[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7PM10JPRT4SC23VWKF4B9":3,"skill-same:01M7F7PM10JPRT4SC23VWKF4B9":66},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7F7PM10JPRT4SC23VWKF4B9","segmentation",null,"Guides Attention-Gated Networks medical image segmentation workflows, including 3D U-Net training, validation, NIfTI layouts, and attention or feature-map export.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fattention-gated-networks\u002Fsub-skills\u002Fsegmentation\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: segmentation\ndescription: \"Guides Attention-Gated Networks medical image segmentation\n  workflows, including 3D U-Net training, validation, NIfTI layouts, and\n  attention or feature-map export.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Segmentation\n\nUse this sub-skill for medical image segmentation tasks in Attention-Gated\nNetworks. It covers 2D\u002F3D U-Net variants, CT deep-supervision networks,\nattention-gated U-Nets, non-local blocks, NIfTI datasets, segmentation\ntraining\u002Fvalidation scripts, and feature or attention map exports.\n\n## Read first\n\n- Read [api-reference.md](references\u002Fapi-reference.md) when you need exact\n  model names, wrapper methods, dataset class signatures, metric functions, or\n  hookable layer names.\n- Read [data-layout.md](references\u002Fdata-layout.md) before arranging NIfTI data\n  or debugging split, image\u002Flabel, and transform problems.\n- Read [workflows.md](references\u002Fworkflows.md) for training, validation,\n  checkpoint use, and safe attention\u002Ffeature map export.\n- Read [troubleshooting.md](references\u002Ftroubleshooting.md) for CUDA, memory,\n  SimpleITK, torchsample, NIfTI, shape, metric, or layer-hook failures.\n- Run [run_segmentation.py](scripts\u002Frun_segmentation.py) for skill-owned\n  training commands that replace the source repo's root training entry point.\n- Run [validate_and_export_maps.py](scripts\u002Fvalidate_and_export_maps.py) to\n  replace hard-coded validation and feature-map scripts with a parameterized,\n  skill-owned helper.\n- For fast environment validation, run the root helper\n  `..\u002F..\u002Fscripts\u002Fcheck_env.py --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks --mode segmentation`.\n\n## When to use this sub-skill\n\nUse this route when the user asks to:\n\n- train a segmentation network from the repository configs;\n- choose between baseline U-Net, non-local U-Net, CT deep supervision, and\n  multi-attention U-Net variants;\n- validate a segmentation checkpoint and compute dice, IoU, precision\u002Frecall,\n  mean distance, or Hausdorff-style distances;\n- arrange 3D NIfTI data for `acdc_sax`, `ukbb_sax`, `rvsc_sax`, or `test_sax`;\n- export NIfTI predictions, attention volumes, feature maps, or slice previews;\n- debug 3D shape, memory, CUDA, SimpleITK, torchsample, or layer-hook issues.\n\nRoute ultrasound scan-plane classification and 2D attention overlays to\n`..\u002Fclassification\u002FSKILL.md` instead.\n\n## Quick workflow\n\n1. Install the repository with CUDA-enabled PyTorch, torchsample, NIfTI, and\n   visualization dependencies. Then run:\n\n   ```bash\n   python ..\u002F..\u002Fscripts\u002Fcheck_env.py --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks --mode segmentation\n   ```\n\n2. Arrange NIfTI files under split directories with paired `image\u002F` and\n   `label\u002F` subfolders. See [data-layout.md](references\u002Fdata-layout.md).\n3. Copy a CT config and replace `data_path.acdc_sax` with the current dataset\n   root. The stock configs use `output_nc=4`, `tensor_dim='3D'`, and\n   `gpu_ids=[0]`.\n\nRelative config paths are resolved from the explicit `--repo-root`; relative\n`data_path` values are resolved from the config file's parent. NIfTI data and\nmodel weights\u002Fcheckpoints must exist externally. The bundled runner and\n`check_env.py --config ...` fail fast on missing or private `\u002Fvol\u002F...` paths;\nthey never fabricate data.