[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FX7VSWQSEYAYSRQRCV4ZC":3,"skill-same:01M79FX7VSWQSEYAYSRQRCV4ZC":144},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M79FX7VSWQSEYAYSRQRCV4ZC","tao-train-oneformer",null,"OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running inference for a TAO OneFormer model. Trigger phrases include \"train OneFormer\", \"universal segmentation\", \"task-conditioned segmentation\", \"panoptic \u002F instance \u002F semantic in one model\".","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tao-train-oneformer\ndescription: OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a\n  single architecture using task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running\n  inference for a TAO OneFormer model. Trigger phrases include \"train OneFormer\", \"universal segmentation\",\n  \"task-conditioned segmentation\", \"panoptic \u002F instance \u002F semantic in one model\".\nlicense: Apache-2.0\ncompatibility: Requires docker + nvidia-container-toolkit.\nmetadata:\n  version: \"0.1.0\"\n  author: NVIDIA Corporation\nallowed-tools: Read Bash\ntags:\n- segmentation\n---\n\n# OneFormer\n\nOneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries.\n\nSet train.pretrained_backbone and\u002For train.pretrained_model.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), read `references\u002Ftao-deploy-oneformer.md` first. Deploy spec templates live in this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml` prefix.\n\n## Dataclass Schemas\n\nGenerated TAO Core schemas are packaged in `schemas\u002F\u003Caction>.schema.json`, with `schemas\u002Fmanifest.json` listing available actions. Each generated schema also emits `references\u002Fspec_template_\u003Caction>.yaml` from the schema top-level `default` field. AutoML enablement is declared at the model layer in `references\u002Fskill_info.yaml` via `automl_enabled`. Runnable AutoML still requires `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` to exist and parse. Use the packaged train schema for `automl_default_parameters`, `automl_disabled_parameters`, defaults, min\u002Fmax bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect `~\u002Ftao-core` at runtime; maintainers regenerate schemas\u002Ftemplates before packaging the skill bank.\n\n## Train Action Policy\n\nThis model is AutoML-enabled at the model layer. Before handling any train-stage request, read `references\u002Fskill_info.yaml` and resolve the run override from either an explicit `automl_policy` value or the user's workflow request. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only; otherwise default to `auto`. When `automl_policy: auto`, `automl_enabled: true`, and both `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` are packaged, route the train action through `tao-skill-bank:tao-run-automl` by default with this model's `skill_dir`. Preserve workflow\u002Fapplication overrides for datasets, specs, output directories, GPU\u002Fplatform settings, parent checkpoints, and `automl_policy`. Use direct model training only when `automl_policy: off` or the packaged train schema\u002Ftemplate is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.\n\nNon-train actions such as `evaluate`, `inference`, `export`, and deploy flows stay in this model skill. The per-run `automl_policy` override does not change model metadata.\n\n## Training Requirements\n\n- **Dataset type:** segmentation\n- **Formats:** coco_panoptic, coco\n- **Monitoring metric:** mIoU\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | dataset.train.images | train_datasets | images.tar.gz | No |\n| evaluate | dataset.label_map | train_datasets | label_map.json | No |\n| evaluate | dataset.train.annotations | train_datasets | annotations.json | No |\n| evaluate | dataset.train.panoptic | train_datasets | images_panoptic.tar.gz | No |\n| evaluate | dataset.val.images | eval_dataset | images.tar.gz | No |\n| evaluate | dataset.val.annotations | eval_dataset | annotations.json | No |\n| evaluate | dataset.val.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| evaluate | dataset.test.images | eval_dataset | images.tar.gz | No |\n| evaluate | dataset.test.annotations | eval_dataset | annotations.json | No |\n| evaluate | dataset.test.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| inference | dataset.train.images | train_datasets | images.tar.gz | No |\n| inference | dataset.label_map | train_datasets | coco_panoptic: label_map_panoptic.json; *: label_map.json | No |\n| inference | dataset.train.annotations | train_datasets | annotations.json | No |\n| inference | dataset.train.panoptic | train_datasets | images_panoptic.tar.gz | No |\n| inference | dataset.val.images | eval_dataset | images.tar.gz | No |\n| inference | dataset.val.annotations | eval_dataset | annotations.json | No |\n| inference | dataset.val.