[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797M8DRKJSVYG1YZATVKKMH":3,"skill-same:01M797M8DRKJSVYG1YZATVKKMH":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M797M8DRKJSVYG1YZATVKKMH","training",null,"Guides YOLOP training, validation, evaluation metrics, staged multitask flags, checkpoints, auto-anchor behavior, and training smoke diagnostics.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Ftraining\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: training\ndescription: \"Guides YOLOP training, validation, evaluation metrics, staged\n  multitask flags, checkpoints, auto-anchor behavior, and training smoke\n  diagnostics.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# YOLOP Training and Evaluation\n\nUse this sub-skill when the task asks to train YOLOP, run validation\u002Fevaluation, change end-to-end versus staged\u002Fsingle-task modes, diagnose `tools\u002Ftrain.py` or `tools\u002Ftest.py`, reason about `MultiHeadLoss`, configure auto-anchor, or interpret YOLOP detection\u002Fsegmentation metrics.\n\nDo not use this sub-skill for only preparing data roots (use `data-preparation`), running demo inference (use `inference`), or exporting ONNX\u002FTensorRT artifacts (use `export`).\n\n## Read first\n\n- [references\u002Fworkflows.md](references\u002Fworkflows.md) gives the source training and evaluation command shapes, config fields, checkpoint behavior, and staged\u002Fsingle-task modes.\n- [references\u002Fevaluation.md](references\u002Fevaluation.md) explains validation outputs, detection metrics, segmentation metrics, and visualization side effects.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers data\u002Fconfig errors, torch-version loss issues, GPU\u002FDDP pitfalls, batch size problems, and auto-anchor failures.\n- Run [scripts\u002Ftrain_smoke.py](scripts\u002Ftrain_smoke.py) before expensive training to verify imports, model construction, forward shapes, and optionally expose loss-version incompatibilities on a tiny tensor.\n\n## Minimal workflow\n\n1. Validate BDD100K roots and masks with the `data-preparation` sub-skill.\n2. Edit or patch `lib.config.cfg` values for dataset roots, image size, batch sizes, workers, training mode flags, pretrained checkpoint paths, and `LOG_DIR`.\n3. Run a CPU or CUDA model smoke:\n\n```bash\npython sub-skills\u002Ftraining\u002Fscripts\u002Ftrain_smoke.py --repo-root \u002Fpath\u002Fto\u002FYOLOP --device cpu --image-size 128\n```\n\n4. Start training from the YOLOP checkout root:\n\n```bash\nPYTHONPATH=. python tools\u002Ftrain.py\n```\n\n5. For distributed training, only after a compatible CUDA torch\u002Ftorchvision stack is installed and dataset\u002Fbatch settings are ready:\n\n```bash\nPYTHONPATH=. python -m torch.distributed.launch --nproc_per_node=N tools\u002Ftrain.py\n```\n\n6. Evaluate a checkpoint:\n\n```bash\nPYTHONPATH=. python tools\u002Ftest.py --weights weights\u002FEnd-to-end.pth\n```\n\n## Important decisions\n\n- All staged\u002Fsingle-task flags false means end-to-end multitask training.\n- `TRAIN.SEG_ONLY`, `DET_ONLY`, `ENC_SEG_ONLY`, `ENC_DET_ONLY`, `DRIVABLE_ONLY`, and `LANE_ONLY` change both parameter freezing and loss components.\n- `NEED_AUTOANCHOR=True` is not a cheap smoke check; it runs k-means\u002Fevolution over the training labels.\n- `tools\u002Ftrain.py` and `tools\u002Ftest.py` use the yacs config more than their parser suggests; several parsed arguments are not applied by `update_config` in the current source.\n- CPU smokes validate code shape, but full training and reported paper\u002FREADME metrics require real BDD100K data and practical GPU runtime.\n\n## Cross-links\n\n- If dataset construction fails before the model starts, switch to [..\u002Fdata-preparation\u002FSKILL.md](..\u002Fdata-preparation\u002FSKILL.md).\n- If the trained checkpoint should be used for a demo, switch to [..\u002Finference\u002FSKILL.md](..\u002Finference\u002FSKILL.md).\n- If the checkpoint should become ONNX or TensorRT artifacts, switch to [..\u002Fexport\u002FSKILL.md](..\u002Fexport\u002FSKILL.md).\n","# YOLOP Training and Evaluation\n\nUse this sub-skill when the task asks to train YOLOP, run validation\u002Fevaluation, change end-to-end versus staged\u002Fsingle-task modes, diagnose `tools\u002Ftrain.py` or `tools\u002Ftest.py`, reason about `MultiHeadLoss`, configure auto-anchor, or interpret YOLOP detection\u002Fsegmentation metrics.