data-preparation
Guides RoboSat data preparation for Slippy Map imagery, OSM features, rasterized masks, tile CSVs, dataset configs, class weights, and safe CLI validation.
- License 许可
- MIT
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- data-preparation
- license
- MIT
- metadata
- { "disco-role": "operating" }
- description
- Guides RoboSat data preparation for Slippy Map imagery, OSM features, rasterized masks, tile CSVs, dataset configs, class weights, and safe CLI validation.
- disable-model-invocation
- true
02 资源文件 5
- 参考文档references/api-reference.md4.5 KB
- 参考文档references/data-formats.md2.6 KB
- 参考文档references/troubleshooting.md2.6 KB
- 参考文档references/workflows.md2.4 KB
- 脚本scripts/validate_slippy_map.py7.1 KB
03 SKILL.md 正文
Data Preparation
Use this sub-skill when you need RoboSat dataset inputs, not model training or post-processing.
Use this for
- extracting OSM features into GeoJSON
- building tile cover CSVs
- downloading imagery into Slippy Map directories
- rasterizing features into masks
- computing class weights from training labels
- validating tile layout and tile-list alignment
- drafting dataset TOML templates
Route elsewhere
- model lifecycle: training, export, predict, serve, checkpoints, UNet
- feature post-processing: probability-to-mask, features, merge, dedupe, compare
Quick path
- Start with the recipes in workflows.
- Check the data layouts in data formats.
- Use the API notes in API reference when wiring helpers.
- Run validate_slippy_map.py before weights or rasterize jobs.
- Use troubleshooting for install, geometry, sync, or zoom problems.
Common outputs
features.geojsontiles.csv- Slippy Map image and mask trees
- dataset TOML with
[common]and[weights] - class weights list from
rs weights
Safe defaults
- Prefer
rsorpython -m robosat.tools ...from an installed environment. - Keep downloads, tokens, and large datasets outside the skill tree.
- Treat
rs rasterizeas binary-only in this release.
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).