52 lines
3.4 KiB
Bash
52 lines
3.4 KiB
Bash
|
#!/usr/bin/env bash
|
|||
|
|
# 一条龙：bash ml/pipeline.sh <阶段> ；阶段按顺序：
|
|||
|
|
# setup 安装 Python/Node 依赖（torch 需先按 CUDA 版本装好）
|
|||
|
|
# kin 导出运动学/碰撞模型 + JS↔PyTorch 对拍（必须 PASS）
|
|||
|
|
# gate1 老师一致性门禁（决定生成时是否加 --consensus 4）
|
|||
|
|
# gen 生成 5 万条老师轨迹（NPROC 进程；CONSENSUS=1 时加共识过滤）
|
|||
|
|
# prep 打包训练样本
|
|||
|
|
# train 预训练（先 2000 步摸吞吐，再正式训练）
|
|||
|
|
# m5 MeanFlow 头门禁：贴立柱集关安全层穿柱率 ≤ 2%（不过 → 用 configs/wta.json 重训）
|
|||
|
|
# apg APG 首轮微调
|
|||
|
|
# mine 挖错循环（3–6 轮，含门禁回滚）
|
|||
|
|
# export 导出 ONNX（fp16）到 webapp/models/
|
|||
|
|
# bench 部署形态评测（Node，策略 + 安全层）
|
|||
|
|
# all 依次执行 kin → bench
|
|||
|
|
set -e
|
|||
|
|
cd "$(dirname "$0")/.."
|
|||
|
|
NPROC=${NPROC:-$(nproc)}
|
|||
|
|
N_TASKS=${N_TASKS:-50000}
|
|||
|
|
CFG=${CFG:-ml/configs/base.json}
|
|||
|
|
stage=${1:-help}
|
|||
|
|
run() { echo "== $*"; "$@"; }
|
|||
|
|
case $stage in
|
|||
|
|
setup) run pip install -r ml/requirements.txt; (cd ml && npm install --no-audit --no-fund) ;;
|
|||
|
|
kin) run node ml/prep/export_kin.cjs; run node ml/eval/dump_parity.cjs 2000; run python -m ml.eval.check_parity ;;
|
|||
|
|
gate1) mkdir -p ml/data; run node ml/gen/consistency.cjs 300 4242 | tee ml/data/consistency.json ;;
|
|||
|
|
gen) per=$(( (N_TASKS + NPROC - 1) / NPROC ))
|
|||
|
|
if [ -z "${CONSENSUS:-}" ] && [ -f ml/data/consistency.json ]; then
|
|||
|
|
CONSENSUS=$(python -c "import json;print(1 if json.load(open('ml/data/consistency.json'))['consistentByGateRule']<0.9 else 0)")
|
|||
|
|
echo "一致性门禁结果 → CONSENSUS=$CONSENSUS"
|
|||
|
|
fi
|
|||
|
|
extra=""; [ "${CONSENSUS:-0}" = "1" ] && extra="--consensus 4"
|
|||
|
|
run bash ml/gen/run_parallel.sh $per $NPROC 1 "$extra" ;;
|
|||
|
|
prep) run bash ml/prep/run_prep.sh $NPROC ;;
|
|||
|
|
train) run python -m ml.train --samples ml/data/samples --out ml/runs/bench --steps 2000 --no-eval --config $CFG
|
|||
|
|
run python -m ml.train --samples ml/data/samples --out ml/runs/base --config $CFG ;;
|
|||
|
|
m5) [ -f ml/runs/nc_gate.jsonl ] || run python -m ml.mining.mine_round --make-gate 1000 --seed 4321 --mix 0,0,1,0 --name nc_gate.jsonl --out ml/runs
|
|||
|
|
run python -m ml.sim.closed_loop --ckpt ml/runs/base/best.pt --tasks ml/runs/nc_gate.jsonl --n 1000 --out ml/runs/m5_gate.json
|
|||
|
|
python - <<'PY'
|
|||
|
|
import json; r = json.load(open('ml/runs/m5_gate.json'))
|
|||
|
|
print('贴立柱集（关安全层）穿柱率 %.2f%%，到达率 %.2f%%' % (100 * r['collision_rate'], 100 * r['success']))
|
|||
|
|
print('M5 门禁：' + ('通过' if r['collision_rate'] <= 0.02 else '不通过 → CFG=ml/configs/wta.json bash ml/pipeline.sh train'))
|
|||
|
|
PY
|
|||
|
|
;;
|
|||
|
|
apg) run python -m ml.apg.apg_finetune --init ml/runs/base/best.pt --samples ml/data/samples --out ml/runs/apg; cp ml/runs/apg/best.pt ml/runs/current.pt ;;
|
|||
|
|
mine) run bash ml/mining/loop.sh ${ROUNDS:-6} ${APG_STEPS:-1000} ${MINE_N:-50000} ;;
|
|||
|
|
export) ck=ml/runs/current.pt; [ -f $ck ] || ck=ml/runs/base/best.pt
|
|||
|
|
run python -m ml.export_onnx --ckpt $ck --out webapp/models/traj_policy.onnx --fp16 ;;
|
|||
|
|
bench) run node tests/policy_bench.cjs webapp/models/traj_policy.onnx nc,route --nc1000 --out ml/runs/policy_bench.json ;;
|
|||
|
|
all) for s in kin gate1 gen prep train m5 apg mine export bench; do bash ml/pipeline.sh $s; done ;;
|
|||
|
|
*) sed -n '2,16p' "$0" ;;
|
|||
|
|
esac
|