feat: 完善淘宝小程序拍照、报告与登录流程
接入本地实时识别和自动三连拍，调整报告裁切、商品跳转、分享标题及居中页眉；完善游客会话、后台渠道隔离、部署脚本与回归测试。
This commit is contained in:
Vendored
+56
@@ -0,0 +1,56 @@
|
||||
/* Local-only capture gates; no request, scoring, or report recommendation logic. */
|
||||
(function(root, factory) {
|
||||
if (typeof module === 'object' && module.exports) module.exports = factory(require('./head-pose.js'));
|
||||
else root.CaptureQuality = factory(root.HeadPose);
|
||||
})(typeof window !== 'undefined' ? window : this, function(HeadPose) {
|
||||
'use strict';
|
||||
// Real-phone feedback: ease alignment and normal hand/head movement while
|
||||
// retaining two checked preview frames, one face and framing. No JPEG recheck.
|
||||
var config = Object.freeze({ version: '2026-10-16-preview-only-v11', score: 0.3, frontScore: 0.25,
|
||||
near: 0.30, far: 0.68, center: 0.16, edge: 0.01,
|
||||
dark: 110, bright: 220, holdMs: 450, minFrames: 2, maxGapMs: 2000,
|
||||
yawDrift: 8, pitchDrift: 8, centerDrift: 0.055, sizeDrift: 0.065 });
|
||||
function finite(v) { return typeof v === 'number' && isFinite(v); }
|
||||
function scoreThreshold(target) { return target === 'front' ? config.frontScore : config.score; }
|
||||
function evaluate(d, options) {
|
||||
var failed = function(hint, reason) { return { ok: false, hint: hint, reason: reason || 'quality' }; };
|
||||
if (!d) return failed('未检测到人脸');
|
||||
if (options.count !== 1) return failed('请保持单人出镜');
|
||||
var box = d.detection.box, w = options.width, h = options.height;
|
||||
if (!box || ![box.x, box.y, box.width, box.height, w, h].every(finite) || w <= 0 || h <= 0 || box.width <= 0 || box.height <= 0) return failed('请将脸部完整移入取景框');
|
||||
var ratio = box.height / h;
|
||||
if (!finite(d.detection.score) || d.detection.score < scoreThreshold(options.target)) return failed('请保持面部清晰');
|
||||
if (ratio < config.near) return failed('请靠近一点');
|
||||
if (ratio > config.far) return failed('请远一点');
|
||||
if (box.x < w * config.edge || box.y < h * config.edge || box.x + box.width > w * (1 - config.edge) || box.y + box.height > h * (1 - config.edge)) return failed('请将脸部完整移入取景框');
|
||||
if (!finite(options.offsetX) || Math.abs(options.offsetX) > config.center) return failed('请将脸部移入取景框');
|
||||
var pose;
|
||||
try { pose = HeadPose.estimate(d.landmarks.positions, options.mirrored); } catch (_) { return failed('请正对屏幕'); }
|
||||
if (!pose) return failed('请正对屏幕');
|
||||
// System-camera files may already be mirrored. Retain the established
|
||||
// direction-agnostic fallback, but apply the same angle/pitch/roll limits.
|
||||
var target = options.target;
|
||||
if (options.ignoreDirection && target !== 'front') target = pose.yaw < 0 ? 'left' : 'right';
|
||||
var check = HeadPose.check(d.landmarks.positions, target, options.mirrored);
|
||||
if (!check.ok) return failed(check.hint, finite(check.yaw) ? 'angle' : 'quality');
|
||||
// Lighting is advisory for both live frames and saved JPEGs, never a gate.
|
||||
var warning = finite(options.luma) && options.luma < config.dark ? '建议到光线明亮处拍摄' :
|
||||
finite(options.luma) && options.luma > config.bright ? '光线过强，建议避开强光' : '';
|
||||
return { ok: true, hint: '保持不动', warning: warning, observation: { yaw: pose.yaw, pitch: pose.pitch, roll: pose.roll,
|
||||
score: d.detection.score, luma: finite(options.luma) ? options.luma : null, ratio: ratio,
|
||||
center_x: (box.x + box.width / 2) / w, center_y: (box.y + box.height / 2) / h } };
|
||||
}
|
||||
function hold(state, observation, now) {
|
||||
if (!observation) return { ready: false, state: null };
|
||||
var reset = !state || now - state.lastAt > config.maxGapMs || now < state.lastAt;
|
||||
if (!reset) {
|
||||
var a = state.anchor, b = observation;
|
||||
reset = Math.abs(a.yaw - b.yaw) > config.yawDrift || Math.abs(a.pitch - b.pitch) > config.pitchDrift ||
|
||||
Math.abs(a.center_x - b.center_x) > config.centerDrift || Math.abs(a.center_y - b.center_y) > config.centerDrift || Math.abs(a.ratio - b.ratio) > config.sizeDrift;
|
||||
}
|
||||
var next = reset ? { since: now, lastAt: now, frames: 1, anchor: observation } :
|
||||
{ since: state.since, lastAt: now, frames: state.frames + 1, anchor: state.anchor };
|
||||
return { state: next, ready: now - next.since >= config.holdMs && next.frames >= config.minFrames };
|
||||
}
|
||||
return { config: config, scoreThreshold: scoreThreshold, evaluate: evaluate, hold: hold };
|
||||
});
|
||||
Vendored
+362
@@ -0,0 +1,362 @@
|
