技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
data-preparation【数据与研究】Prepare and validate UniAD nuScenes, CAN bus, map, info-PKL, and motion-anchor data layout without launching training or evaluation.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this sub-skill when the user needs to prepare, validate, or troubleshoot the data assets required by UniAD on nuScenes:
data/nuscenes/, including CAN bus and map extensions;data/infos/;data/others/;Do not launch training, evaluation, visualization, or model editing from here.
training-evaluation.config-and-model-architecture.visualization-and-results.v1.0 trainval/test, trainval-only, test-only, or v1.0-mini.data/others/motion_anchor_infos_mode6.pkl.scripts/check_uniad_data_layout.py before constructing train/eval commands elsewhere.scripts/build_data_command.py; do not run a full conversion unless the user has confirmed the raw nuScenes/CAN bus/map assets and runtime dependencies are present.data/nuscenes/... or absolute dataset paths, the active UniAD config may need data_root = "" instead of the default data_root = "data/nuscenes/".references/data-preparation.md — layout, download choices, info-generation command semantics, and config path cautions.references/data-formats.md — expected PKL, CAN bus, map, raw-sensor, and motion-anchor contents.references/troubleshooting.md — symptoms and fixes for missing directories, missing PKLs, motion anchors, root-path mismatches, network/download limits, and split confusion.scripts/check_uniad_data_layout.py — self-contained dry validation of the expected data layout and common PKL path-root risk.scripts/build_data_command.py — self-contained dry command renderer adapted from UniAD's data conversion wrapper semantics.