Hark
5591adb39a
- B-1 运行时投影护栏恢复 5 mm；老师轨迹按认证最小间隙 < 3 mm 剔除（stats/build_dataset，gapDrop） - B-2 APG 端点+中点 hinge 取均值；B-3 check_r2 空匹配保护、5000×50000、分块 256，pass=false 时 prep 停下 - B-4 R7 按全部 B/C 题统计；B-5 r8 起点贴柱；B-7 pipeline r4（export_onnx --random，训练前测延迟） - B-8 起步失败 ≤0.2%、column_gap 分块、pipefail、门禁结果先写 .tmp - 训练控制台：ml/console.bat|sh → ml/monitor.py（开始/停止/进度/日志接口）+ monitor.html； pipeline.sh all 支持 FROM/TO，阶段状态写 ml/runs/pipeline.json（ml/pstate.py）；训练/APG 日志加 total、t - 文档：README 一键运行与训练控制台；审查文档追加第三轮处置；方案余量决策与 R4 时点
29 lines
2.3 KiB
JavaScript
29 lines
2.3 KiB
JavaScript
/* M1 统计：node ml/gen/stats.cjs ml/data/shard_*.jsonl > ml/data/stats.json */
|
|
'use strict';
|
|
const fs = require('fs');
|
|
const files = process.argv.slice(2);
|
|
/* 2026-10-18：老师样本按认证最小间隙过滤（< MIN_GAP_MM 的轨迹不进训练集，build_dataset.cjs 同值）。
|
|
安全护栏（运行时投影 5 mm）不迁就数据分布；样本数与补量只按过滤后计。 */
|
|
const MIN_GAP_MM = +(process.env.MIN_GAP_MM || 3);
|
|
let gapDrop = 0;
|
|
const by = {}; let total = 0, keep = 0, steps = 0, samples = 0, padTail = 0;
|
|
const q = a => { a.sort((x, y) => x - y); return a.length ? { p10: +a[Math.floor(a.length * 0.1)].toFixed(1), p50: +a[a.length >> 1].toFixed(1), p90: +a[Math.floor(a.length * 0.9)].toFixed(1), max: +a[a.length - 1].toFixed(1) } : null; };
|
|
const plan = [], certMs = [], travel = [], exec = [], gaps = [];
|
|
for (const f of files) for (const line of fs.readFileSync(f, 'utf8').split('\n')) {
|
|
if (!line) continue; const r = JSON.parse(line); total++;
|
|
const k = r.cat + '/' + r.mode; const b = by[k] = by[k] || { n: 0, reached: 0, certFail: 0, keep: 0, demoted: 0, consensusDrop: 0, j6Frozen: 0 };
|
|
b.n++; if (r.reached) b.reached++; if (r.cert && !r.cert.ok) b.certFail++; if (r.demoted) b.demoted++; if (r.why === 'consensus') b.consensusDrop++; if (r.j6Frozen) b.j6Frozen++;
|
|
if (r.plan_ms != null) plan.push(r.plan_ms); if (r.cert) certMs.push(r.cert.ms); if (r.cert) gaps.push(r.cert.minGap);
|
|
if (r.keep && r.cert && r.cert.minGap != null && r.cert.minGap < MIN_GAP_MM) { gapDrop++; b.gapDrop = (b.gapDrop || 0) + 1; }
|
|
else if (r.keep) { b.keep++; keep++; travel.push(r.travel_deg); exec.push(r.exec_s);
|
|
const n = r.traj.length - 1; steps += n; const s = Math.floor(n / 3) + 1; samples += s;
|
|
for (let t = 0; t <= n; t += 3) if (t + 16 > n) padTail++; }
|
|
}
|
|
const out = { tasks: total, keep, keepRate: +(keep / total).toFixed(3), byCatMode: by,
|
|
planMs: q(plan), certMs: q(certMs), vertexMinGapMm: q(gaps), travelDeg: q(travel), execS: q(exec),
|
|
samplesEvery3: samples, samplesPerTask: +(samples / keep).toFixed(1), paddedSampleShare: +(padTail / samples).toFixed(3),
|
|
projectedSamplesFor50k: Math.round(samples / total * 50000),
|
|
gapDrop, minGapFilterMm: MIN_GAP_MM,
|
|
consensusDrop: Object.values(by).reduce((a, b) => a + b.consensusDrop, 0) };
|
|
console.log(JSON.stringify(out, null, 1));
|