||||
/**
|
||||
* head-pose.js —— 纯姿态估算模块（yaw / pitch / roll）
|
||||
*
|
||||
* 输入为 face-api.js 的 68 特征点（[{x,y}, ...]，图片坐标系、未镜像），
|
||||
* 输出角度制姿态角。纯数据进、纯数据出：不碰 DOM、不 require face-api，
|
||||
* 浏览器挂 window.HeadPose，Node 下 module.exports，可直接单测。
|
||||
*
|
||||
* ------------------------- 坐标与符号约定 -------------------------
|
||||
* 68 点索引（dlib/face-api 约定，以「看图视角」描述）：
|
||||
* 36 = 画面左侧眼外角（被摄者右眼外角）
|
||||
* 45 = 画面右侧眼外角（被摄者左眼外角）
|
||||
* 30 = 鼻尖，33 = 鼻底，19/24 = 左右眉峰，8 = 下巴尖
|
||||
* 图片坐标系：x 向右，y 向下。
|
||||
*
|
||||
* yaw（左右转头）：
|
||||
* yaw > 0 表示鼻尖偏向画面右侧（45 点一侧），即被摄者向【自己的左侧】转头
|
||||
* （此时画面中看到被摄者的右脸 → check 的 target 'right'）；
|
||||
* yaw < 0 表示被摄者向【自己的右侧】转头（画面中看到左脸 → target 'left'）。
|
||||
* mirrored=true（前置摄像头预览做了水平镜像）时内部翻转 yaw 符号，
|
||||
* 使输出相对用户所看到的画面方向一致；check() 内部会还原语义方向，
|
||||
* 因此 check 结果与 mirrored 取值无关。
|
||||
* ⚠ 方向符号真机需校准：不同机型/镜像策略下若左右相反，
|
||||
* 只需调整调用方传入的 mirrored 标志或 YAW_COEFF 符号。
|
||||
*
|
||||
* pitch（俯仰）：
|
||||
* pitch > 0 表示抬头（鼻底相对眉眼连线中点的纵向下移增大），
|
||||
* pitch < 0 表示低头。⚠ 经验映射，真机需校准 PITCH_BASELINE / PITCH_COEFF。
|
||||
*
|
||||
* roll（平面内歪头）：
|
||||
* 两眼外角连线倾角，roll > 0 表示画面右侧（45 点一侧）偏低。
|
||||
*
|
||||
* 所有映射均为基于 68 点几何的轻量经验估算（非 solvePnP 精确解），
|
||||
* 系数仅保证量级与单调性合理，上线前需用真机样本回归校准。
|
||||
*/
|
||||
(function (root, factory) {
|
||||
if (typeof module === 'object' && module.exports) {
|
||||
module.exports = factory();
|
||||
} else {
|
||||
root.HeadPose = factory();
|
||||
}
|
||||
}(typeof self !== 'undefined' ? self : this, function () {
|
||||
'use strict';
|
||||
|
||||
// ---- 68 点索引 ----
|
||||
var IDX = {
|
||||
EYE_LEFT_OUTER: 36, // 画面左侧眼外角
|
||||
EYE_RIGHT_OUTER: 45, // 画面右侧眼外角
|
||||
NOSE_TIP: 30,
|
||||
NOSE_BASE: 33,
|
||||
BROW_LEFT: 19,
|
||||
BROW_RIGHT: 24,
|
||||
CHIN: 8
|
||||
};
|
||||
|
||||
// ---- 经验系数(2026-09-27 用 C3 三视图(+45°侧脸)模拟摄像头校准) ----
|
||||
// yaw = atan((dLeft-dRight)/(dLeft+dRight)) × YAW_COEFF。
|
||||
// 校准:±45° 实拍侧脸读数 ±25°(2.2 偏小)→ 3.8 使读数落在 44° 上下;正脸 ~4°,仍 <12° 阈值
|
||||
var YAW_COEFF = 3.8;
|
||||
// pitch:鼻底相对「眉眼连线中点」的纵向偏移 / 脸高(眉 19/24 — 下巴 8),
|
||||
// 减去中性正脸基线后线性映射为角度。
|
||||
var PITCH_BASELINE = 0.45; // 校准:0.32 时正脸误读 ~29°(被误判低头),实测基线 0.48,留 0.03 余量
|
||||
var PITCH_COEFF = 180; // 归一化偏移 → 角度 的增益
|
||||
|
||||
// ---- check 阈值（角度制） ----
|
||||
// Real-phone feedback: relaxed alignment, without accepting frontal photos
|
||||
// as side views. These empirical angles are not upstream quality scores.
|
||||
// 2026-10-15: expand accepted angles by 20%; lower side minimum by 20%.
|
||||
var FRONT_YAW_MAX = 18;
|
||||
var FRONT_PITCH_MAX = 26;
|
||||
var SIDE_YAW_MIN = 24;
|
||||
var SIDE_YAW_MAX = 84;
|
||||
var SIDE_PITCH_MAX = 29;
|
||||
var ROLL_MAX = 22;
|
||||
|
||||
var HINT_KEEP = '保持不动';
|
||||
var HINT_TURN_LEFT = '请向左转头'; // 用户向自己的左侧转
|
||||
var HINT_TURN_RIGHT = '请向右转头'; // 用户向自己的右侧转
|
||||
var HINT_RAISE = '请略微抬头';
|
||||
var HINT_LOWER = '请略微低头';
|
||||
var HINT_FRONT = '请正对屏幕';
|
||||
|
||||
var RAD2DEG = 180 / Math.PI;
|
||||
|
||||
function dist(a, b) {
|
||||
var dx = a.x - b.x;
|
||||
var dy = a.y - b.y;
|
||||
return Math.sqrt(dx * dx + dy * dy);
|
||||
}
|
||||
|
||||
function midpoint(a, b) {
|
||||
return { x: (a.x + b.x) / 2, y: (a.y + b.y) / 2 };
|
||||
}
|
||||
|
||||
function clamp(v, lo, hi) {
|
||||
return v < lo ? lo : (v > hi ? hi : v);
|
||||
}
|
||||
|
||||
function assertPoints(points) {
|
||||
if (!points || typeof points.length !== 'number' || points.length < 68) {
|
||||
throw new TypeError('HeadPose.estimate: 需要 68 个特征点数组');
|
||||
}
|
||||
var names = Object.keys(IDX);
|
||||
for (var i = 0; i < names.length; i++) {
|
||||
var p = points[IDX[names[i]]];
|
||||
if (!p || typeof p.x !== 'number' || typeof p.y !== 'number' ||
|
||||
!isFinite(p.x) || !isFinite(p.y)) {
|
||||
throw new TypeError('HeadPose.estimate: 特征点 ' + IDX[names[i]] + ' 非法');
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* estimate(points, mirrored) -> { yaw, pitch, roll }（角度制），非法/退化输入返回 null
|
||||
* points : face-api 68 特征点 [{x,y}, ...]（图片坐标系，未镜像）
|
||||
* mirrored : 预览画面是否水平镜像（true 时翻转 yaw 符号）
|
||||
* 返回 null 的情形：特征点重合（dLeft+dRight=0，yaw 退化为 NaN）、
|
||||
* 脸高过小（pitch 不可信，不再静默置 0）、结果出现 NaN/Infinity。
|
||||
*/
|
||||
function estimate(points, mirrored) {
|
||||
assertPoints(points);
|
||||
|
||||
var eyeL = points[IDX.EYE_LEFT_OUTER];
|
||||
var eyeR = points[IDX.EYE_RIGHT_OUTER];
|
||||
var noseTip = points[IDX.NOSE_TIP];
|
||||
var noseBase = points[IDX.NOSE_BASE];
|
||||
var browMid = midpoint(points[IDX.BROW_LEFT], points[IDX.BROW_RIGHT]);
