[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78JEEQG2WEGSDC89Z9Q90VT":3,"skill-same:01M78JEEQG2WEGSDC89Z9Q90VT":127},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":13,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M78JEEQG2WEGSDC89Z9Q90VT","tao-train-fast-foundation-stereo",null,"Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of FoundationStereo. Predicts disparity maps from stereo image pairs with ~10× lower latency than full FoundationStereo. Use when training, evaluating, exporting, or running inference for a TAO FastFoundationStereo (FFS) model. Trigger phrases include \"train fast stereo\", \"real-time stereo disparity\", \"FastFoundationStereo\", \"distilled stereo depth\".","matheussluzz\u002FZeuZ-Agent","matheussluzz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F209255758?v=4","01M78HKHH1D1ASC9KC9BG583DH","01M78HKHHP6W7XRXQM2SBCAM3R",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tao-train-fast-foundation-stereo\ndescription: Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of\n  FoundationStereo. Predicts disparity maps from stereo image pairs with ~10× lower latency than full FoundationStereo. Use\n  when training, evaluating, exporting, or running inference for a TAO FastFoundationStereo (FFS) model. Trigger phrases\n  include \"train fast stereo\", \"real-time stereo disparity\", \"FastFoundationStereo\", \"distilled stereo depth\".\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- stereo\n- depth\n- estimation\n- realtime\n- distilled\n---\n\n# Depth Net Fast Stereo\n\nReal-time stereo depth estimation using **FastFoundationStereo (FFS)** — the bp2 commercial distilled variant of FoundationStereo. Predicts disparity maps from rectified stereo image pairs with per-layer pruned widths for real-time inference.\n\nThe mono \u002F stereo \u002F fast-stereo skills share the unified TAO `depth_net` CLI; FFS is selected via `model.model_type: FastFoundationStereo`. FFS differs from `FoundationStereo` only in pruned per-layer widths and a serialized forward path; everything else (entrypoint, action verbs, dataset classes, deploy chain) is identical to `depth-net-stereo`.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, TensorRT `inference`), read `references\u002Ftao-deploy-fast-foundation-stereo.md` first. The deploy spec template lives at `references\u002Fspec_template_deploy.yaml`.\n\n## When to Use\n\nUse this skill to train, evaluate, export, or run inference for a TAO FastFoundationStereo model. Two supported use cases:\n\nFFS raw-deploy and bp2-finetune flows require a pre-trained bp2 commercial checkpoint (`model_best_bp2_serialize.pth`). The default PyT image does not guarantee that this file is present on disk, so treat the checkpoint path as a required user\u002Fregistry artifact. If no bp2 checkpoint is available, scratch training is still usable for workflow validation, but the resulting metrics are not representative of the bp2 model.\n\n1. **Raw deploy** — use the bp2 ckpt as-is. Skip `train`; run `inference` \u002F `evaluate` \u002F `export` \u002F `gen_trt_engine` directly with the bp2 file as the action's checkpoint.\n2. **Finetune on user data** — set `train.pretrained_model_path` to the bp2 file, train on user data, then verify + deploy on the resulting ckpt. The full 7-action sequence (train → evaluate pyt → inference pyt → export → gen_trt_engine → inference deploy → evaluate deploy) is supported.\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. Use `automl_policy: on` by default and only expose `on` \u002F `off` in new launch prompts. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only. When `automl_policy: on`, `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\nFFS shares the `depth_net_stereo` schema but its bp2 architecture widths are fixed invariants. For default AutoML, search only `train.optim.lr` and `train.optim.lr_decay` unless the user explicitly requests a wider search. Do not include FFS architecture fields such as `model.volume_dim`, `model.hidden_dims`, or other bp2 width settings in the default search space.\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## Workflow\n\n### Prerequisites — data accessibility\n\nYour dataset (left + right images + GT disparity for train \u002F evaluate, left + right only for inference) must be reachable from inside the container:\n- **SDK runner**: place files at the S3 paths the runner resolves (`S3_TRAIN` \u002F `S3_EVAL` placeholders shown in spec overrides).