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| inference | dataset.test.images | eval_dataset | images.tar.gz | No |\n| quantize | dataset.train.images | train_datasets | images.tar.gz | No |\n| quantize | dataset.train.annotations | train_datasets | annotations.json | No |\n| quantize | dataset.label_map | train_datasets | label_map.json | No |\n| quantize | dataset.train.panoptic | train_datasets | images_panoptic.tar.gz | No |\n| quantize | dataset.val.images | eval_dataset | images.tar.gz | No |\n| quantize | dataset.val.annotations | eval_dataset | annotations.json | No |\n| quantize | dataset.val.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| quantize | dataset.test.images | eval_dataset | images.tar.gz | No |\n| quantize | dataset.quant_calibration_dataset.images_dir | train_datasets | images.tar.gz | No |\n| train | dataset.train.images | train_datasets | images.tar.gz | No |\n| train | dataset.train.annotations | train_datasets | annotations.json | No |\n| train | dataset.label_map | train_datasets | label_map.json | No |\n| train | dataset.train.panoptic | train_datasets | images_panoptic.tar.gz | No |\n| train | dataset.val.images | eval_dataset | images.tar.gz | No |\n| train | dataset.val.annotations | eval_dataset | annotations.json | No |\n| train | dataset.val.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| train | dataset.test.images | eval_dataset | images.tar.gz | No |\n\n### Typical Spec Overrides\n\nData source overrides are **mandatory for every action** — the agent MUST construct data source paths from the Per-Action Dataset Requirements table above and include them in `spec_overrides`.\n\n```python\nS3_TRAIN = \"s3:\u002F\u002Fbucket\u002Fdata\u002Ftrain\"\nS3_EVAL = \"s3:\u002F\u002Fbucket\u002Fdata\u002Feval\"\n```\n\n**train (mandatory data sources):**\n```python\n{\n    \"train.num_gpus\": 1,\n    \"train.num_epochs\": 10,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"model.sem_seg_head.num_classes\": 133,\n    \"dataset.contiguous_id\": True,\n    \"train.precision\": \"32\",\n    \"dataset.train.images\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n    \"dataset.train.annotations\": f\"{S3_TRAIN}\u002Fannotations.json\",\n    \"dataset.label_map\": f\"{S3_TRAIN}\u002Flabel_map.json\",\n    \"dataset.train.panoptic\": f\"{S3_TRAIN}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.val.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.val.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.val.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.test.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"model.sem_seg_head.num_classes\": 133,\n    \"dataset.contiguous_id\": True,\n    \"dataset.train.images\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n    \"dataset.label_map\": f\"{S3_TRAIN}\u002Flabel_map.json\",\n    \"dataset.train.annotations\": f\"{S3_TRAIN}\u002Fannotations.json\",\n    \"dataset.train.panoptic\": f\"{S3_TRAIN}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.val.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.val.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.val.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.test.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.test.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.test.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n}\n```\n\n**export:**\n```python\n{\n    \"model.sem_seg_head.num_classes\": 133,\n    \"model.export\": True,\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.train.images\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n    \"dataset.label_map\": {\"coco_panoptic\": f\"{S3_TRAIN}\u002Flabel_map_panoptic.json; *: label_map.json\"},\n    \"dataset.train.annotations\": f\"{S3_TRAIN}\u002Fannotations.json\",\n    \"dataset.train.panoptic\": f\"{S3_TRAIN}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.val.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.val.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.val.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.test.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n}\n```\n\n**quantize (mandatory data sources):**\n```python\n{\n    \"dataset.train.images\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n    \"dataset.train.annotations\": f\"{S3_TRAIN}\u002Fannotations.json\",\n    \"dataset.label_map\": f\"{S3_TRAIN}\u002Flabel_map.json\",\n    \"dataset.train.panoptic\": f\"{S3_TRAIN}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.val.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.val.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.val.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.test.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.quant_calibration_dataset.images_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n}\n```\n## Eval Dataset\n\nOptional. Val data configured alongside train in the dataset config.\n\n## Important Parameters\n\n- **model.sem_seg_head.num_classes**: Number of segmentation classes. Default 133 (COCO panoptic).