|
||||
var chin = points[IDX.CHIN];
|
||||
|
||||
// roll：两眼外角连线倾角（y 向下，45 点偏低为正）
|
||||
var roll = Math.atan2(eyeR.y - eyeL.y, eyeR.x - eyeL.x) * RAD2DEG;
|
||||
|
||||
// yaw：鼻尖到左右眼外角距离的不对称度；特征点重合（dLeft+dRight=0）时为 NaN，走非法分支
|
||||
var dLeft = dist(noseTip, eyeL);
|
||||
var dRight = dist(noseTip, eyeR);
|
||||
var dSum = dLeft + dRight;
|
||||
var yaw = NaN;
|
||||
if (dSum > 0) yaw = Math.atan((dLeft - dRight) / dSum) * RAD2DEG * YAW_COEFF;
|
||||
|
||||
// pitch：鼻底相对眉眼连线中点的纵向偏移，以脸高归一后线性映射；
|
||||
// 脸高过小时 pitch 不可信，不再静默置 0，走非法分支
|
||||
var eyeMid = midpoint(eyeL, eyeR);
|
||||
var browEyeMid = midpoint(browMid, eyeMid);
|
||||
var faceHeight = chin.y - browMid.y;
|
||||
var pitch = NaN;
|
||||
if (faceHeight > 1) {
|
||||
var ratio = (noseBase.y - browEyeMid.y) / faceHeight;
|
||||
pitch = (ratio - PITCH_BASELINE) * PITCH_COEFF;
|
||||
}
|
||||
|
||||
if (!isFinite(yaw) || !isFinite(pitch) || !isFinite(roll)) return null; // 退化输入 → 非法三角
|
||||
|
||||
yaw = clamp(yaw, -90, 90);
|
||||
pitch = clamp(pitch, -90, 90);
|
||||
if (mirrored) { yaw = -yaw; }
|
||||
|
||||
return { yaw: yaw, pitch: pitch, roll: roll };
|
||||
}
|
||||
|
||||
/**
|
||||
* check(points, target, mirrored) -> { ok, hint }
|
||||
* target: 'front' | 'left' | 'right'
|
||||
* 'front' : |yaw|<=18 且 |pitch|<=26、|roll|<=22；角度不合格只提示回正，
|
||||
* 不在正脸拍摄完成前播侧脸转头指令。
|
||||
* 'left' : 画面中看到左脸 = 被摄者头向右转（语义 yaw ∈ [-84°,-24°]），|pitch|<=29
|
||||
* 'right' : 画面中看到右脸 = 被摄者头向左转（语义 yaw ∈ [24°,84°]），|pitch|<=29
|
||||
* ok=true 时 hint='保持不动'；输入非法（含 estimate 返回 null 的退化特征点）时 ok=false、hint='请正对屏幕'。
|
||||
*/
|
||||
function check(points, target, mirrored) {
|
||||
var e;
|
||||
try {
|
||||
e = estimate(points, mirrored);
|
||||
} catch (err) {
|
||||
return { ok: false, hint: HINT_FRONT, yaw: null };
|
||||
}
|
||||
if (!e) return { ok: false, hint: HINT_FRONT, yaw: null }; // 退化特征点（重合/脸高过小 → NaN/Infinity）
|
||||
|
||||
// 语义 yaw:>0 = 被摄者向自己的左侧转头。estimate(mirrored) 内部已按镜像翻转过符号,
|
||||
// 这里直接用 e.yaw(此前再翻一次是双重镜像 bug:侧脸引导方向完全相反)
|
||||
var sYaw = e.yaw;
|
||||
var pitch = e.pitch;
|
||||
if (Math.abs(e.roll) > ROLL_MAX) return { ok: false, hint: '请勿歪头', yaw: sYaw };
|
||||
|
||||
if (target === 'front') {
|
||||
if (Math.abs(sYaw) <= FRONT_YAW_MAX && Math.abs(pitch) <= FRONT_PITCH_MAX) {
|
||||
return { ok: true, hint: HINT_KEEP, yaw: sYaw };
|
||||
}
|
||||
return { ok: false, hint: HINT_FRONT, yaw: sYaw };
|
||||
}
|
||||
|
||||
if (target === 'left' || target === 'right') {
|
||||
// 'left' 需要语义 yaw 为负（头向右转），'right' 需要为正
|
||||
var want = target === 'left' ? -1 : 1;
|
||||
var sy = sYaw * want; // 统一折算到正区间判断
|
||||
if (sy >= SIDE_YAW_MIN && sy <= SIDE_YAW_MAX && Math.abs(pitch) <= SIDE_PITCH_MAX) {
|
||||
return { ok: true, hint: HINT_KEEP, yaw: sYaw };
|
||||
}
|
||||
if (sy < SIDE_YAW_MIN) {
|
||||
// 转得不够（含转错方向）：提示朝目标方向转
|
||||
return { ok: false, hint: target === 'left' ? HINT_TURN_RIGHT : HINT_TURN_LEFT, yaw: sYaw };
|
||||
}
|
||||
if (sy > SIDE_YAW_MAX) {
|
||||
// 转过了：提示往回
|
||||
return { ok: false, hint: target === 'left' ? HINT_TURN_LEFT : HINT_TURN_RIGHT, yaw: sYaw };
|
||||
}
|
||||
return { ok: false, hint: pitch > 0 ? HINT_LOWER : HINT_RAISE, yaw: sYaw };
|
||||
}
|
||||
|
||||
return { ok: false, hint: HINT_FRONT, yaw: null };
|
||||
}
|
||||
|
||||
return {
|
||||
estimate: estimate,
|
||||
check: check,
|
||||
// 导出阈值与系数便于调用方/真机校准阶段调整
|
||||
config: {
|
||||
YAW_COEFF: YAW_COEFF,
|
||||
PITCH_BASELINE: PITCH_BASELINE,
|
||||
PITCH_COEFF: PITCH_COEFF,
|
||||
FRONT_YAW_MAX: FRONT_YAW_MAX,
|
||||
FRONT_PITCH_MAX: FRONT_PITCH_MAX,
|
||||
SIDE_YAW_MIN: SIDE_YAW_MIN,
|
||||
SIDE_YAW_MAX: SIDE_YAW_MAX,
|
||||
SIDE_PITCH_MAX: SIDE_PITCH_MAX,
|
||||
ROLL_MAX: ROLL_MAX
|
||||
}
|
||||
};
|
||||
}));
|
||||
|
||||
// -------------------------- Node 自测 --------------------------
|
||||
if (typeof module !== 'undefined' && typeof require !== 'undefined' && require.main === module) {
|
||||
var HeadPose = module.exports;
|
||||
var failures = 0;
|
||||
|
||||
function ok(cond, msg) {
|
||||
if (cond) {
|
||||
console.log('PASS ' + msg);
|
||||
} else {
|
||||
failures++;
|
||||
console.error('FAIL ' + msg);
|
||||
}
|
||||
}
|
||||
|
||||
// 合成对称正脸：眼距 100，脸高 170，pitch 偏移恰好落在基线上
|
||||
function makeFrontal() {
|
||||
var pts = [];
|
||||
for (var i = 0; i < 68; i++) { pts.push({ x: 200, y: 150 }); }
|
||||
pts[36] = { x: 150, y: 100 }; // 左眼外角（画面左）
|
||||
pts[45] = { x: 250, y: 100 }; // 右眼外角（画面右）
|
||||