\n4. Train with the bundled replacement:\n\n   ```bash\n   python scripts\u002Frun_segmentation.py --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks --config path\u002Fto\u002Fconfig.json\n   ```\n\n5. Validate a checkpoint or export maps with the bundled helper:\n\n   ```bash\n   python scripts\u002Fvalidate_and_export_maps.py --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks --config path\u002Fto\u002Fconfig.json --checkpoint path\u002Fto\u002Fcheckpoint.pth --output-dir \u002Ftmp\u002Fag-net-validation --mode validate\n   ```\n\n6. For safe smoke validation or map export without private paths, use:\n\n   ```bash\n   python scripts\u002Fvalidate_and_export_maps.py \\\n     --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks \\\n     --config configs\u002Fconfig_unet_ct_multi_att_dsv.json \\\n     --output-dir \u002Ftmp\u002Fag-net-segmentation \\\n     --mode both\n   ```\n\n## Key decisions\n\n- CUDA is required for the unmodified source wrappers. A CPU-only install does\n  not verify the selected segmentation workflows.\n- `unet_ct_dsv` is the simpler CT deep-supervision route; use\n  `unet_ct_multi_att_dsv` when attention maps are a first-class goal.\n- Real CT configs use large volumes (`160 x 160 x 96` patches). The generated\n  helper's `16 x 16 x 16` synthetic volume is only a wiring smoke.\n- The source validation and map-export scripts hard-code private paths. Prefer\n  the bundled helper or explicitly parameterize a project-local copy.\n- The source CRF post-processing script is reference-only, not bundled as a\n  safe helper.\n\n## Expected outputs\n\nTraining writes checkpoints and logs below the configured checkpoint directory\nand experiment name. Validation writes NIfTI predictions and CSV metrics. The\nbundled helper writes synthetic or fixture NIfTI outputs, `metrics.json`,\nfeature\u002Fattention-map NIfTI files, and middle-slice preview PNGs to the selected\noutput directory.\n","# Segmentation\n\nUse this sub-skill for medical image segmentation tasks in Attention-Gated\nNetworks. It covers 2D\u002F3D U-Net variants, CT deep-supervision networks,\nattention-gated U-Nets, non-local blocks, NIfTI datasets, segmentation\ntraining\u002Fvalidation scripts, and feature or attention map exports.\n\n## Read first\n\n- Read [api-reference.md](references\u002Fapi-reference.md) when you need exact\n  model names, wrapper methods, dataset class signatures, metric functions, or\n  hookable layer names.\n- Read [data-layout.md](references\u002Fdata-layout.md) before arranging NIfTI data\n  or debugging split, image\u002Flabel, and transform problems.\n- Read [workflows.md](references\u002Fworkflows.md) for training, validation,\n  checkpoint use, and safe attention\u002Ffeature map export.\n- Read [troubleshooting.md](references\u002Ftroubleshooting.md) for CUDA, memory,\n  SimpleITK, torchsample, NIfTI, shape, metric, or layer-hook failures.\n- Run [run_segmentation.py](scripts\u002Frun_segmentation.py) for skill-owned\n  training commands that replace the source repo's root training entry point.\n- Run [validate_and_export_maps.py](scripts\u002Fvalidate_and_export_maps.py) to\n  replace hard-coded validation and feature-map scripts with a parameterized,\n  skill-owned helper.\n- For fast environment validation, run the root helper\n  `..\u002F..\u002Fscripts\u002Fcheck_env.py --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks --mode segmentation`.\n\n## When to use this sub-skill\n\nUse this route when the user asks to:\n\n- train a segmentation network from the repository configs;\n- choose between baseline U-Net, non-local U-Net, CT deep supervision, and\n  multi-attention U-Net variants;\n- validate a segmentation checkpoint and compute dice, IoU, precision\u002Frecall,\n  mean distance, or Hausdorff-style distances;\n- arrange 3D NIfTI data for `acdc_sax`, `ukbb_sax`, `rvsc_sax`, or `test_sax`;\n- export NIfTI predictions, attention volumes, feature maps, or slice previews;\n- debug 3D shape, memory, CUDA, SimpleITK, torchsample, or layer-hook issues.\n\nRoute ultrasound scan-plane classification and 2D attention overlays to\n`..\u002Fclassification\u002FSKILL.md` instead.\n\n## Quick workflow\n\n1. Install the repository with CUDA-enabled PyTorch, torchsample, NIfTI, and\n   visualization dependencies. Then run:\n\n   ```bash\n   python ..\u002F..