\n- **Direct `docker run`** (e.g. local testing): mount the host dataset root read-only at the same in-container path:\n\n```\ndocker run ... -v \u003Chost_data_root>:\u003Chost_data_root>:ro \u003Ccontainer> ...\n```\n\nThe same accessibility requirement applies to the `\u003Coutput_dir>` written by all actions, and to the bp2 checkpoint path.\n\n### Step 1 — Annotation file\n\nPer-line annotation file referenced by `data_sources[*].data_file`. Schema is identical to `depth-net-stereo`:\n\n| Columns | Format | Use |\n|---|---|---|\n| 2 | `\u003Cleft> \u003Cright>` | Stereo inference (no GT) |\n| 3 | `\u003Cleft> \u003Cright> \u003Cdisparity>` | Stereo with GT |\n| 4 | `\u003Cleft> \u003Cright> \u003Cdisparity> \u003Cocclusion_mask>` | Stereo with GT and occlusion mask |\n\nGenerate via `depth_net convert` if needed; see the `depth-net-stereo` skill for `convert_spec.yaml` template.\n\n### Step 2 — Pair `model_type` and `dataset_name` based on your data\n\nUse `model_type: FastFoundationStereo` for FFS. The `dataset_name` choice mirrors the stereo skill — pick the dataset-specific class when your layout matches a registered one, otherwise `GenericDataset`.\n\n| Data category | `model_type` | `dataset_name` |\n|---|---|---|\n| Middlebury | `FastFoundationStereo` | `Middlebury` |\n| KITTI | `FastFoundationStereo` | `Kitti` |\n| ETH3D | `FastFoundationStereo` | `Eth3d` |\n| FSD synthetic | `FastFoundationStereo` | `FSD` |\n| IsaacReal synthetic | `FastFoundationStereo` | `IsaacRealDataset` |\n| Crestereo synthetic | `FastFoundationStereo` | `Crestereo` |\n| Other \u002F non-canonical | `FastFoundationStereo` | `GenericDataset` |\n\nFor inference with 2-column annotations (left + right, no GT), use `dataset_name: GenericDataset` regardless of layout.\n\n### Step 3 — Set the bp2 distilled width overrides\n\nFFS requires 15 model-section width override fields whose values match the bp2 commercial checkpoint exactly. Omitting any field falls back to TAO defaults that do **not** match the bp2 ckpt and produce shape-mismatch errors at forward time. See `references\u002Fsetup-and-run.md` for the full copy-as-is `model:` block and notes. The spec templates at `references\u002Fspec_template_*.yaml` carry this block as the canonical source.\n\n### Step 4 — Write spec yaml from spec overrides\n\nCopy the action block from `references\u002Fspec-overrides.md`. Replace:\n- `model.model_type: FastFoundationStereo` (already set)\n- `dataset.\u003C...>.data_sources[*].dataset_name` from Step 2\n- `dataset.\u003C...>.data_sources[*].data_file` with the path from Step 1\n- For raw deploy use cases (no train): set `\u003Caction>.checkpoint` to the bp2 file path\n- For finetune use cases: set `train.pretrained_model_path` to the bp2 file path\n\nFor chained train → next-action checkpoint path resolution and shape-consistency notes, see `references\u002Fsetup-and-run.md`. SDK-runner deploys resolve handoff automatically via `parent_job_id` — see `references\u002Fparent-model-inference.md`.\n\n### Step 5 — Run\n\nCreate writable home\u002Fcache directories inside the mounted output path before using `--user`, then launch `docker run ... depth_net \u003Caction> -e \u003Cspec.yaml>`. See `references\u002Fsetup-and-run.md` for the full `mkdir` + `docker run` command, the `--user` rationale, and the local bind-mount `__pycache__` tip.\n\n### Step 6 — Verify\n\nCheck container exit code 0 and a populated `status.json` `kpi` block. For `train` inspect per-step `train_loss` directly (the entrypoint reports `Execution status: PASS` even when loss is NaN); for `evaluate` rely on `epe` \u002F `bp1` \u002F `bp2` \u002F `bp3` \u002F `d1` \u002F `rmse`; for `inference` check artifacts under `results_dir`. The pyt-vs-deploy KPI namespace difference and the expected deploy drift are detailed in `references\u002Fsetup-and-run.md`.\n\n### 7-action deploy flow\n\n```\ntrain (optional)            → finetuned ckpt\nevaluate (pyt)              → PyT eager EPE \u002F bp on val GT\ninference (pyt)             → PyT eager disparity samples (visual sanity)\nexport                      → static fp32 ONNX (recommended at 480×736 or 320×736)\ngen_trt_engine             → fp16 TRT engine on static ONNX path\ninference (deploy)         → TRT disparity samples\nevaluate (deploy)          → TRT EPE \u002F bp drift vs PyT eager fp32\n```\n\nSkip `train` for raw-bp2 deploy. The remaining 6 actions (or the 4 deploy-only verbs starting from `export`) cover both use cases.