pts[19] = { x: 170, y: 70 };
|
||||
pts[24] = { x: 230, y: 70 };
|
||||
pts[8] = { x: 200, y: 240 }; // 下巴 → 脸高 240-70=170
|
||||
pts[30] = { x: 200, y: 140 }; // 鼻尖居中
|
||||
pts[33] = { x: 200, y: 161.5 }; // (161.5-85)/170 = 0.45 = PITCH_BASELINE
|
||||
return pts;
|
||||
}
|
||||
|
||||
// 把鼻点横向偏移 17.7px，模拟 ~45° 侧脸（向画面右侧偏 = 被摄者向左转；偏移量按 YAW_COEFF=3.8 数值标定）
|
||||
function makeSide() {
|
||||
var pts = makeFrontal();
|
||||
pts[30] = { x: 217.7, y: 140 };
|
||||
pts[33] = { x: 217.7, y: 161.5 };
|
||||
return pts;
|
||||
}
|
||||
|
||||
// 1) 对称正脸 → yaw/pitch/roll ≈ 0
|
||||
var front = HeadPose.estimate(makeFrontal(), false);
|
||||
ok(Math.abs(front.yaw) < 0.5, '正脸 yaw≈0 (got ' + front.yaw.toFixed(2) + ')');
|
||||
ok(Math.abs(front.pitch) < 1, '正脸 pitch≈0 (got ' + front.pitch.toFixed(2) + ')');
|
||||
ok(Math.abs(front.roll) < 0.5, '正脸 roll≈0 (got ' + front.roll.toFixed(2) + ')');
|
||||
|
||||
// 2) 正脸 front check 通过
|
||||
var fc = HeadPose.check(makeFrontal(), 'front', false);
|
||||
ok(fc.ok === true && fc.hint === '保持不动', '正脸 front ok，hint=保持不动');
|
||||
|
||||
// 3) 45° 侧脸：读数落在合理区间
|
||||
var side = HeadPose.estimate(makeSide(), false);
|
||||
ok(side.yaw > 40 && side.yaw < 50, '侧脸 yaw≈45° (got ' + side.yaw.toFixed(2) + ')');
|
||||
|
||||
// 4) 方向语义：鼻尖偏画面右 = 被摄者向左转 = target 'right' 通过、'left' 拒绝
|
||||
var rc = HeadPose.check(makeSide(), 'right', false);
|
||||
var lc = HeadPose.check(makeSide(), 'left', false);
|
||||
ok(rc.ok === true, '侧脸（被摄者左转）target=right ok');
|
||||
ok(lc.ok === false && lc.hint === '请向右转头', '同侧脸 target=left 拒绝并引导向右');
|
||||
|
||||
// 5) mirrored=true 翻转 yaw 符号,check 语义随之翻转(同一点集在镜像预览下对应相反的物理转头)
|
||||
var sideM = HeadPose.estimate(makeSide(), true);
|
||||
ok(Math.abs(sideM.yaw + side.yaw) < 0.001, 'mirrored=true 时 yaw 符号翻转');
|
||||
ok(HeadPose.check(makeSide(), 'right', true).ok === false, 'mirrored 语义翻转:check(right) 拒绝');
|
||||
ok(HeadPose.check(makeSide(), 'left', true).ok === true, 'mirrored 语义翻转:check(left) 通过');
|
||||
|
||||
// 6) 反方向侧脸:鼻尖偏画面左 → target 'left' 通过
|
||||
var back = makeSide();
|
||||
back[30] = { x: 182.3, y: 140 };
|
||||
back[33] = { x: 182.3, y: 161.5 };
|
||||
var bc = HeadPose.check(back, 'left', false);
|
||||
ok(bc.ok === true, '反向侧脸 target=left ok');
|
||||
ok(HeadPose.check(back, 'right', false).ok === false, '反向侧脸 target=right 拒绝');
|
||||
|
||||
// 7) 正面步骤只提示回正，不能提前引导拍下一张侧脸。
|
||||
var sc = HeadPose.check(makeSide(), 'front', false);
|
||||
ok(sc.ok === false && sc.hint === '请正对屏幕', '左转侧脸 front 拒绝，hint=请正对屏幕');
|
||||
var scb = makeSide();
|
||||
scb[30] = { x: 182.3, y: 140 };
|
||||
scb[33] = { x: 182.3, y: 161.5 };
|
||||
ok(HeadPose.check(scb, 'front', false).hint === '请正对屏幕', '右转侧脸 front 拒绝，hint=请正对屏幕');
|
||||
|
||||
// 8) roll：右眼（45 点）下移 10px → roll≈5.7°
|
||||
var tilted = makeFrontal();
|
||||
tilted[45] = { x: 250, y: 110 };
|
||||
ok(Math.abs(HeadPose.estimate(tilted, false).roll - 5.71) < 0.2, 'roll≈5.71°');
|
||||
|
||||
// 9) 低头：鼻底上移 → pitch<0，front 拒绝并提示略微抬头
|
||||
var down = makeFrontal();
|
||||
down[33] = { x: 200, y: 100 };
|
||||
var de = HeadPose.estimate(down, false);
|
||||
var dc = HeadPose.check(down, 'front', false);
|
||||
ok(de.pitch < -30, '低头 pitch<0 (got ' + de.pitch.toFixed(2) + ')');
|
||||
ok(dc.ok === false && dc.hint === '请正对屏幕', '低头 front 拒绝，hint=请正对屏幕');
|
||||
var up = makeFrontal();
|
||||
up[33] = { x: 200, y: 200 };
|
||||
ok(HeadPose.check(up, 'front', false).hint === '请正对屏幕', '抬头过多 front 拒绝，hint=请正对屏幕');
|
||||
|
||||
// 10) 非法输入：check 不抛异常，返回兜底引导
|
||||
var bad = HeadPose.check(null, 'front', false);
|
||||
ok(bad.ok === false && bad.hint === '请正对屏幕', '非法输入兜底 hint=请正对屏幕');
|
||||
|
||||
// 11) 退化特征点：全部重合 → dLeft+dRight=0 → yaw=NaN → estimate 返回 null，check 兜底「请正对屏幕」（不再误导「请向左转头」）
|
||||
var flat = [];
|
||||
for (var fi = 0; fi < 68; fi++) { flat.push({ x: 100, y: 100 }); }
|
||||
ok(HeadPose.estimate(flat, false) === null, '特征点重合 → estimate 返回 null');
|
||||
var fc2 = HeadPose.check(flat, 'front', false);
|
||||
ok(fc2.ok === false && fc2.hint === '请正对屏幕', '退化输入 check 兜底 hint=请正对屏幕');
|
||||
|
||||
// 12) 脸高过小 → pitch 不可信，不再静默置 0，走非法分支
|
||||
var tiny = makeFrontal();
|
||||
tiny[8] = { x: 200, y: 70.5 }; // faceHeight = 0.5 ≤ 1
|
||||
ok(HeadPose.estimate(tiny, false) === null, 'faceHeight 过小 → estimate 返回 null');
|
||||
ok(HeadPose.check(tiny, 'front', false).hint === '请正对屏幕', 'faceHeight 过小 check 兜底');
|
||||
|
||||
// 13) Phone feedback: expand the frontal margin to 18 degrees.