\u002Fscripts\u002Fcheck_env.py --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks --mode segmentation\n   ```\n\n2. Arrange NIfTI files under split directories with paired `image\u002F` and\n   `label\u002F` subfolders. See [data-layout.md](references\u002Fdata-layout.md).\n3. Copy a CT config and replace `data_path.acdc_sax` with the current dataset\n   root. The stock configs use `output_nc=4`, `tensor_dim='3D'`, and\n   `gpu_ids=[0]`.\n\nRelative config paths are resolved from the explicit `--repo-root`; relative\n`data_path` values are resolved from the config file's parent. NIfTI data and\nmodel weights\u002Fcheckpoints must exist externally. The bundled runner and\n`check_env.py --config ...` fail fast on missing or private `\u002Fvol\u002F...` paths;\nthey never fabricate data.\n4. Train with the bundled replacement:\n\n   ```bash\n   python scripts\u002Frun_segmentation.py --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks --config path\u002Fto\u002Fconfig.json\n   ```\n\n5. Validate a checkpoint or export maps with the bundled helper:\n\n   ```bash\n   python scripts\u002Fvalidate_and_export_maps.py --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks --config path\u002Fto\u002Fconfig.json --checkpoint path\u002Fto\u002Fcheckpoint.pth --output-dir \u002Ftmp\u002Fag-net-validation --mode validate\n   ```\n\n6. For safe smoke validation or map export without private paths, use:\n\n   ```bash\n   python scripts\u002Fvalidate_and_export_maps.py \\\n     --repo-root \u002Fpath\u002Fto\u002FAttention-Gated-Networks \\\n     --config configs\u002Fconfig_unet_ct_multi_att_dsv.json \\\n     --output-dir \u002Ftmp\u002Fag-net-segmentation \\\n     --mode both\n   ```\n\n## Key decisions\n\n- CUDA is required for the unmodified source wrappers. A CPU-only install does\n  not verify the selected segmentation workflows.\n- `unet_ct_dsv` is the simpler CT deep-supervision route; use\n  `unet_ct_multi_att_dsv` when attention maps are a first-class goal.\n- Real CT configs use large volumes (`160 x 160 x 96` patches). The generated\n  helper's `16 x 16 x 16` synthetic volume is only a wiring smoke.\n- The source validation and map-export scripts hard-code private paths. Prefer\n  the bundled helper or explicitly parameterize a project-local copy.\n- The source CRF post-processing script is reference-only, not bundled as a\n  safe helper.\n\n## Expected outputs\n\nTraining writes checkpoints and logs below the configured checkpoint directory\nand experiment name. Validation writes NIfTI predictions and CSV metrics. The\nbundled helper writes synthetic or fixture NIfTI outputs, `metrics.json`,\nfeature\u002Fattention-map NIfTI files, and middle-slice preview PNGs to the selected\noutput directory.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fattention-gated-networks\u002Fsub-skills\u002Fsegmentation",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":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill segmentation",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill segmentation",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill segmentation","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\u002Fattention-gated-networks\u002Fsub-skills\u002Fsegmentation\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fapi-reference.md","REFERENCE","参考文档",6200,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fattention-gated-networks\u002Fsub-skills\u002Fsegmentation\u002Freferences\u002Fapi-reference.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdata-layout.md",3237,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fattention-gated-networks\u002Fsub-skills\u002Fsegmentation\u002Freferences\u002Fdata-layout.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",4713,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fattention-gated-networks\u002Fsub-skills\u002Fsegmentation\u002Freferences\u002Ftroubleshooting.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fworkflows.md",4159,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fattention-gated-networks\u002Fsub-skills\u002Fsegmentation\u002Freferences\u002Fworkflows.md",[67,74,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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",[],[]]