[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VPPJVS016VCYJH68DFW55":3,"skill-same:01M78VPPJVS016VCYJH68DFW55":70},{"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},"01M78VPPJVS016VCYJH68DFW55","deep-person-reid",null,"Route Torchreid deep-person-reid workflows for person re-identification training, evaluation, feature extraction, metrics, visualization, and model export.","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\u002Fdeep-person-reid\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deep-person-reid\ndescription: \"Route Torchreid deep-person-reid workflows for person\n  re-identification training, evaluation, feature extraction, metrics,\n  visualization, and model export.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# deep-person-reid \u002F Torchreid\n\nUse this repo skill when a task involves Torchreid (`torchreid`) or Kaiyang Zhou's deep-person-reid package for person re-identification (ReID). It is an operating graph for package use, not a maintainer-development guide.\n\n## Use this skill for\n\n- Training or evaluating image\u002Fvideo ReID models such as OSNet, OSNet-AIN, ResNet, MLFN, HACNN, PCB, or MobileNet variants.\n- Building Torchreid data managers, custom datasets, samplers, losses, optimizers, schedulers, and `Engine.run(...)` plans.\n- Extracting embeddings with `FeatureExtractor`, computing query\u002Fgallery distances, CMC\u002FmAP, re-ranking, model complexity, ranked-result visualization, or activation maps.\n- Exporting core Torchreid checkpoints toward ONNX, OpenVINO, or TFLite-style artifacts with explicit optional-dependency checks.\n- Diagnosing install\u002Fimport, dataset-layout, config, optional-backend, checkpoint, or export failures.\n\n## Do not use this skill for\n\n- General person ReID literature surveys with no Torchreid\u002Fdeep-person-reid implementation need.\n- DML, OSNet-AIN NAS, or PA-100K attribute-recognition project-local scripts unless a future extension bundles those projects; they are recorded as long-tail gaps rather than runtime routes here.\n- Claims that CUDA, OpenVINO, TensorFlow, TFLite, or large-dataset training was verified unless the current task runs those checks.\n\n## Install\n\nFrom a fresh clone of the package, install the runtime dependencies and the local package itself:\n\n```bash\npython -m pip install -U pip\npython -m pip install -r requirements.txt\npython -m pip install -e .\n```\n\nIf editable installation fails because build-time NumPy\u002FCython visibility is missing, install the needed build prerequisites first and retry with `--no-build-isolation`, then use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for the exact recovery steps.\n\nRun the quick verification check after install:\n\n```bash\npython scripts\u002Fcheck_torchreid_env.py --model-name osnet_x0_25\n```\n\n## First checks\n\n1. Confirm the package is installed in the task environment:\n\n   ```python\n   import torchreid\n   print(torchreid.__version__)\n   ```\n\n2. Confirm PyTorch\u002Ftorchvision match the intended backend. CPU is enough for API inspection and small smoke tests; CUDA is optional but practical for real training\u002Fevaluation.\n3. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is current for a particular checkout.\n4. For package\u002Fmodule coverage and backend status, read [references\u002Fpackage-overview.md](references\u002Fpackage-overview.md).\n5. For cross-cutting failures, start with [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n6. To run a quick non-training package check, use [scripts\u002Fcheck_torchreid_env.py](scripts\u002Fcheck_torchreid_env.py).\n\n## Route map\n\n### Training, evaluation, data, and configs\n\nUse [sub-skills\u002Ftraining-evaluation\u002FSKILL.md](sub-skills\u002Ftraining-evaluation\u002FSKILL.md) when the request names training, testing, data managers, datasets, config files, CLI-style command generation, split-log parsing, or dataset mean\u002Fstd.\n\nTypical triggers: `ImageDataManager`, `VideoDataManager`, `Engine.run`, `scripts\u002Fmain.py`-style workflow, `test.evaluate True`, `visrank`, Market1501\u002FDukeMTMC\u002FMSMT\u002FCUHK03\u002FMARS layouts, `RandomIdentitySampler`, `train.lr_scheduler`, checkpoint resume\u002Ffine-tune.