|
||||
ok(HeadPose.config.FRONT_YAW_MAX === 18, 'config.FRONT_YAW_MAX = 18');
|
||||
var slight = makeFrontal();
|
||||
slight[30] = { x: 205.6, y: 140 }; // 偏移 5.6 → yaw≈14.9°(YAW_COEFF=3.8 标定)
|
||||
slight[33] = { x: 205.6, y: 161.5 };
|
||||
var se = HeadPose.estimate(slight, false);
|
||||
ok(se.yaw > 13.5 && se.yaw <= 15, '轻微偏头 yaw∈(13.5,15] (got ' + se.yaw.toFixed(2) + ')');
|
||||
var sc2 = HeadPose.check(slight, 'front', false);
|
||||
ok(sc2.ok === true, 'yaw≈14.9° front 通过（真机反馈放宽）');
|
||||
var slight2 = makeFrontal();
|
||||
slight2[30] = { x: 206.2, y: 140 }; // 偏移 6.2 → yaw≈16.2°
|
||||
slight2[33] = { x: 206.2, y: 161.5 };
|
||||
var se2 = HeadPose.estimate(slight2, false);
|
||||
ok(se2.yaw > 15 && se2.yaw < 17.5, '偏头 yaw∈(15,17.5) (got ' + se2.yaw.toFixed(2) + ')');
|
||||
var sc3 = HeadPose.check(slight2, 'front', false);
|
||||
ok(sc3.ok === true, 'yaw≈16.2° front 通过（放宽20%）');
|
||||
|
||||
if (failures > 0) {
|
||||
console.error('\n' + failures + ' 项自测失败');
|
||||
process.exit(1);
|
||||
}
|
||||
console.log('\n全部自测通过');
|
||||
}
|
||||
Vendored
+3
-1
@@ -1,5 +1,7 @@
|
||||
{
|
||||
"skin-score.js": "1f3256fd8d5863de3407c2037df30b6a801ac49858a8a0acab7163f83f642abc",
|
||||
"report-ui.js": "2c6acaad7cf6e9c826f062f9e79d419470b37da71ab86a5399897d62fd695caf",
|
||||
"report-copy.js": "402aa543c3437f4e8043e2281b09d7e4d734c0dd2d103636c9f37fe8aa28d6c2"
|
||||
"report-copy.js": "402aa543c3437f4e8043e2281b09d7e4d734c0dd2d103636c9f37fe8aa28d6c2",
|
||||
"head-pose.js": "2068b76dca267f7de67fde96d6a257792da079b02b5ca189307ca6953edfc8ae",
|
||||
"capture-quality.js": "895be1a2a28ae8878f8f24b2e3ad20cfa325b4e73c73b0ed72924124a9c70d23"
|
||||
}
|
||||
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2018 Vincent Mühler
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
+202
@@ -0,0 +1,202 @@
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Portions Copyright (c) Microsoft Corporation.
|
||||
Portions Copyright 2017 Google Inc.
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
Vendored
+242
@@ -0,0 +1,242 @@
|
||||
# Local tensor face engine
|
||||
|
||||
Runtime adapter: `taobao/utils/native-face.js`.
|
||||
|
||||
The vendor bundle, tiny detector and full 68-point model come from the existing,
|
||||
unchanged `h5/vendor/faceapi/` files. The added tiny 68-point model is downloaded
|
||||
only from the same official upstream's `weights/` directory; its manifest,
|
||||
77224-byte shard and source URLs/hashes are in `reference/native-face-models/`.
|
||||
Upstream is
|
||||
https://github.com/justadudewhohacks/face-api.js. MIT and TensorFlow Apache 2.0
|
||||
licenses are included; original inline Google/Microsoft notices are retained.
|
||||
|
||||
Build or verify from the repository root:
|
||||
|
||||
```
|
||||
node taobao/scripts/build-native-face.cjs
|
||||
node taobao/scripts/build-native-face.cjs --check
|
||||
node --test taobao/test/native-face.test.cjs
|
||||
node taobao/scripts/benchmark-native-face.cjs --repeats=2
|
||||
node taobao/scripts/benchmark-native-face.cjs --guided --input-sizes=256,160,128 --repeats=2
|
||||
```
|
||||
|
||||
`provenance.json` records every source file's SHA-256 and byte length. The
|
||||
quantized model bytes total 627385 bytes including the optional full model;
|
||||
the default tiny detector plus tiny landmark weights total 270545 bytes.
|
||||
Base64 and manifests are packaged in
|
||||
one CJS module. Runtime decoding uses typed arrays, with no filesystem or Buffer.