\n- **model.backbone.name**: Default D2SwinTransformer (Swin-based). embed_dim=192, depths=[2,2,18,2] by default.\n- **train.num_epochs**: Default 50 — significantly higher than most TAO models. OneFormer needs more epochs for convergence.\n- **train.optim.lr**: Learning rate. Default 1e-5. Lower than Mask2Former's 2e-4.\n- **model.task_toggling**: Enable\u002Fdisable specific tasks: semantic_on, instance_on, panoptic_on.\n- **export.task**: Export task mode. Options: semantic, instance, panoptic. Default semantic. Export input defaults to 640x640.\n- **inference.mode**: Inference mode. Options: semantic, instance, panoptic. Default semantic. image_size defaults to [1024, 1024].\n- **evaluate.iou_per_class**: Report per-class IoU in evaluation. Default True.\n\n## Multi-GPU \u002F Multi-Node\n\n**Launch method:** Lightning-managed (single `python` process, Lightning spawns workers).\n\n| Spec Key | Description | Default |\n|----------|-------------|---------|\n| `train.num_gpus` | Number of GPUs | 1 |\n| `train.gpu_ids` | GPU device indices | [0] |\n| `train.num_nodes` | Number of nodes | 1 |\n\n- Uses explicit `DDPStrategy` with `find_unused_parameters=True`, `gradient_as_bucket_view=True`, `process_group_backend=\"nccl\"`\n- `sync_batchnorm` is always enabled\n- No fsdp support — DDP only\n\n**Multi-node env vars** (set by orchestrator): `WORLD_SIZE`, `NODE_RANK`, `MASTER_ADDR`, `MASTER_PORT`, `NUM_GPU_PER_NODE`.\n\n## Hardware\n\nMinimum 2 GPU(s), recommended 4 GPU(s). 24GB+ (A100 recommended) VRAM per GPU. OneFormer is memory-intensive like Mask2Former. batch_size=1 is the default. Multi-GPU needed for reasonable training speed, especially with 50 epochs.\n\n## Error Patterns\n\n**CUDA out of memory**: batch_size is already 1. Reduce image resolution or use a smaller Swin configuration.\n\n**Slow training**: 50 default epochs with batch_size=1 is slow on single GPU. Use multi-GPU distributed training.\n\n## Spec Param \u002F Parent Model Inference\n\nModel-specific inference mappings belong in this MD file, not in `config.json`. Generated runners should read this section and apply the mappings with SDK helpers before `create_job()`. This mirrors the old microservices `infer_params.py` flow.\n\nInference mappings from TAO Core `oneformer.config.json`:\n\n| Action | Spec Field | Inference Function | Meaning |\n|---|---|---|---|\n| evaluate | `encryption_key` | `key` | encryption key |\n| evaluate | `evaluate.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `evaluate.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `results_dir` | `output_dir` | current job results directory |\n| export | `encryption_key` | `key` | encryption key |\n| export | `export.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| export | `export.onnx_file` | `create_onnx_file` | output ONNX path |\n| export | `results_dir` | `output_dir` | current job results directory |\n| gen_trt_engine | `encryption_key` | `key` | encryption key |\n| gen_trt_engine | `gen_trt_engine.onnx_file` | `parent_model` | model file inferred from the parent job results folder |\n| gen_trt_engine | `gen_trt_engine.trt_engine` | `create_engine_file` | output TensorRT engine path |\n| gen_trt_engine | `results_dir` | `output_dir` | current job results directory |\n| inference | `encryption_key` | `key` | encryption key |\n| inference | `inference.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `inference.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `results_dir` | `output_dir` | current job results directory |\n| quantize | `encryption_key` | `key` | encryption key |\n| quantize | `quantize.model_path` | `parent_model` | model file inferred from the parent job results folder |\n| quantize | `results_dir` | `output_dir` | current job results directory |\n| train | `encryption_key` | `key` | encryption key |\n| train | `results_dir` | `output_dir` | current job results directory |\n| train | `train.pretrained_backbone` | `{'link': 'https:\u002F\u002Fgithub.com\u002FSwinTransformer\u002Fstorage\u002Freleases\u002Fdownload\u002Fv1.0.8\u002Fswin_tiny_patch4_window7_224_22k.pth', 'destination_path': '\u002Fptm\u002Fmask2former\u002Fswin_tiny_patch4_window7_224_22k\u002Fswin_tiny_patch4_window7_224_22k.pth'}` | {'link': 'https:\u002F\u002Fgithub.com\u002FSwinTransformer\u002Fstorage\u002Freleases\u002Fdownload\u002Fv1.0.8\u002Fswin_tiny_patch4_window7_224_22k.pth', 'destination_path': '\u002Fptm\u002Fmask2former\u002Fswin_tiny_patch4_window7_224_22k\u002Fswin_tiny_patch4_window7_224_22k.pth'} |\n| train | `train.pretrained_model` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `train.resume_training_checkpoint_path` | `resume_model` | model file inferred from the current job results folder |\n\nFor `parent_model` or `parent_model_folder`, pass the upstream train\u002Fexport\u002FAutoML child job id as `parent_job_id`. The SDK lists the parent result folder, filters checkpoint artifacts, and returns the selected model file or folder. Do not add these mappings back to `config.json` and do not patch generated runner scripts to guess checkpoint paths.