visualization
Inspects and renders VAD prediction artifacts with nuScenes camera, LiDAR, vector-map, motion, and planning context.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- visualization
- license
- Apache 2.0
- metadata
- { "disco-role": "operating" }
- description
- Inspects and renders VAD prediction artifacts with nuScenes camera, LiDAR, vector-map, motion, and planning context.
- disable-model-invocation
- true
02 资源文件 3
- 参考文档references/rendering-reference.md2.8 KB
- 参考文档references/troubleshooting.md2.1 KB
- 脚本scripts/inspect_result_artifact.py2.5 KB
03 SKILL.md 正文
VAD visualization
Use this route when a user has VAD inference output and wants a video/BEV view, trajectory/map overlays, or diagnosis of empty or misaligned results.
Route
- Generate or locate a result artifact with training-evaluation, preferably with its
--outpath recorded. - Read rendering-reference.md and inspect the artifact with
python scripts/inspect_result_artifact.py RESULTbefore loading nuScenes. - Confirm the nuScenes root, calibration/pose/sample files, six camera channels, and output directory.
- Run the repository's compatible renderer using placeholder paths only after the artifact and data preflight pass. Rendering needs the legacy VAD plugin and native dependencies.
- Diagnose coordinate and normalization mismatches with troubleshooting.md.
The bundled inspector never imports VAD, nuScenes, matplotlib, or a renderer. It is a structural preflight only; it does not render or download.
Scope boundaries
- Data acquisition and temporal conversion: data-preparation.
- Model/checkpoint/evaluation generation: training-evaluation.
- Plugin API/config changes: architecture-configuration.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).