|
||||
|
||||
The generated face-api copy has a private TFJS global registry and shadows Node
|
||||
`process`/`Buffer`. Optional Node-only imports (`crypto`, `node-fetch`, `util`,
|
||||
`fs`) are replaced with functions that explicitly throw if reached. The
|
||||
tfjs-node help-string reference is also replaced. The build fails if an
|
||||
unreviewed static `require()` remains, because the IDE resolves unreachable
|
||||
imports too. No Node polyfill or native AI plugin is bundled.
|
||||
|
||||
Create an engine with `create({defaultPixelFormat:'RGBA', maxSide:320,
|
||||
inputSize:160, landmarkModel:'tiny', scoreThreshold:0.35})`; these are the
|
||||
defaults. `landmarkModel:'full'` remains available for controlled comparisons.
|
||||
The runtime default backend remains `cpu` for compatibility. Select WebGL
|
||||
explicitly with `create({backend:'webgl', platform:my, ...})`; no unsupported
|
||||
WebGL request silently falls back to the CPU profile that was too slow on phone.
|
||||
`init()` returns a Promise with backend, inputSize, maxSide, landmarkModel and
|
||||
cpuOptimization. `detect(frame)` returns a Promise with original width,
|
||||
height, total faceCount and at most two complete detections. Each detection has
|
||||
`detection.{box:{x,y,width,height},score}` and `landmarks.positions` containing
|
||||
68 `{x,y}` points. All coordinates refer to original raw frame pixels; no
|
||||
mirroring, rotation or preview crop is applied. Two complete detections suffice
|
||||
for the existing multiple-person rejection gate.
|
||||
|
||||
Input must have integer width/height in 1..4096 and tightly packed four-channel
|
||||
data in an ArrayBuffer or typed-array view. RGBA, BGRA, ARGB, ABGR and their
|
||||
8888 aliases are supported. An explicit format is authoritative: the configured
|
||||
default only fills missing metadata. Unknown formats (including NV/YUV), a
|
||||
stride/bytesPerRow other than width*4, and a nonzero rotation marker are rejected.
|
||||
|
||||
`detect()` synchronously snapshots only the downsampled RGB before returning,
|
||||
so native buffer reuse cannot change a queued inference. All model operations
|
||||
use the CPU backend. The lower-level tensor crop/landmark path avoids the
|
||||
high-level `withFaceLandmarks()` canvas dependency. Concurrent inference rejects
|
||||
with `NATIVE_FACE_BUSY`. `dispose()` is idempotent; pending work rejects with
|
||||
`NATIVE_FACE_DISPOSED`, and tensors are released after that work settles. The
|
||||
last engine instance releases the shared model tensors. `stats()` returns only
|
||||
backend, selected configuration, memory counters and lifecycle booleans.
|
||||
|
||||
The CPU `pad-copy` specialization copies contiguous source blocks into the
|
||||
already zero-filled output tensor. It preserves the original pad values exactly;
|
||||
unhandled scalar/complex inputs fall back to the bundled implementation. Disable
|
||||
it with `cpuOptimization:false` (`cpuOptimization:'none'` in returned diagnostics).
|
||||
It does not change model arithmetic or relax quality/freshness gates. The trial
|
||||
1x1 convolution specialization showed no stable benefit and was removed.
|
||||
|
||||
`detect()` additionally returns inputSize, maxSide, landmarkModel,
|
||||
cpuOptimization and `timings.{snapshotMs,modelMs,tensorMs,detectorMs,landmarkMs,
|
||||
totalMs}` in milliseconds. `elapsedMs` remains total elapsed wall time; source
|
||||
frame age must still be calculated from the camera's frame arrival time.
|
||||
|
||||
Tests run the real models without document, Image, canvas, fetch, process,
|
||||
Buffer or host Node imports. The local face fixture derives from the already
|
||||
present reference SDK example `C3_180.jpg`; it is never transmitted. Tests check
|
||||
actual positive face detection and 68 points, all supported byte layouts,
|
||||
original-coordinate scaling, concurrent/disposed calls, native buffer reuse,
|
||||
and zero tensors after final disposal. The pad kernel is tested bit-for-bit
|
||||
against original CPU pad across ranks 1–4, dtypes and padding/constants; the
|
||||
real full-model detection and all 68 points are identical with it enabled or
|
||||
disabled. An aspect-preserving two-face composition must reach the actual
|
||||
native-face-quality single-person rejection gate. Tests print timings/counts,
|
||||
never the image or point coordinates.
|
||||
|
||||
Desktop no-DOM VM stage measurements on the same 540×960 portrait reference
|
||||
(two samples per profile): old full/256/no specialization took about 934 ms
|
||||
(detector 730, landmarks 189, snapshot 16). Tiny/160/pad-copy took about 302 ms
|
||||
(detector 188, landmarks 99, snapshot 15), about 3.1× faster. Default model
|
||||
tensors occupy 1082180 bytes (47 tensors), versus full's 2200644 bytes (68).
|
||||
|
||||
The original small face ratio was 0.208, below the H5 near gate of 0.30. With
|
||||
an aspect-preserving crop targeting a valid larger face, tiny/128 can detect
|
||||
one face and 68 points in about 254 ms; however, 128 misses one person in the
|
||||
two-face regression while 160 detects both. Therefore 160 remains the default.
|
||||
Reducing maxSide from 320 to 192 saved only about 24 ms on the eligible portrait;
|
||||
320 is retained for landmark detail. These are desktop CPU observations, not
|
||||
phone performance guarantees. Benchmark flags `--baseline-cpu`, `--max-side=192`
|
||||
and `--input-sizes=160,128` support reproducing the separate comparisons. A zero
|
||||
face result is explicitly flagged by `allSamplesDetected:false`, not a speed win.
|
||||
|
||||
## Explicit WebGL candidate
|
||||
|
||||
`utils/native-face-webgl.js` obtains an owned logical-layer Canvas using the
|
||||
official synchronous `my.createOffscreenCanvas(32,32)` and
|
||||
`getContext('webgl',{enable_flip_y_after_read_pixels:false})`.
|
||||
The host app must enable its documented Skia capability. The adapter injects the
|
||||
actual GL1 context into the bundled TFJS backend; it never forges HAS_WEBGL or
|
||||
float-extension ENV flags. Initialization runs a 16×16 matrix product, a
|
||||
four-channel convolution, numerical readback checks and observed real shader
|
||||
draw/readPixels counters. A missing or readonly instrumentable native API fails
|
||||
explicitly; the adapter does not report GPU success from API names alone.
|
||||
|
||||
The current device candidate is `LOCAL-FACE-20261102-07`. The preceding `03`
|
||||
candidate executed four matrix shader draws on the iPhone, then failed the
|
||||
strict numerical check with `MATMUL_FAILED`; it did not process camera frames.