\n\n## Deployment\n\n- [tao-deploy-oneformer](references\u002Ftao-deploy-oneformer.md) — OneFormer deploy workflow for TensorRT engine generation, TensorRT evaluation, and TensorRT inference using TAO Deploy.\n","# OneFormer\n\nOneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries.\n\nSet train.pretrained_backbone and\u002For train.pretrained_model.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), read `references\u002Ftao-deploy-oneformer.md` first. Deploy spec templates live in this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml` prefix.\n\n## Dataclass Schemas\n\nGenerated TAO Core schemas are packaged in `schemas\u002F\u003Caction>.schema.json`, with `schemas\u002Fmanifest.json` listing available actions. Each generated schema also emits `references\u002Fspec_template_\u003Caction>.yaml` from the schema top-level `default` field. AutoML enablement is declared at the model layer in `references\u002Fskill_info.yaml` via `automl_enabled`. Runnable AutoML still requires `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` to exist and parse. Use the packaged train schema for `automl_default_parameters`, `automl_disabled_parameters`, defaults, min\u002Fmax bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect `~\u002Ftao-core` at runtime; maintainers regenerate schemas\u002Ftemplates before packaging the skill bank.\n\n## Train Action Policy\n\nThis model is AutoML-enabled at the model layer. Before handling any train-stage request, read `references\u002Fskill_info.yaml` and resolve the run override from either an explicit `automl_policy` value or the user's workflow request. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only; otherwise default to `auto`. When `automl_policy: auto`, `automl_enabled: true`, and both `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` are packaged, route the train action through `tao-skill-bank:tao-run-automl` by default with this model's `skill_dir`. Preserve workflow\u002Fapplication overrides for datasets, specs, output directories, GPU\u002Fplatform settings, parent checkpoints, and `automl_policy`. Use direct model training only when `automl_policy: off` or the packaged train schema\u002Ftemplate is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.\n\nNon-train actions such as `evaluate`, `inference`, `export`, and deploy flows stay in this model skill. The per-run `automl_policy` override does not change model metadata.\n\n## Training Requirements\n\n- **Dataset type:** segmentation\n- **Formats:** coco_panoptic, coco\n- **Monitoring metric:** mIoU\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | dataset.train.images | train_datasets | images.tar.gz | No |\n| evaluate | dataset.label_map | train_datasets | label_map.json | No |\n| evaluate | dataset.train.annotations | train_datasets | annotations.json | No |\n| evaluate | dataset.train.panoptic | train_datasets | images_panoptic.tar.gz | No |\n| evaluate | dataset.val.images | eval_dataset | images.tar.gz | No |\n| evaluate | dataset.val.annotations | eval_dataset | annotations.json | No |\n| evaluate | dataset.val.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| evaluate | dataset.test.images | eval_dataset | images.tar.gz | No |\n| evaluate | dataset.test.annotations | eval_dataset | annotations.json | No |\n| evaluate | dataset.test.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| inference | dataset.train.images | train_datasets | images.tar.gz | No |\n| inference | dataset.label_map | train_datasets | coco_panoptic: label_map_panoptic.json; *: label_map.json | No |\n| inference | dataset.train.annotations | train_datasets | annotations.json | No |\n| inference | dataset.train.panoptic | train_datasets | images_panoptic.tar.gz | No |\n| inference | dataset.val.images | eval_dataset | images.tar.gz | No |\n| inference | dataset.val.annotations | eval_dataset | annotations.json | No |\n| inference | dataset.val.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| inference | dataset.test.images | eval_dataset | images.tar.gz | No |\n| quantize | dataset.train.images | train_datasets | images.tar.gz | No |\n| quantize | dataset.train.annotations | train_datasets | annotations.json | No |\n| quantize | dataset.label_map | train_datasets | label_map.json | No |\n| quantize | dataset.train.panoptic | train_datasets | images_panoptic.tar.gz | No |\n| quantize | dataset.val.images | eval_dataset | images.tar.gz | No |\n| quantize | dataset.val.annotations | eval_dataset | annotations.json | No |\n| quantize | dataset.val.