[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FB63D2MDZFD5Z2KBW8X5BZ":3,"skill-same:01M7FB63D2MDZFD5Z2KBW8X5BZ":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7FB63D2MDZFD5Z2KBW8X5BZ","training-evaluation-inference",null,"Builds and troubleshoots PaddleDetection training, evaluation, repository inference, distributed launch, AMP, logging, and slim command workflows.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fpaddle-detection\u002Fsub-skills\u002Ftraining-evaluation-inference\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: training-evaluation-inference\ndescription: \"Builds and troubleshoots PaddleDetection training, evaluation,\n  repository inference, distributed launch, AMP, logging, and slim command\n  workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Training, Evaluation, and Repository Inference\n\nUse this route when the task asks to train, fine-tune, resume, evaluate, run `infer` on images\u002Fdirectories, perform slice inference, use VisualDL\u002FW&B, launch multi-GPU jobs, enable AMP\u002Ffleet, or connect config\u002Fdata\u002Fweights to PaddleDetection repository tools.\n\n## Safe command planning\n\n1. Choose and summarize a config with the model-zoo\u002Fconfig route.\n2. Validate the dataset route before training or evaluation.\n3. Decide device and budget. CPU is fine for parser\u002Fconfig checks; serious training and many tutorials expect GPU.\n4. Construct commands with [`scripts\u002Fbuild_train_eval_infer_command.py`](scripts\u002Fbuild_train_eval_infer_command.py). It only prints commands for a user-provided checkout; it does not train.\n5. Start with `use_gpu=false` or `--device=CPU` for smoke checks, local weights, a tiny image, and `--save_results` only when needed.\n6. Promote to GPU\u002Fdistributed\u002FAMP only after the CPU\u002Fimport\u002Fconfig\u002Fdata preflight passes.\n\n## Common command shapes\n\n```bash\npython tools\u002Ftrain.py -c \u003Cconfig.yml> --eval -o use_gpu=true\npython tools\u002Feval.py -c \u003Cconfig.yml> -o weights=\u003Cmodel.pdparams> use_gpu=true\npython tools\u002Finfer.py -c \u003Cconfig.yml> --infer_img=\u003Cimage.jpg> --output_dir=\u003Cout> -o weights=\u003Cmodel.pdparams> use_gpu=false\npython -m paddle.distributed.launch --gpus 0,1,2,3 tools\u002Ftrain.py -c \u003Cconfig.yml> --eval\n```\n\nTreat the source-checkout `tools\u002F*.py` scripts as target repository entry points, not files from this generated skill. Use the bundled command builder and references for the decisions.\n\n## References\n\n- [`references\u002Ftraining-workflows.md`](references\u002Ftraining-workflows.md): fine-tuning, resume, distributed launch, logging, AMP\u002Fslim, and output expectations.\n- [`references\u002Fcli-reference.md`](references\u002Fcli-reference.md): verified training\u002Feval\u002Finfer flags and override behavior.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): errors for devices, data, weights, configs, metrics, and optional dependencies.\n","# Training, Evaluation, and Repository Inference\n\nUse this route when the task asks to train, fine-tune, resume, evaluate, run `infer` on images\u002Fdirectories, perform slice inference, use VisualDL\u002FW&B, launch multi-GPU jobs, enable AMP\u002Ffleet, or connect config\u002Fdata\u002Fweights to PaddleDetection repository tools.\n\n## Safe command planning\n\n1. Choose and summarize a config with the model-zoo\u002Fconfig route.\n2. Validate the dataset route before training or evaluation.\n3. Decide device and budget. CPU is fine for parser\u002Fconfig checks; serious training and many tutorials expect GPU.\n4. Construct commands with [`scripts\u002Fbuild_train_eval_infer_command.py`](scripts\u002Fbuild_train_eval_infer_command.py). It only prints commands for a user-provided checkout; it does not train.\n5. Start with `use_gpu=false` or `--device=CPU` for smoke checks, local weights, a tiny image, and `--save_results` only when needed.\n6. Promote to GPU\u002Fdistributed\u002FAMP only after the CPU\u002Fimport\u002Fconfig\u002Fdata preflight passes.\n\n## Common command shapes\n\n```bash\npython tools\u002Ftrain.py -c \u003Cconfig.yml> --eval -o use_gpu=true\npython tools\u002Feval.py -c \u003Cconfig.yml> -o weights=\u003Cmodel.pdparams> use_gpu=true\npython tools\u002Finfer.py -c \u003Cconfig.yml> --infer_img=\u003Cimage.jpg> --output_dir=\u003Cout> -o weights=\u003Cmodel.pdparams> use_gpu=false\npython -m paddle.distributed.launch --gpus 0,1,2,3 tools\u002Ftrain.py -c \u003Cconfig.yml> --eval\n```\n\nTreat the source-checkout `tools\u002F*.py` scripts as target repository entry points, not files from this generated skill. Use the bundled command builder and references for the decisions.\n\n## References\n\n- [`references\u002Ftraining-workflows.md`](references\u002Ftraining-workflows.md): fine-tuning, resume, distributed launch, logging, AMP\u002Fslim, and output expectations.\n- [`references\u002Fcli-reference.md`](references\u002Fcli-reference.md): verified training\u002Feval\u002Finfer flags and override behavior.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): errors for devices, data, weights, configs, metrics, and optional dependencies.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fpaddle-detection\u002Fsub-skills\u002Ftraining-evaluation-inference",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill training-evaluation-inference",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill training-evaluation-inference",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill training-evaluation-inference","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fpaddle-detection\u002Fsub-skills\u002Ftraining-evaluation-inference\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fcli-reference.md","REFERENCE","参考文档",1684,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fpaddle-detection\u002Fsub-skills\u002Ftraining-evaluation-inference\u002Freferences\u002Fcli-reference.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Ftraining-workflows.md",2113,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fpaddle-detection\u002Fsub-skills\u002Ftraining-evaluation-inference\u002Freferences\u002Ftraining-workflows.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftroubleshooting.md",1578,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fpaddle-detection\u002Fsub-skills\u002Ftraining-evaluation-inference\u002Freferences\u002Ftroubleshooting.md",[64,72,77,84,91,98],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":73,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]