45403b23b4
- 新增 app/tree/repair/regenerator.py(VLM 重生成 + 级联修复) - supplement.py: deduplicate_field str() 防御 + inject_value strip - patch.py: ruff format 格式化 - repair_trees.sh: conda source 激活修复 - 新增 migrate_from_trm4.sh 迁移工具 - enhance/__init__.py → repair/__init__.py 重命名 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
30 lines
1001 B
Bash
Executable File
30 lines
1001 B
Bash
Executable File
#!/usr/bin/env bash
|
||
# 树修复管线:检测 + VLM 重生成 + 校验 + Q&A 补全
|
||
#
|
||
# 用法:
|
||
# bash scripts/repair_trees.sh # 默认 16 并发续跑
|
||
# bash scripts/repair_trees.sh --dry-run # 仅检测不修复
|
||
# bash scripts/repair_trees.sh --reaggregate-all # 强制全量重聚合
|
||
# CONCURRENCY=8 bash scripts/repair_trees.sh # 自定义并发数
|
||
#
|
||
# 日志输出:
|
||
# stderr → 终端实时显示
|
||
# logs/repair_trees.log → 完整日志(自动 rotation 50MB)
|
||
# logs/repair_telemetry.db → LLM/VLM 调用遥测
|
||
# logs/repair_progress.json → 断点续跑进度
|
||
|
||
set -euo pipefail
|
||
|
||
CONCURRENCY="${CONCURRENCY:-16}"
|
||
|
||
# shellcheck source=/dev/null
|
||
source "$(conda info --base)/etc/profile.d/conda.sh"
|
||
conda activate Video-Tree-TRM
|
||
|
||
python tools/repair_trees.py \
|
||
--videos-dir store/videos \
|
||
--srt-dir data/Video-MME/subtitle \
|
||
--questions-dir store/questions/benchmarks/Video-MME \
|
||
--concurrency "$CONCURRENCY" \
|
||
"$@"
|