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| quantize | dataset.test.images | eval_dataset | images.tar.gz | No |\n| quantize | dataset.quant_calibration_dataset.images_dir | train_datasets | images.tar.gz | No |\n| train | dataset.train.images | train_datasets | images.tar.gz | No |\n| train | dataset.train.annotations | train_datasets | annotations.json | No |\n| train | dataset.label_map | train_datasets | label_map.json | No |\n| train | dataset.train.panoptic | train_datasets | images_panoptic.tar.gz | No |\n| train | dataset.val.images | eval_dataset | images.tar.gz | No |\n| train | dataset.val.annotations | eval_dataset | annotations.json | No |\n| train | dataset.val.panoptic | eval_dataset | images_panoptic.tar.gz | No |\n| train | dataset.test.images | eval_dataset | images.tar.gz | No |\n\n### Typical Spec Overrides\n\nData source overrides are **mandatory for every action** — the agent MUST construct data source paths from the Per-Action Dataset Requirements table above and include them in `spec_overrides`.\n\n```python\nS3_TRAIN = \"s3:\u002F\u002Fbucket\u002Fdata\u002Ftrain\"\nS3_EVAL = \"s3:\u002F\u002Fbucket\u002Fdata\u002Feval\"\n```\n\n**train (mandatory data sources):**\n```python\n{\n    \"train.num_gpus\": 1,\n    \"train.num_epochs\": 10,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"model.sem_seg_head.num_classes\": 133,\n    \"dataset.contiguous_id\": True,\n    \"train.precision\": \"32\",\n    \"dataset.train.images\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n    \"dataset.train.annotations\": f\"{S3_TRAIN}\u002Fannotations.json\",\n    \"dataset.label_map\": f\"{S3_TRAIN}\u002Flabel_map.json\",\n    \"dataset.train.panoptic\": f\"{S3_TRAIN}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.val.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.val.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.val.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.test.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"model.sem_seg_head.num_classes\": 133,\n    \"dataset.contiguous_id\": True,\n    \"dataset.train.images\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n    \"dataset.label_map\": f\"{S3_TRAIN}\u002Flabel_map.json\",\n    \"dataset.train.annotations\": f\"{S3_TRAIN}\u002Fannotations.json\",\n    \"dataset.train.panoptic\": f\"{S3_TRAIN}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.val.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.val.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.val.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.test.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.test.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.test.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n}\n```\n\n**export:**\n```python\n{\n    \"model.sem_seg_head.num_classes\": 133,\n    \"model.export\": True,\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.train.images\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n    \"dataset.label_map\": {\"coco_panoptic\": f\"{S3_TRAIN}\u002Flabel_map_panoptic.json; *: label_map.json\"},\n    \"dataset.train.annotations\": f\"{S3_TRAIN}\u002Fannotations.json\",\n    \"dataset.train.panoptic\": f\"{S3_TRAIN}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.val.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.val.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.val.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.test.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n}\n```\n\n**quantize (mandatory data sources):**\n```python\n{\n    \"dataset.train.images\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n    \"dataset.train.annotations\": f\"{S3_TRAIN}\u002Fannotations.json\",\n    \"dataset.label_map\": f\"{S3_TRAIN}\u002Flabel_map.json\",\n    \"dataset.train.panoptic\": f\"{S3_TRAIN}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.val.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.val.annotations\": f\"{S3_EVAL}\u002Fannotations.json\",\n    \"dataset.val.panoptic\": f\"{S3_EVAL}\u002Fimages_panoptic.tar.gz\",\n    \"dataset.test.images\": f\"{S3_EVAL}\u002Fimages.tar.gz\",\n    \"dataset.quant_calibration_dataset.images_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\",\n}\n```\n## Eval Dataset\n\nOptional. Val data configured alongside train in the dataset config.\n\n## Important Parameters\n\n- **model.sem_seg_head.num_classes**: Number of segmentation classes. Default 133 (COCO panoptic).\n- **model.backbone.name**: Default D2SwinTransformer (Swin-based). embed_dim=192, depths=[2,2,18,2] by default.\n- **train.num_epochs**: Default 50 — significantly higher than most TAO models. OneFormer needs more epochs for convergence.\n- **train.optim.lr**: Learning rate. Default 1e-5. Lower than Mask2Former's 2e-4.\n- **model.task_toggling**: Enable\u002Fdisable specific tasks: semantic_on, instance_on, panoptic_on.\n- **export.task**: Export task mode. Options: semantic, instance, panoptic. Default semantic. Export input defaults to 640x640.\n- **inference.mode**: Inference mode. Options: semantic, instance, panoptic. Default semantic. image_size defaults to [1024, 1024].