBoxes.length > 0) { if (nmsBoxes && nmsBoxes.length > 0) {
const nms = await tf.image.nonMaxSuppressionAsync(nmsBoxes, nmsScores, config.object.maxDetected, config.object.iouThreshold, config.object.minConfidence); const nms = await tf.image.nonMaxSuppressionAsync(nmsBoxes, nmsScores, config.object.maxDetected, config.object.iouThreshold, config.object.minConfidence);
nmsIdx = nms.dataSync(); nmsIdx = await nms.data();
tf.dispose(nms); tf.dispose(nms);
} }

2
src/segmentation/segmentation.ts
View File

@ -59,7 +59,7 @@ export async function predict(input: { tensor: Tensor | null, canvas: OffscreenC
resizeOutput = tf.image.resizeBilinear(squeeze, [width, height]); resizeOutput = tf.image.resizeBilinear(squeeze, [width, height]);
} }
if (typeof document === 'undefined') return resizeOutput.dataSync(); // we're running in nodejs so return alpha array as-is if (typeof document === 'undefined') return resizeOutput.data(); // we're running in nodejs so return alpha array as-is
const overlay = (typeof OffscreenCanvas !== 'undefined') ? new OffscreenCanvas(width, height) : document.createElement('canvas'); const overlay = (typeof OffscreenCanvas !== 'undefined') ? new OffscreenCanvas(width, height) : document.createElement('canvas');
overlay.width = width; overlay.width = width;