[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PSHX1F8H2F8JXNQJ8T4019":3,"skill-same:01M6PSHX1F8H2F8JXNQJ8T4019":167},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6PSHX1F8H2F8JXNQJ8T4019","tao-train-grounding-dino",null,"Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection — detects objects described by text prompts without a fixed class vocabulary. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Grounding DINO model. Trigger phrases include \"train Grounding DINO\", \"open-vocabulary detection\", \"text-prompted detector\", \"language-guided object detection\".","headmktlucca-ui\u002Fneuroads-lp","headmktlucca-ui","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F247379838?v=4","01M6PDVAV6M1W96D1SR1PDF8CS","NeuroAds","01M6PDVAZ4P281GNDKD45CYTF5",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"tao train grounding dino","tao","grounding","train","container","for","object","with","trigger","objects","docker","use","model","text","Bash","open","SET","NVIDIA","toolkit","training","2026-11-10 10:12:30",false,"---\nname: tao-train-grounding-dino\ndescription: Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for\n  language-guided detection — detects objects described by text prompts without a fixed class vocabulary. Use when training,\n  evaluating, exporting, quantizing, or running inference for a TAO Grounding DINO model. Trigger phrases include \"train\n  Grounding DINO\", \"open-vocabulary detection\", \"text-prompted detector\", \"language-guided object detection\".\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- object\n- detection\n---\n\n# Grounding DINO\n\nGrounding DINO for open-set object detection. Combines DINO-style detection with BERT text encoder for language-guided detection. Detects objects described by text prompts without fixed class vocabulary.\n\nSet train.pretrained_model_path for full Grounding DINO weights or model.pretrained_backbone_path for backbone-only.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), read `references\u002Ftao-deploy-grounding-dino.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:** object_detection\n- **Formats:** odvg, coco, raw\n- **Monitoring metric:** val_mAP50\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | dataset.test_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| inference | dataset.infer_data_sources | inference_dataset | image_dir: images.tar.gz, classmap: label_map.txt | No |\n| quantize | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json | Yes |\n| quantize | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| quantize | dataset.quant_calibration_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json | No |\n| train | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json | Yes |\n| train | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | 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_epochs\": 10,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"train.num_gpus\": 1,\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations_odvg.jsonl\", \"label_map\": f\"{S3_TRAIN}\u002Fannotations_odvg_labelmap.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n\n**gen_trt_engine:**\n```python\n{\n    \"gen_trt_engine.tensorrt.data_type\": \"FP16\",\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.infer_data_sources.captions\": [\n        \"person\"\n    ],\n    \"dataset.infer_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"classmap\": f\"{S3_EVAL}\u002Flabel_map.txt\"},\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"dataset.test_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n\n**quantize (mandatory data sources):**\n```python\n{\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations_odvg.jsonl\", \"label_map\": f\"{S3_TRAIN}\u002Fannotations_odvg_labelmap.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n    \"dataset.quant_calibration_data_sources\": {\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations_odvg.jsonl\", \"label_map\": f\"{S3_TRAIN}\u002Fannotations_odvg_labelmap.json\"},\n}\n```\n## Eval Dataset\n\nOptional. Validation uses COCO-format annotations for mAP even though training can use ODVG format.\n\n## Important Parameters\n\n- **model.backbone**: Default swin_tiny_224_1k. Also supports resnet_50 and other Swin variants. Swin generally performs better for grounding tasks.\n- **model.text_encoder_type**: BERT model for text encoding. Default bert-base-uncased. max_text_len defaults to 256.\n- **train.optim.lr**: Learning rate. Default 2e-4. lr_backbone 2e-5. Supports bf16 precision in addition to fp16\u002Ffp32.\n- **dataset.max_labels**: Maximum labels per image during training. Default 50. Increase for dense annotation datasets.\n- **model.num_queries**: Object queries. Default 900 (higher than DINO's 300) due to open-vocabulary nature.\n- **train.optim.lr_steps**: MultiStep LR schedule. Default [10].\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| `train.distributed_strategy` | `ddp` or `fsdp` | `ddp` |\n\nSame DDP\u002FFSDP behavior as DINO. Multi-node requires `WORLD_SIZE`, `NODE_RANK`, `MASTER_ADDR`, `MASTER_PORT` env vars set by orchestrator.\n\n## Export \u002F TRT Defaults\n\n- Export input: 960x544 (larger than other OD models), opset 17\n- TRT data types: FP32, FP16 only — **INT8 is NOT supported**\n- TRT workspace: 8192 MB (8x larger than other OD models)\n- TRT max_batch_size: 4\n\nFull TAO Deploy reference: [tao-deploy-grounding-dino](references\u002Ftao-deploy-grounding-dino.md).