\n- **evaluate.iou_per_class**: Report per-class IoU in evaluation. Default True.\n\n## Multi-GPU \u002F Multi-Node\n\n**Launch method:** Lightning-managed (single `python` process, Lightning spawns workers).\n\n| Spec Key | Description | Default |\n|----------|-------------|---------|\n| `train.num_gpus` | Number of GPUs | 1 |\n| `train.gpu_ids` | GPU device indices | [0] |\n| `train.num_nodes` | Number of nodes | 1 |\n\n- Uses explicit `DDPStrategy` with `find_unused_parameters=True`, `gradient_as_bucket_view=True`, `process_group_backend=\"nccl\"`\n- `sync_batchnorm` is always enabled\n- No fsdp support — DDP only\n\n**Multi-node env vars** (set by orchestrator): `WORLD_SIZE`, `NODE_RANK`, `MASTER_ADDR`, `MASTER_PORT`, `NUM_GPU_PER_NODE`.\n\n## Hardware\n\nMinimum 2 GPU(s), recommended 4 GPU(s). 24GB+ (A100 recommended) VRAM per GPU. OneFormer is memory-intensive like Mask2Former. batch_size=1 is the default. Multi-GPU needed for reasonable training speed, especially with 50 epochs.\n\n## Error Patterns\n\n**CUDA out of memory**: batch_size is already 1. Reduce image resolution or use a smaller Swin configuration.\n\n**Slow training**: 50 default epochs with batch_size=1 is slow on single GPU. Use multi-GPU distributed training.\n\n## Spec Param \u002F Parent Model Inference\n\nModel-specific inference mappings belong in this MD file, not in `config.json`. Generated runners should read this section and apply the mappings with SDK helpers before `create_job()`. This mirrors the old microservices `infer_params.py` flow.\n\nInference mappings from TAO Core `oneformer.config.json`:\n\n| Action | Spec Field | Inference Function | Meaning |\n|---|---|---|---|\n| evaluate | `encryption_key` | `key` | encryption key |\n| evaluate | `evaluate.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `evaluate.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `results_dir` | `output_dir` | current job results directory |\n| export | `encryption_key` | `key` | encryption key |\n| export | `export.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| export | `export.onnx_file` | `create_onnx_file` | output ONNX path |\n| export | `results_dir` | `output_dir` | current job results directory |\n| gen_trt_engine | `encryption_key` | `key` | encryption key |\n| gen_trt_engine | `gen_trt_engine.onnx_file` | `parent_model` | model file inferred from the parent job results folder |\n| gen_trt_engine | `gen_trt_engine.trt_engine` | `create_engine_file` | output TensorRT engine path |\n| gen_trt_engine | `results_dir` | `output_dir` | current job results directory |\n| inference | `encryption_key` | `key` | encryption key |\n| inference | `inference.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `inference.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `results_dir` | `output_dir` | current job results directory |\n| quantize | `encryption_key` | `key` | encryption key |\n| quantize | `quantize.model_path` | `parent_model` | model file inferred from the parent job results folder |\n| quantize | `results_dir` | `output_dir` | current job results directory |\n| train | `encryption_key` | `key` | encryption key |\n| train | `results_dir` | `output_dir` | current job results directory |\n| train | `train.pretrained_backbone` | `{'link': 'https:\u002F\u002Fgithub.com\u002FSwinTransformer\u002Fstorage\u002Freleases\u002Fdownload\u002Fv1.0.8\u002Fswin_tiny_patch4_window7_224_22k.pth', 'destination_path': '\u002Fptm\u002Fmask2former\u002Fswin_tiny_patch4_window7_224_22k\u002Fswin_tiny_patch4_window7_224_22k.pth'}` | {'link': 'https:\u002F\u002Fgithub.com\u002FSwinTransformer\u002Fstorage\u002Freleases\u002Fdownload\u002Fv1.0.8\u002Fswin_tiny_patch4_window7_224_22k.pth', 'destination_path': '\u002Fptm\u002Fmask2former\u002Fswin_tiny_patch4_window7_224_22k\u002Fswin_tiny_patch4_window7_224_22k.pth'} |\n| train | `train.pretrained_model` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `train.resume_training_checkpoint_path` | `resume_model` | model file inferred from the current job results folder |\n\nFor `parent_model` or `parent_model_folder`, pass the upstream train\u002Fexport\u002FAutoML child job id as `parent_job_id`. The SDK lists the parent result folder, filters checkpoint artifacts, and returns the selected model file or folder. Do not add these mappings back to `config.json` and do not patch generated runner scripts to guess checkpoint paths.\n\n## Deployment\n\n- [tao-deploy-oneformer](references\u002Ftao-deploy-oneformer.md) — OneFormer deploy workflow for TensorRT engine generation, TensorRT evaluation, and TensorRT inference using TAO Deploy.