\n\n### Feature extraction, models, metrics, and visualization\n\nUse [sub-skills\u002Ffeature-extraction\u002FSKILL.md](sub-skills\u002Ffeature-extraction\u002FSKILL.md) when the request names embeddings, `FeatureExtractor`, model keys, checkpoint loading, distance matrices, CMC\u002FmAP, re-ranking, model complexity, ranked-result visualizations, or activation maps.\n\nTypical triggers: compare query\u002Fgallery images, compute cosine\u002Feuclidean distances, load local weights without downloads, `evaluate_rank`, `re_ranking`, `compute_model_complexity`, `return_featuremaps=True`.\n\n### Model export and deployment artifacts\n\nUse [sub-skills\u002Fmodel-export\u002FSKILL.md](sub-skills\u002Fmodel-export\u002FSKILL.md) when the request asks to export a trained core Torchreid checkpoint to ONNX, OpenVINO, or TFLite-style outputs.\n\nTypical triggers: `--include onnx`, OpenVINO Model Optimizer, `openvino2tensorflow`, dynamic axes, opset choice, model-name inference, optional export dependency failures.\n\n## Root operating rules\n\n- Prefer local checkpoint paths and explicit model names. Avoid automatic pretrained downloads unless the user approves network access.\n- Treat datasets as user-provided unless a specific dataset class has an automated download path and the user approves network access.\n- Use bundled helper scripts for command planning and smoke checks; do not tell future agents to run source-repo scripts from an unavailable checkout.\n- Keep CPU verification separate from CUDA claims. CPU import\u002Fmodel\u002Ffeature checks do not prove multi-GPU training throughput.\n- Use export extras only for requested export formats; the core skill does not install ONNX\u002FOpenVINO\u002FTensorFlow by default.\n- If a task requires the excluded `projects\u002F` workflows, either report the long-tail gap or extend the repo skill by bundling those project sources and verification cases first.\n","# deep-person-reid \u002F Torchreid\n\nUse this repo skill when a task involves Torchreid (`torchreid`) or Kaiyang Zhou's deep-person-reid package for person re-identification (ReID). It is an operating graph for package use, not a maintainer-development guide.\n\n## Use this skill for\n\n- Training or evaluating image\u002Fvideo ReID models such as OSNet, OSNet-AIN, ResNet, MLFN, HACNN, PCB, or MobileNet variants.\n- Building Torchreid data managers, custom datasets, samplers, losses, optimizers, schedulers, and `Engine.run(...)` plans.\n- Extracting embeddings with `FeatureExtractor`, computing query\u002Fgallery distances, CMC\u002FmAP, re-ranking, model complexity, ranked-result visualization, or activation maps.\n- Exporting core Torchreid checkpoints toward ONNX, OpenVINO, or TFLite-style artifacts with explicit optional-dependency checks.\n- Diagnosing install\u002Fimport, dataset-layout, config, optional-backend, checkpoint, or export failures.\n\n## Do not use this skill for\n\n- General person ReID literature surveys with no Torchreid\u002Fdeep-person-reid implementation need.\n- DML, OSNet-AIN NAS, or PA-100K attribute-recognition project-local scripts unless a future extension bundles those projects; they are recorded as long-tail gaps rather than runtime routes here.\n- Claims that CUDA, OpenVINO, TensorFlow, TFLite, or large-dataset training was verified unless the current task runs those checks.\n\n## Install\n\nFrom a fresh clone of the package, install the runtime dependencies and the local package itself:\n\n```bash\npython -m pip install -U pip\npython -m pip install -r requirements.txt\npython -m pip install -e .\n```\n\nIf editable installation fails because build-time NumPy\u002FCython visibility is missing, install the needed build prerequisites first and retry with `--no-build-isolation`, then use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for the exact recovery steps.\n\nRun the quick verification check after install:\n\n```bash\npython scripts\u002Fcheck_torchreid_env.py --model-name osnet_x0_25\n```\n\n## First checks\n\n1. Confirm the package is installed in the task environment:\n\n   ```python\n   import torchreid\n   print(torchreid.__version__)\n   ```\n\n2. Confirm PyTorch\u002Ftorchvision match the intended backend. CPU is enough for API inspection and small smoke tests; CUDA is optional but practical for real training\u002Fevaluation.