\n\n## Training Requirements\n\n- **Valid `dataset_name` values for stereo `data_sources`** (case-insensitive): `FSD`, `IsaacRealDataset`, `Crestereo`, `Middlebury`, `Eth3d`, `Kitti`, `GenericDataset`\n- **Monitoring metric:** val\u002Floss\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | dataset.test_dataset.data_sources | eval_dataset | data_file: annotations.txt + dataset_name | Yes |\n| inference | dataset.infer_dataset.data_sources | inference_dataset | data_file: annotations.txt + dataset_name | Yes |\n| train | dataset.train_dataset.data_sources | train_datasets | data_file: annotations.txt + dataset_name | Yes |\n| train | dataset.val_dataset.data_sources | eval_dataset | data_file: annotations.txt + dataset_name | Yes |\n\n### Typical Spec Overrides\n\nData source overrides are **mandatory for every action**. Each `data_sources` entry is a dict with **two mandatory fields**: `data_file` and `dataset_name`. The `model.*` width fields are also mandatory — see Step 3. See `references\u002Fspec-overrides.md` for the `FFS_MODEL_BLOCK` and per-action (train \u002F evaluate \u002F inference \u002F export) Python override dicts.\n\n## Eval Dataset\n\nOptional. Val dataset configured via `dataset.val_dataset.data_sources` (each entry needs `data_file` and `dataset_name`).\n\n## Important Parameters\n\nKey knobs include `model.model_type` (`FastFoundationStereo`), `model.encoder` (`vitl`), `model.max_disparity` (set `192` explicitly — schema default `416` causes severe drift), `model.mixed_precision` (`false`), `model.gwc_feature_normalize` (`true`), `model.volume_dim` (`28`), `model.valid_iters` (`8`), and per-split `batch_size` \u002F `workers` \u002F `crop_size` \u002F `data_sources`. Full parameter reference, evaluation metrics, multi-GPU \u002F multi-node spec keys, export \u002F TRT defaults, the export use-case matrix, and hardware guidance are in `references\u002Fimportant-parameters.md`.\n\n## Error Patterns\n\nFor `shape mismatch`, `gwc_feature_normalize` schema errors, `max_disparity` drift, negative disparity, `depth_net_stereo: not found`, the pyt-`evaluate` `crop_size` asymmetry, the `Failed to import SAM3` warning, and the dynamic-engine stride-incompatible silent failure, see `references\u002Ferror-patterns.md`.\n\n## Spec Param \u002F Parent Model Inference\n\nModel-specific inference mappings (per-action spec field → inference function) for train \u002F evaluate \u002F inference \u002F export \u002F gen_trt_engine, plus `parent_job_id` \u002F `parent_model` resolution and raw-bp2 explicit-checkpoint handling, are in `references\u002Fparent-model-inference.md`. Generated runners should read that section and apply the mappings with SDK helpers before `create_job()`.\n\n## Deployment\n\n- [tao-deploy-fast-foundation-stereo](references\u002Ftao-deploy-fast-foundation-stereo.md)\n","# Depth Net Fast Stereo\n\nReal-time stereo depth estimation using **FastFoundationStereo (FFS)** — the bp2 commercial distilled variant of FoundationStereo. Predicts disparity maps from rectified stereo image pairs with per-layer pruned widths for real-time inference.\n\nThe mono \u002F stereo \u002F fast-stereo skills share the unified TAO `depth_net` CLI; FFS is selected via `model.model_type: FastFoundationStereo`. FFS differs from `FoundationStereo` only in pruned per-layer widths and a serialized forward path; everything else (entrypoint, action verbs, dataset classes, deploy chain) is identical to `depth-net-stereo`.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, TensorRT `inference`), read `references\u002Ftao-deploy-fast-foundation-stereo.md` first. The deploy spec template lives at `references\u002Fspec_template_deploy.yaml`.\n\n## When to Use\n\nUse this skill to train, evaluate, export, or run inference for a TAO FastFoundationStereo model. Two supported use cases:\n\nFFS raw-deploy and bp2-finetune flows require a pre-trained bp2 commercial checkpoint (`model_best_bp2_serialize.pth`). The default PyT image does not guarantee that this file is present on disk, so treat the checkpoint path as a required user\u002Fregistry artifact. If no bp2 checkpoint is available, scratch training is still usable for workflow validation, but the resulting metrics are not representative of the bp2 model.\n\n1. **Raw deploy** — use the bp2 ckpt as-is. Skip `train`; run `inference` \u002F `evaluate` \u002F `export` \u002F `gen_trt_engine` directly with the bp2 file as the action's checkpoint.