\n\n## Hardware\n\nMinimum 1 GPU(s), recommended 4 GPU(s). 24GB+ (A100 recommended) VRAM per GPU. Grounding DINO is heavier than standard DINO due to the text encoder (BERT). 24GB+ GPU memory recommended. Reduce batch_size for 16GB GPUs.\n\n## Error Patterns\n\n**CUDA out of memory**: Reduce batch_size (4 -> 2 -> 1). The BERT text encoder adds significant memory overhead on top of the vision backbone.\n\n**Val annotation category IDs**: Validation annotations should have category IDs starting from 0 for correct loss computation. Use annotation format conversion if needed.\n\n**Text encoder loading error**: Ensure the container has access to download bert-base-uncased weights or provide a local path.\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 `grounding_dino.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 | `model.pretrained_backbone_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `results_dir` | `output_dir` | current job results directory |\n| train | `train.pretrained_model_path` | `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","# Grounding DINO\n\nGrounding DINO for open-set object detection. Combines DINO-style detection with BERT text encoder for language-guided detection. Detects objects described by text prompts without fixed class vocabulary.\n\nSet train.pretrained_model_path for full Grounding DINO weights or model.pretrained_backbone_path for backbone-only.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), read `references\u002Ftao-deploy-grounding-dino.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:** object_detection\n- **Formats:** odvg, coco, raw\n- **Monitoring metric:** val_mAP50\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | dataset.test_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| inference | dataset.infer_data_sources | inference_dataset | image_dir: images.tar.gz, classmap: label_map.txt | No |\n| quantize | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json | Yes |\n| quantize | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| quantize | dataset.quant_calibration_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json | No |\n| train | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json | Yes |\n| train | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | 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_epochs\": 10,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"train.num_gpus\": 1,\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations_odvg.jsonl\", \"label_map\": f\"{S3_TRAIN}\u002Fannotations_odvg_labelmap.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n\n**gen_trt_engine:**\n```python\n{\n    \"gen_trt_engine.tensorrt.data_type\": \"FP16\",\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.infer_data_sources.captions\": [\n        \"person\"\n    ],\n    \"dataset.infer_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"classmap\": f\"{S3_EVAL}\u002Flabel_map.txt\"},\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"dataset.test_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n\n**quantize (mandatory data sources):**\n```python\n{\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations_odvg.jsonl\", \"label_map\": f\"{S3_TRAIN}\u002Fannotations_odvg_labelmap.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n    \"dataset.quant_calibration_data_sources\": {\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations_odvg.jsonl\", \"label_map\": f\"{S3_TRAIN}\u002Fannotations_odvg_labelmap.json\"},\n}\n```\n## Eval Dataset\n\nOptional. Validation uses COCO-format annotations for mAP even though training can use ODVG format.\n\n## Important Parameters\n\n- **model.backbone**: Default swin_tiny_224_1k. Also supports resnet_50 and other Swin variants. Swin generally performs better for grounding tasks.\n- **model.text_encoder_type**: BERT model for text encoding. Default bert-base-uncased. max_text_len defaults to 256.\n- **train.optim.lr**: Learning rate. Default 2e-4. lr_backbone 2e-5. Supports bf16 precision in addition to fp16\u002Ffp32.\n- **dataset.max_labels**: Maximum labels per image during training. Default 50. Increase for dense annotation datasets.\n- **model.num_queries**: Object queries. Default 900 (higher than DINO's 300) due to open-vocabulary nature.\n- **train.optim.lr_steps**: MultiStep LR schedule. Default [10].\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| `train.distributed_strategy` | `ddp` or `fsdp` | `ddp` |\n\nSame DDP\u002FFSDP behavior as DINO. Multi-node requires `WORLD_SIZE`, `NODE_RANK`, `MASTER_ADDR`, `MASTER_PORT` env vars set by orchestrator.\n\n## Export \u002F TRT Defaults\n\n- Export input: 960x544 (larger than other OD models), opset 17\n- TRT data types: FP32, FP16 only — **INT8 is NOT supported**\n- TRT workspace: 8192 MB (8x larger than other OD models)\n- TRT max_batch_size: 4\n\nFull TAO Deploy reference: [tao-deploy-grounding-dino](references\u002Ftao-deploy-grounding-dino.md).\n\n## Hardware\n\nMinimum 1 GPU(s), recommended 4 GPU(s). 24GB+ (A100 recommended) VRAM per GPU. Grounding DINO is heavier than standard DINO due to the text encoder (BERT). 24GB+ GPU memory recommended. Reduce batch_size for 16GB GPUs.\n\n## Error Patterns\n\n**CUDA out of memory**: Reduce batch_size (4 -> 2 -> 1). The BERT text encoder adds significant memory overhead on top of the vision backbone.\n\n**Val annotation category IDs**: Validation annotations should have category IDs starting from 0 for correct loss computation. Use annotation format conversion if needed.