|
||||
Candidate `04` tried `default`, `packed_byte` (disables float downloads),
|
||||
then `unpacked_byte` (also disables packed shaders). Each attempt runs the same
|
||||
matrix/convolution/readback checks with the original numerical tolerance. A
|
||||
failed attempt releases its backend and tracked GL objects before the next
|
||||
attempt. Only numerical/readback failures permit another profile; missing APIs,
|
||||
context loss and resource errors stop explicitly. There is no CPU fallback.
|
||||
|
||||
All three profiles failed on the device in `04`. The final unpacked byte
|
||||
attempt observed five draws, one byte read, checksum 0 versus expected 2786,
|
||||
244 mismatches and maximum absolute error 22. These aggregate values have an
|
||||
all-zero signature; they do not by themselves prove every output value is zero
|
||||
or identify the cause. Real camera frames were never processed.
|
||||
|
||||
Candidate `05` disables the host's extra readPixels flip using the documented
|
||||
[Taobao context option](https://developer.alibaba.com/docs/doc.htm?articleId=121761&docType=1&treeId=829).
|
||||
A canvas-height-based read-coordinate conversion with a smaller framebuffer can
|
||||
produce zero output in an isolated experiment; that is a testable hypothesis,
|
||||
not a confirmed description of the device implementation. Before TFJS setup,
|
||||
the adapter checks a 2×2 RGBA8 framebuffer with clear/readback, an asymmetric
|
||||
shader pattern, byte-texture sampling and float-texture sampling. Fixed nonzero
|
||||
synthetic inputs and a prefilled destination sentinel distinguish an unchanged
|
||||
typed array from incorrect GPU output. Any failed preflight stops initialization
|
||||
and releases its graphics objects. Passing this preflight does not replace the
|
||||
original matrix/convolution numerical checks, compatibility selection or model
|
||||
warmup.
|
||||
|
||||
On the device, `05` passed clear/readback but failed the asymmetric shader with
|
||||
three mismatches: expected checksum 2244, actual 2040. The actual checksum equals
|
||||
the preceding clear color's checksum. This is consistent with no draw coverage,
|
||||
but does not uniquely distinguish coverage, coordinates, typed-buffer uploads
|
||||
or GL state. Real camera inference still did not start.
|
||||
|
||||
Candidate `06` explicitly initializes drawing state and clears to black before
|
||||
each draw. It first checks a constant-color `drawArrays` pass and then an indexed
|
||||
pass, followed by the original asymmetric shader and byte/float texture tests.
|
||||
It verifies native strategies in order: `standard`, `buffer_copy` (tightly copy
|
||||
a view's bytes into an ArrayBuffer for standard bufferData upload),
|
||||
`framebuffer_y` (compensate viewport/scissor Y only for a bound framebuffer),
|
||||
then `combined`. These are candidates selected by actual numerical checks, not
|
||||
assumptions based on phone model. Only `VALUE_MISMATCH` permits another native
|
||||
strategy; all other failures stop. All four native strategies share one context
|
||||
and release each probe's objects before the next. The TF profiles still create
|
||||
at most three contexts. A selected native strategy must pass every native test,
|
||||
then the unchanged strict matrix/convolution tests and real-model warmup.
|
||||
The source frame freshness limit remains 1500 ms. Device strategy selection,
|
||||
compatibility, speed and automatic capture still need phone acceptance.
|
||||
|
||||
Candidate `06` failed on the device after its standard constant-array draw
|
||||
passed: `nativeInitialStage=constant_indexed`. The later coordinate candidate's
|
||||
black output is not the original failure. Candidate `07` first rebinds the
|
||||
element buffer immediately before indexed draws. If the indexed result still
|
||||
fails while the array draw passed, it verifies a four-vertex triangle strip as
|
||||
an alternative. Strip probes report `constantQuad:passed` and leave
|
||||
`constantIndexed:not_run`; `drawStrategy:quad_strip` identifies the physical
|
||||
method without claiming the native indexed API passed.
|
||||
|
||||
Only the owned quad with uploaded indices `[0,1,2,2,1,3]` and exact
|
||||
`TRIANGLES/6/UNSIGNED_SHORT/offset0` arguments can be converted. Upload bytes
|
||||
are checked within typed-view bounds. Unknown buffers, different signatures,
|
||||
numeric allocations and buffers modified with bufferSubData are refused;
|
||||
deletion invalidates the record. This matches the pinned upstream
|
||||
[quad data](https://raw.githubusercontent.com/tensorflow/tfjs/tfjs-core-v1.7.0/tfjs-core/src/backends/webgl/gpgpu_util.ts)
|
||||
and retains the original tensor checks and model warmup. Native strategies can
|
||||
each add a verified strip attempt, up to eight probes on the same context.
|
||||
This is an experimental device compatibility path, not an assertion that the
|
||||
Taobao indexed API is generally unsupported. Phone success and speed remain
|
||||
unverified.
|
||||
|
||||
After the numerical checks, initialization loads the selected real models and
|
||||
warms both the detector on synthetic portrait black pixels and the landmark
|
||||
network on a synthetic tensor crop. Warmup results are discarded and never
|
||||
count as user face/pose data. Only after the warmup does initialization return
|
||||
`backend:'webgl'`, `gpu.selftest:'passed'` and `gpu.stage:'ready'`. The source
|
||||
frame age and 1500 ms capture gate remain the camera's responsibility.
|
||||
|
||||
The returned `gpu` record contains fixed stage/code/profile enums, booleans,
|
||||
counts and metrics computed only from the fixed synthetic selftest arrays:
|
||||
requested, selftest, stage, code, contextLost, profile, attemptCount,
|
||||
matmulDraws, convDraws, pixelReads, floatReads, byteReads, selftestMs and
|
||||
warmupMs. Each synthetic matrix/convolution record reports actual length,
|
||||
nonfinite/mismatch counts, maximum absolute error, first expected/actual values
|
||||
and expected/actual checksums. The camera caches those synthetic metrics,
|
||||
profile, attempts and read counts only during initialization; later detection
|
||||
results cannot replace them in copied diagnostics. Errors use
|
||||
`NATIVE_FACE_WEBGL_*` codes and the same safe record. Native error strings,
|
||||
renderer strings, image pixels and coordinates do not enter that record. Each
|
||||
detect checks actual context-loss state before and after model work; a lost
|
||||
backend must be retired and rebuilt.