\n",{"name":5,"tags":24,"license":15,"metadata":26,"description":7,"allowed-tools":29,"compatibility":30},[25],"segmentation",{"author":27,"version":28},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit.","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","skills\u002Fnvidia\u002Ftao-train-oneformer","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill tao-train-oneformer",{"tool":43,"command":44},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill tao-train-oneformer",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill tao-train-oneformer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002FSKILL.md",true,[51,57,61,65,69,73,76,80,84,88,92,96,99,103,107,111,115,119,122,126,130,134,138],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"BENCHMARK.md","REFERENCE","参考文档",4257,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002FBENCHMARK.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Fevals.json",755,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fevals\u002Fevals.json",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fskill_info.yaml",2027,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fskill_info.yaml",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fspec_template_deploy_evaluate.yaml",521,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_deploy_evaluate.yaml",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fspec_template_deploy_gen_trt_engine.yaml",277,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_deploy_gen_trt_engine.yaml",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":75},"references\u002Fspec_template_deploy_inference.yaml","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_deploy_inference.yaml",{"path":77,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fspec_template_evaluate.yaml",4751,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_evaluate.yaml",{"path":81,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fspec_template_export.yaml",4820,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_export.yaml",{"path":85,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fspec_template_gen_trt_engine.yaml",4883,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_gen_trt_engine.yaml",{"path":89,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fspec_template_inference.yaml",4796,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_inference.yaml",{"path":93,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fspec_template_quantize.yaml",4604,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_quantize.yaml",{"path":97,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":94,"sourceHtmlUrl":98},"references\u002Fspec_template_train.yaml","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Fspec_template_train.yaml",{"path":100,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Ftao-deploy-oneformer.md",4950,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Ftao-deploy-oneformer.md",{"path":104,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Ftao-deploy-oneformer.skill_info.yaml",2121,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Freferences\u002Ftao-deploy-oneformer.skill_info.yaml",{"path":108,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":109,"sourceHtmlUrl":110},"schemas\u002Fevaluate.schema.json",74630,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fschemas\u002Fevaluate.schema.json",{"path":112,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":113,"sourceHtmlUrl":114},"schemas\u002Fexport.schema.json",75291,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fschemas\u002Fexport.schema.json",{"path":116,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":117,"sourceHtmlUrl":118},"schemas\u002Fgen_trt_engine.schema.json",77185,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fschemas\u002Fgen_trt_engine.schema.json",{"path":120,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":113,"sourceHtmlUrl":121},"schemas\u002Finference.schema.json","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fschemas\u002Finference.schema.json",{"path":123,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":124,"sourceHtmlUrl":125},"schemas\u002Fmanifest.json",18662,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fschemas\u002Fmanifest.json",{"path":127,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":128,"sourceHtmlUrl":129},"schemas\u002Fquantize.schema.json",71837,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fschemas\u002Fquantize.schema.json",{"path":131,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":132,"sourceHtmlUrl":133},"schemas\u002Ftrain.schema.json",71831,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fschemas\u002Ftrain.schema.json",{"path":135,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":136,"sourceHtmlUrl":137},"skill-card.md",3973,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fskill-card.md",{"path":139,"resourceType":140,"resourceTypeDesc":141,"sizeBytes":142,"sourceHtmlUrl":143},"skill.oms.sig","OTHER","其他",9357,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-oneformer\u002Fskill.oms.sig",[145,152,159,166,173,180],{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]