\n\n**Text encoder loading error**: Ensure the container has access to download bert-base-uncased weights or provide a local path.\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 `grounding_dino.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 | `model.pretrained_backbone_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `results_dir` | `output_dir` | current job results directory |\n| train | `train.pretrained_model_path` | `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",{"name":5,"tags":44,"license":15,"metadata":46,"description":7,"allowed-tools":49,"compatibility":50},[25,45],"detection",{"author":47,"version":48},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit.","main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".claude\u002Fskills\u002Ftao-train-grounding-dino","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui","https:\u002F\u002Fneuroads.com.br","2026-08-12 00:42:44",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-grounding-dino",{"tool":64,"command":65},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-grounding-dino",{"tool":67,"command":68},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-grounding-dino","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002FSKILL.md",true,[72,78,82,86,90,94,98,102,106,110,114,118,121,125,129,133,137,141,145,149,153,157,161],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"BENCHMARK.md","REFERENCE","参考文档",4432,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002FBENCHMARK.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"evals\u002Fevals.json",780,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fevals\u002Fevals.json",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fskill_info.yaml",2045,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fskill_info.yaml",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fspec_template_deploy_evaluate.yaml",375,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_deploy_evaluate.yaml",{"path":91,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fspec_template_deploy_gen_trt_engine.yaml",343,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_deploy_gen_trt_engine.yaml",{"path":95,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fspec_template_deploy_inference.yaml",417,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_deploy_inference.yaml",{"path":99,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fspec_template_evaluate.yaml",3357,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_evaluate.yaml",{"path":103,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fspec_template_export.yaml",3454,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_export.yaml",{"path":107,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fspec_template_gen_trt_engine.yaml",3491,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_gen_trt_engine.yaml",{"path":111,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fspec_template_inference.yaml",3437,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_inference.yaml",{"path":115,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fspec_template_quantize.yaml",3209,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_quantize.yaml",{"path":119,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":116,"sourceHtmlUrl":120},"references\u002Fspec_template_train.yaml","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Fspec_template_train.yaml",{"path":122,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":123,"sourceHtmlUrl":124},"references\u002Ftao-deploy-grounding-dino.md",5142,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Ftao-deploy-grounding-dino.md",{"path":126,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":127,"sourceHtmlUrl":128},"references\u002Ftao-deploy-grounding-dino.skill_info.yaml",2317,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Freferences\u002Ftao-deploy-grounding-dino.skill_info.yaml",{"path":130,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":131,"sourceHtmlUrl":132},"schemas\u002Fevaluate.schema.json",57583,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fschemas\u002Fevaluate.schema.json",{"path":134,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":135,"sourceHtmlUrl":136},"schemas\u002Fexport.schema.json",58148,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fschemas\u002Fexport.schema.json",{"path":138,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":139,"sourceHtmlUrl":140},"schemas\u002Fgen_trt_engine.schema.json",59913,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fschemas\u002Fgen_trt_engine.schema.json",{"path":142,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":143,"sourceHtmlUrl":144},"schemas\u002Finference.schema.json",58523,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fschemas\u002Finference.schema.json",{"path":146,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":147,"sourceHtmlUrl":148},"schemas\u002Fmanifest.json",19620,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fschemas\u002Fmanifest.json",{"path":150,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":151,"sourceHtmlUrl":152},"schemas\u002Fquantize.schema.json",54213,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fschemas\u002Fquantize.schema.json",{"path":154,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":155,"sourceHtmlUrl":156},"schemas\u002Ftrain.schema.json",54207,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fschemas\u002Ftrain.schema.json",{"path":158,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":159,"sourceHtmlUrl":160},"skill-card.md",3880,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fskill-card.md",{"path":162,"resourceType":163,"resourceTypeDesc":164,"sizeBytes":165,"sourceHtmlUrl":166},"skill.oms.sig","OTHER","其他",9381,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-grounding-dino\u002Fskill.oms.sig",[168,194,218,244,262,297],{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":172,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":183,"publishedAt":39},"01M6PTDCZTXTGSTX4RFK901YSZ","xunit-skill","Generates