|
||||
|
||||
The startup record also includes the fixed-input `nativeProbe` stage/result,
|
||||
sentinel-change and mismatch counts, expected/actual checksums, read return-kind
|
||||
enum, GL error and framebuffer status. The record also preserves
|
||||
`nativeInitialStage`/`nativeInitialCode`, selected `nativeStrategy`,
|
||||
`constantArrays`/`constantIndexed`, optional vertex/index buffer byte counts and
|
||||
`pixel0` through `pixel3` as big-endian RGBA uint32 values from fixed synthetic
|
||||
input only. TFJS readback state is collected before
|
||||
throwing for a numerical mismatch, so a failing value no longer hides a native
|
||||
GL error. These fields are cached only during initialization and cannot be
|
||||
replaced by real-camera inference results.
|
||||
|
||||
A shared live engine group admits one backend kind at a time. Initialization,
|
||||
model loading, warmup and inference are queued; decoded weights are not reused
|
||||
across a CPU/WebGL switch. Disposal waits for pending work, then releases model
|
||||
tensors, backend programs/textures, the externally supplied GPGPUContext and all
|
||||
remaining tracked GL objects including TFJS 1.7's vertex buffer/shader leftovers.
|
||||
Native cleanup exceptions are isolated so they cannot preserve a busy lock or
|
||||
replace the original inference error.
|
||||
|
||||
```
|
||||
node --test taobao/test/native-face.test.cjs taobao/test/native-face-webgl.test.cjs
|
||||
```
|
||||
|
||||
The WebGL tests run packaged modules with DOM/Node environment names hidden,
|
||||
explicitly supply real headless WebGL1 and abort all network routes. They cover
|
||||
numerical shader/readback, corrupted FLOAT readback followed by packed byte
|
||||
readback, two failed contexts followed by unpacked byte readback, and all three
|
||||
profiles failing closed. Both compatible paths run the real 68-point model and
|
||||
are compared with CPU face boxes, confidence and landmark geometry. They also
|
||||
cover context loss, initialization failure, shared engines, deferred disposal
|
||||
and rebuilding, with zero final
|
||||
tensors and tracked GL objects. Desktop SwiftShader proves the computation and
|
||||
lifecycle paths; it does not establish native Taobao iPhone compatibility or
|
||||
phone inference speed. Those still require the device's actual diagnostics.
|
||||
+6571
File diff suppressed because one or more lines are too long
+70
@@ -0,0 +1,70 @@
|
||||
{
|
||||
"source": "Existing h5/vendor/faceapi (unchanged) plus official upstream tiny 68 model in reference/native-face-models",
|
||||
"upstream": "https://github.com/justadudewhohacks/face-api.js",
|
||||
"build": "node taobao/scripts/build-native-face.cjs",
|
||||
"verify": "node taobao/scripts/build-native-face.cjs --check",
|
||||
"modifications": [
|
||||
"Module-local TFJS registry",
|
||||
"Shadow process and Buffer to keep Node branches inactive",
|
||||
"Node-only require calls replaced with explicit unsupported stubs"
|
||||
],
|
||||
"nodeOnlyStubs": {
|
||||
"crypto": 1,
|
||||
"@tensorflow/tfjs-node": 1,
|
||||
"node-fetch": 1,
|
||||
"util": 1,
|
||||
"fs": 1
|
||||
},
|
||||
"quantizedBytes": 627385,
|
||||
"sourceFiles": [
|
||||
{
|
||||
"path": "h5/vendor/faceapi/models/tiny_face_detector_model-weights_manifest.json",
|
||||
"bytes": 2953,
|
||||
"sha256": "14c60659a31b6b7b1320077171b8f8adcb24ef0e62dde62ce603bcb49a1b49b5"
|
||||
},
|
||||
{
|
||||
"path": "h5/vendor/faceapi/models/tiny_face_detector_model-shard1",
|
||||
"bytes": 193321,
|
||||
"sha256": "b7503ce7df31039b1c43316a9b865cab6a70dd748cc602d3fa28b551503c3871"
|
||||
},
|
||||
{
|
||||
"path": "h5/vendor/faceapi/models/face_landmark_68_model-weights_manifest.json",
|
||||
"bytes": 7889,
|
||||
"sha256": "d30f6cc341009ea4f8223876959289b96576fc54a2615f92da9741ab9c5f0bbc"
|
||||
},
|
||||
{
|
||||
"path": "h5/vendor/faceapi/models/face_landmark_68_model-shard1",
|
||||
"bytes": 356840,
|
||||
"sha256": "4611ef65c87d836d03d684b30eec4d195d8b219fa1dd58fc58945831c6b9299b"
|
||||
},
|
||||
{
|
||||
"path": "reference/native-face-models/face_landmark_68_tiny_model-weights_manifest.json",
|
||||
"bytes": 4441,
|
||||
"sha256": "3c63b8984302c187b218d9ef5aa149ed8c2c7fa3fe54db078614692bc48d153c"
|
||||
},
|
||||
{
|
||||
"path": "reference/native-face-models/face_landmark_68_tiny_model-shard1",
|
||||
"bytes": 77224,
|
||||
"sha256": "b98e9f2f7da76f8a6dda9741a36ed485b224b889d552de2b2c1bb16217f67bfc"
|
||||
},
|
||||
{
|
||||
"path": "h5/vendor/faceapi/face-api.js",
|
||||
"bytes": 859250,
|
||||
"sha256": "24e27b366566d9c871619d4a3dc0187766f054aecd6858fd40a329ec30a57b0b"
|
||||
}
|
||||
],
|
||||
"downloadedSources": [
|
||||
{
|
||||
"file": "face_landmark_68_tiny_model-weights_manifest.json",
|
||||
"source": "https://raw.githubusercontent.com/justadudewhohacks/face-api.js/master/weights/face_landmark_68_tiny_model-weights_manifest.json",
|
||||
"bytes": 4441,
|
||||
"sha256": "3c63b8984302c187b218d9ef5aa149ed8c2c7fa3fe54db078614692bc48d153c"
|
||||
},
|
||||
{
|
||||
"file": "face_landmark_68_tiny_model-shard1",
|
||||
"source": "https://raw.githubusercontent.com/justadudewhohacks/face-api.js/master/weights/face_landmark_68_tiny_model-shard1",
|
||||
"bytes": 77224,
|
||||
"sha256": "b98e9f2f7da76f8a6dda9741a36ed485b224b889d552de2b2c1bb16217f67bfc"
|
||||
}
|
||||
]
|
||||
}
|
||||
Vendored
+2
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user