\n2. **Finetune on user data** — set `train.pretrained_model_path` to the bp2 file, train on user data, then verify + deploy on the resulting ckpt. The full 7-action sequence (train → evaluate pyt → inference pyt → export → gen_trt_engine → inference deploy → evaluate deploy) is supported.\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. Use `automl_policy: on` by default and only expose `on` \u002F `off` in new launch prompts. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only. When `automl_policy: on`, `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\nFFS shares the `depth_net_stereo` schema but its bp2 architecture widths are fixed invariants. For default AutoML, search only `train.optim.lr` and `train.optim.lr_decay` unless the user explicitly requests a wider search. Do not include FFS architecture fields such as `model.volume_dim`, `model.hidden_dims`, or other bp2 width settings in the default search space.\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## Workflow\n\n### Prerequisites — data accessibility\n\nYour dataset (left + right images + GT disparity for train \u002F evaluate, left + right only for inference) must be reachable from inside the container:\n- **SDK runner**: place files at the S3 paths the runner resolves (`S3_TRAIN` \u002F `S3_EVAL` placeholders shown in spec overrides).\n- **Direct `docker run`** (e.g. local testing): mount the host dataset root read-only at the same in-container path:\n\n```\ndocker run ... -v \u003Chost_data_root>:\u003Chost_data_root>:ro \u003Ccontainer> ...\n```\n\nThe same accessibility requirement applies to the `\u003Coutput_dir>` written by all actions, and to the bp2 checkpoint path.\n\n### Step 1 — Annotation file\n\nPer-line annotation file referenced by `data_sources[*].data_file`. Schema is identical to `depth-net-stereo`:\n\n| Columns | Format | Use |\n|---|---|---|\n| 2 | `\u003Cleft> \u003Cright>` | Stereo inference (no GT) |\n| 3 | `\u003Cleft> \u003Cright> \u003Cdisparity>` | Stereo with GT |\n| 4 | `\u003Cleft> \u003Cright> \u003Cdisparity> \u003Cocclusion_mask>` | Stereo with GT and occlusion mask |\n\nGenerate via `depth_net convert` if needed; see the `depth-net-stereo` skill for `convert_spec.yaml` template.\n\n### Step 2 — Pair `model_type` and `dataset_name` based on your data\n\nUse `model_type: FastFoundationStereo` for FFS. The `dataset_name` choice mirrors the stereo skill — pick the dataset-specific class when your layout matches a registered one, otherwise `GenericDataset`.\n\n| Data category | `model_type` | `dataset_name` |\n|---|---|---|\n| Middlebury | `FastFoundationStereo` | `Middlebury` |\n| KITTI | `FastFoundationStereo` | `Kitti` |\n| ETH3D | `FastFoundationStereo` | `Eth3d` |\n| FSD synthetic | `FastFoundationStereo` | `FSD` |\n| IsaacReal synthetic | `FastFoundationStereo` | `IsaacRealDataset` |\n| Crestereo synthetic | `FastFoundationStereo` | `Crestereo` |\n| Other \u002F non-canonical | `FastFoundationStereo` | `GenericDataset` |\n\nFor inference with 2-column annotations (left + right, no GT), use `dataset_name: GenericDataset` regardless of layout.\n\n### Step 3 — Set the bp2 distilled width overrides\n\nFFS requires 15 model-section width override fields whose values match the bp2 commercial checkpoint exactly. Omitting any field falls back to TAO defaults that do **not** match the bp2 ckpt and produce shape-mismatch errors at forward time. See `references\u002Fsetup-and-run.md` for the full copy-as-is `model:` block and notes. The spec templates at `references\u002Fspec_template_*.yaml` carry this block as the canonical source.\n\n### Step 4 — Write spec yaml from spec overrides\n\nCopy the action block from `references\u002Fspec-overrides.md`. Replace:\n- `model.model_type: FastFoundationStereo` (already set)\n- `dataset.\u003C...>.data_sources[*].dataset_name` from Step 2\n- `dataset.\u003C...>.data_sources[*].data_file` with the path from Step 1\n- For raw deploy use cases (no train): set `\u003Caction>.checkpoint` to the bp2 file path\n- For finetune use cases: set `train.pretrained_model_path` to the bp2 file path\n\nFor chained train → next-action checkpoint path resolution and shape-consistency notes, see `references\u002Fsetup-and-run.md`. SDK-runner deploys resolve handoff automatically via `parent_job_id` — see `references\u002Fparent-model-inference.md`.