\n3. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is current for a particular checkout.\n4. For package\u002Fmodule coverage and backend status, read [references\u002Fpackage-overview.md](references\u002Fpackage-overview.md).\n5. For cross-cutting failures, start with [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n6. To run a quick non-training package check, use [scripts\u002Fcheck_torchreid_env.py](scripts\u002Fcheck_torchreid_env.py).\n\n## Route map\n\n### Training, evaluation, data, and configs\n\nUse [sub-skills\u002Ftraining-evaluation\u002FSKILL.md](sub-skills\u002Ftraining-evaluation\u002FSKILL.md) when the request names training, testing, data managers, datasets, config files, CLI-style command generation, split-log parsing, or dataset mean\u002Fstd.\n\nTypical triggers: `ImageDataManager`, `VideoDataManager`, `Engine.run`, `scripts\u002Fmain.py`-style workflow, `test.evaluate True`, `visrank`, Market1501\u002FDukeMTMC\u002FMSMT\u002FCUHK03\u002FMARS layouts, `RandomIdentitySampler`, `train.lr_scheduler`, checkpoint resume\u002Ffine-tune.\n\n### Feature extraction, models, metrics, and visualization\n\nUse [sub-skills\u002Ffeature-extraction\u002FSKILL.md](sub-skills\u002Ffeature-extraction\u002FSKILL.md) when the request names embeddings, `FeatureExtractor`, model keys, checkpoint loading, distance matrices, CMC\u002FmAP, re-ranking, model complexity, ranked-result visualizations, or activation maps.\n\nTypical triggers: compare query\u002Fgallery images, compute cosine\u002Feuclidean distances, load local weights without downloads, `evaluate_rank`, `re_ranking`, `compute_model_complexity`, `return_featuremaps=True`.\n\n### Model export and deployment artifacts\n\nUse [sub-skills\u002Fmodel-export\u002FSKILL.md](sub-skills\u002Fmodel-export\u002FSKILL.md) when the request asks to export a trained core Torchreid checkpoint to ONNX, OpenVINO, or TFLite-style outputs.\n\nTypical triggers: `--include onnx`, OpenVINO Model Optimizer, `openvino2tensorflow`, dynamic axes, opset choice, model-name inference, optional export dependency failures.\n\n## Root operating rules\n\n- Prefer local checkpoint paths and explicit model names. Avoid automatic pretrained downloads unless the user approves network access.\n- Treat datasets as user-provided unless a specific dataset class has an automated download path and the user approves network access.\n- Use bundled helper scripts for command planning and smoke checks; do not tell future agents to run source-repo scripts from an unavailable checkout.\n- Keep CPU verification separate from CUDA claims. CPU import\u002Fmodel\u002Ffeature checks do not prove multi-GPU training throughput.\n- Use export extras only for requested export formats; the core skill does not install ONNX\u002FOpenVINO\u002FTensorFlow by default.\n- If a task requires the excluded `projects\u002F` workflows, either report the long-tail gap or extend the repo skill by bundling those project sources and verification cases first.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdeep-person-reid",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 deep-person-reid",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deep-person-reid",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deep-person-reid","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-person-reid\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fpackage-overview.md","REFERENCE","参考文档",3969,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-person-reid\u002Freferences\u002Fpackage-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2315,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-person-reid\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",344,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-person-reid\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",4071,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-person-reid\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_torchreid_env.py","SCRIPT","脚本",5254,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-person-reid\u002Fscripts\u002Fcheck_torchreid_env.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]