\n\nDo not use this sub-skill for only preparing data roots (use `data-preparation`), running demo inference (use `inference`), or exporting ONNX\u002FTensorRT artifacts (use `export`).\n\n## Read first\n\n- [references\u002Fworkflows.md](references\u002Fworkflows.md) gives the source training and evaluation command shapes, config fields, checkpoint behavior, and staged\u002Fsingle-task modes.\n- [references\u002Fevaluation.md](references\u002Fevaluation.md) explains validation outputs, detection metrics, segmentation metrics, and visualization side effects.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers data\u002Fconfig errors, torch-version loss issues, GPU\u002FDDP pitfalls, batch size problems, and auto-anchor failures.\n- Run [scripts\u002Ftrain_smoke.py](scripts\u002Ftrain_smoke.py) before expensive training to verify imports, model construction, forward shapes, and optionally expose loss-version incompatibilities on a tiny tensor.\n\n## Minimal workflow\n\n1. Validate BDD100K roots and masks with the `data-preparation` sub-skill.\n2. Edit or patch `lib.config.cfg` values for dataset roots, image size, batch sizes, workers, training mode flags, pretrained checkpoint paths, and `LOG_DIR`.\n3. Run a CPU or CUDA model smoke:\n\n```bash\npython sub-skills\u002Ftraining\u002Fscripts\u002Ftrain_smoke.py --repo-root \u002Fpath\u002Fto\u002FYOLOP --device cpu --image-size 128\n```\n\n4. Start training from the YOLOP checkout root:\n\n```bash\nPYTHONPATH=. python tools\u002Ftrain.py\n```\n\n5. For distributed training, only after a compatible CUDA torch\u002Ftorchvision stack is installed and dataset\u002Fbatch settings are ready:\n\n```bash\nPYTHONPATH=. python -m torch.distributed.launch --nproc_per_node=N tools\u002Ftrain.py\n```\n\n6. Evaluate a checkpoint:\n\n```bash\nPYTHONPATH=. python tools\u002Ftest.py --weights weights\u002FEnd-to-end.pth\n```\n\n## Important decisions\n\n- All staged\u002Fsingle-task flags false means end-to-end multitask training.\n- `TRAIN.SEG_ONLY`, `DET_ONLY`, `ENC_SEG_ONLY`, `ENC_DET_ONLY`, `DRIVABLE_ONLY`, and `LANE_ONLY` change both parameter freezing and loss components.\n- `NEED_AUTOANCHOR=True` is not a cheap smoke check; it runs k-means\u002Fevolution over the training labels.\n- `tools\u002Ftrain.py` and `tools\u002Ftest.py` use the yacs config more than their parser suggests; several parsed arguments are not applied by `update_config` in the current source.\n- CPU smokes validate code shape, but full training and reported paper\u002FREADME metrics require real BDD100K data and practical GPU runtime.\n\n## Cross-links\n\n- If dataset construction fails before the model starts, switch to [..\u002Fdata-preparation\u002FSKILL.md](..\u002Fdata-preparation\u002FSKILL.md).\n- If the trained checkpoint should be used for a demo, switch to [..\u002Finference\u002FSKILL.md](..\u002Finference\u002FSKILL.md).\n- If the checkpoint should become ONNX or TensorRT artifacts, switch to [..\u002Fexport\u002FSKILL.md](..\u002Fexport\u002FSKILL.md).\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Ftraining",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill training",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill training",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Ftraining\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fevaluation.md","REFERENCE","参考文档",2784,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Ftraining\u002Freferences\u002Fevaluation.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",3201,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Ftraining\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",4187,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Ftraining\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Ftrain_smoke.py","SCRIPT","脚本",4302,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyolop\u002Fsub-skills\u002Ftraining\u002Fscripts\u002Ftrain_smoke.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp 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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","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()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert 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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch 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).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]