xUnit.net tests in C#. Covers Fact\u002FTheory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal\", \"C# xUnit\". Triggers on: \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal C#\", \"xUnit.net\".","MIT","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxunit-skill\u002FSKILL.md",[175,180],{"categoryNo":176,"categoryName":177,"taxonomyType":178,"taxonomyTypeDesc":179},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":181,"categoryName":182,"taxonomyType":178,"taxonomyTypeDesc":179},"01JBSEEDCAT000000000000023","Skill与智能体开发",[184,185,186,187,188,30,189,190,191,192,193],"xunit","xunit skill","testing","injection","user","tests","triggers","unit","unit-testing","C#",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":172,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":202,"publishedAt":39},"01M6PTCB59ZTG5FTMWGPYEMMBP","xcuitest-skill","Generates XCUITest UI tests for iOS\u002FiPadOS apps in Swift. Apple's native testing framework for reliable, fast UI automation. Supports local simulators and TestMu AI cloud real devices. Use when user mentions \"XCUITest\", \"XCTest\", \"iOS UI test\", \"Swift test\", \"XCUIApplication\". Triggers on: \"XCUITest\", \"XCTest UI\", \"iOS UI test\", \"Swift UI test\", \"XCUIApplication\", \"TestMu\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxcuitest-skill\u002FSKILL.md",[200,201],{"categoryNo":176,"categoryName":177,"taxonomyType":178,"taxonomyTypeDesc":179},{"categoryNo":181,"categoryName":182,"taxonomyType":178,"taxonomyTypeDesc":179},[203,204,186,205,206,207,208,209,30,210,211,212,213,214,189,190,215,216,24,217],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","objective",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":172,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":228,"publishedAt":39},"01M6PTATMNTY9NF4J7KSR76YK6","world-builder","Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fworld-builder\u002FSKILL.md",[224,227],{"categoryNo":225,"categoryName":226,"taxonomyType":178,"taxonomyTypeDesc":179},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":181,"categoryName":182,"taxonomyType":178,"taxonomyTypeDesc":179},[229,230,231,232,233,234,235,236,30,237,238,239,240,241,242,24,243],"builder","world","world builder","MCP","create","mcp tools","Tools","game","pokemon","manage","style","via","theme","zone","generative",{"skillNo":245,"name":246,"nameZh":6,"description":247,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":172,"licenseFileUrl":6,"sourceHtmlUrl":248,"categories":249,"keywords":252,"publishedAt":39},"01M6PT9Z92JTSQEHE1QR0NNW5F","webdriverio-skill","Generates WebdriverIO (WDIO) automation tests in JavaScript or TypeScript. Supports local and TestMu AI cloud. Use when user mentions \"WebdriverIO\", \"WDIO\", \"wdio.conf\", \"browser.url\", \"$\", \"$$\". Triggers on: \"WebdriverIO\", \"WDIO\", \"wdio\", \"browser.$\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebdriverio-skill\u002FSKILL.md",[250,251],{"categoryNo":176,"categoryName":177,"taxonomyType":178,"taxonomyTypeDesc":179},{"categoryNo":181,"categoryName":182,"taxonomyType":178,"taxonomyTypeDesc":179},[253,186,254,205,255,256,257,258,188,30,259,213,189,190,260,261],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","URL","conf",{"skillNo":263,"name":264,"nameZh":6,"description":265,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":172,"licenseFileUrl":6,"sourceHtmlUrl":266,"categories":267,"keywords":277,"publishedAt":39},"01M6PT9NVK36ZWCQ69YXK3FR4K","web-design-guidelines","Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb\u002FSKILL.md",[268,271,272],{"categoryNo":269,"categoryName":270,"taxonomyType":178,"taxonomyTypeDesc":179},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":225,"categoryName":226,"taxonomyType":178,"taxonomyTypeDesc":179},{"categoryNo":273,"categoryName":274,"taxonomyType":275,"taxonomyTypeDesc":276},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[278,279,280,281,282,283,284,285,286,287,288,289,290,291,292,293,294,295,190,296],"design","web","guidelines","web design guidelines","web design","css","performance","components","web components","tasks","code","web performance","ui","platform design","html","responsive design","responsive","platform","implementing",{"skillNo":298,"name":299,"nameZh":6,"description":300,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":172,"licenseFileUrl":6,"sourceHtmlUrl":301,"categories":302,"keywords":305,"publishedAt":39},"01M6PT9A3JKRE3X34276F2FW5R","watchos-design-guidelines","Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwatchos\u002FSKILL.md",[303,304],{"categoryNo":225,"categoryName":226,"taxonomyType":178,"taxonomyTypeDesc":179},{"categoryNo":273,"categoryName":274,"taxonomyType":275,"taxonomyTypeDesc":276},[278,280,306,287,290,30,307,308,214,295,309,190,215,310,24,311,312],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]