\n\n### Step 5 — Run\n\nCreate writable home\u002Fcache directories inside the mounted output path before using `--user`, then launch `docker run ... depth_net \u003Caction> -e \u003Cspec.yaml>`. See `references\u002Fsetup-and-run.md` for the full `mkdir` + `docker run` command, the `--user` rationale, and the local bind-mount `__pycache__` tip.\n\n### Step 6 — Verify\n\nCheck container exit code 0 and a populated `status.json` `kpi` block. For `train` inspect per-step `train_loss` directly (the entrypoint reports `Execution status: PASS` even when loss is NaN); for `evaluate` rely on `epe` \u002F `bp1` \u002F `bp2` \u002F `bp3` \u002F `d1` \u002F `rmse`; for `inference` check artifacts under `results_dir`. The pyt-vs-deploy KPI namespace difference and the expected deploy drift are detailed in `references\u002Fsetup-and-run.md`.\n\n### 7-action deploy flow\n\n```\ntrain (optional)            → finetuned ckpt\nevaluate (pyt)              → PyT eager EPE \u002F bp on val GT\ninference (pyt)             → PyT eager disparity samples (visual sanity)\nexport                      → static fp32 ONNX (recommended at 480×736 or 320×736)\ngen_trt_engine             → fp16 TRT engine on static ONNX path\ninference (deploy)         → TRT disparity samples\nevaluate (deploy)          → TRT EPE \u002F bp drift vs PyT eager fp32\n```\n\nSkip `train` for raw-bp2 deploy. The remaining 6 actions (or the 4 deploy-only verbs starting from `export`) cover both use cases.\n\n## Training Requirements\n\n- **Valid `dataset_name` values for stereo `data_sources`** (case-insensitive): `FSD`, `IsaacRealDataset`, `Crestereo`, `Middlebury`, `Eth3d`, `Kitti`, `GenericDataset`\n- **Monitoring metric:** val\u002Floss\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | dataset.test_dataset.data_sources | eval_dataset | data_file: annotations.txt + dataset_name | Yes |\n| inference | dataset.infer_dataset.data_sources | inference_dataset | data_file: annotations.txt + dataset_name | Yes |\n| train | dataset.train_dataset.data_sources | train_datasets | data_file: annotations.txt + dataset_name | Yes |\n| train | dataset.val_dataset.data_sources | eval_dataset | data_file: annotations.txt + dataset_name | Yes |\n\n### Typical Spec Overrides\n\nData source overrides are **mandatory for every action**. Each `data_sources` entry is a dict with **two mandatory fields**: `data_file` and `dataset_name`. The `model.*` width fields are also mandatory — see Step 3. See `references\u002Fspec-overrides.md` for the `FFS_MODEL_BLOCK` and per-action (train \u002F evaluate \u002F inference \u002F export) Python override dicts.\n\n## Eval Dataset\n\nOptional. Val dataset configured via `dataset.val_dataset.data_sources` (each entry needs `data_file` and `dataset_name`).\n\n## Important Parameters\n\nKey knobs include `model.model_type` (`FastFoundationStereo`), `model.encoder` (`vitl`), `model.max_disparity` (set `192` explicitly — schema default `416` causes severe drift), `model.mixed_precision` (`false`), `model.gwc_feature_normalize` (`true`), `model.volume_dim` (`28`), `model.valid_iters` (`8`), and per-split `batch_size` \u002F `workers` \u002F `crop_size` \u002F `data_sources`. Full parameter reference, evaluation metrics, multi-GPU \u002F multi-node spec keys, export \u002F TRT defaults, the export use-case matrix, and hardware guidance are in `references\u002Fimportant-parameters.md`.\n\n## Error Patterns\n\nFor `shape mismatch`, `gwc_feature_normalize` schema errors, `max_disparity` drift, negative disparity, `depth_net_stereo: not found`, the pyt-`evaluate` `crop_size` asymmetry, the `Failed to import SAM3` warning, and the dynamic-engine stride-incompatible silent failure, see `references\u002Ferror-patterns.md`.\n\n## Spec Param \u002F Parent Model Inference\n\nModel-specific inference mappings (per-action spec field → inference function) for train \u002F evaluate \u002F inference \u002F export \u002F gen_trt_engine, plus `parent_job_id` \u002F `parent_model` resolution and raw-bp2 explicit-checkpoint handling, are in `references\u002Fparent-model-inference.md`. Generated runners should read that section and apply the mappings with SDK helpers before `create_job()`.\n\n## Deployment\n\n- [tao-deploy-fast-foundation-stereo](references\u002Ftao-deploy-fast-foundation-stereo.md)\n",{"name":5,"tags":23,"license":14,"metadata":29,"description":7,"allowed-tools":32,"compatibility":33},[24,25,26,27,28],"stereo","depth","estimation","realtime","distilled",{"author":30,"version":31},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit.","main","fc4f2c7759ae400c66cd38656db70ead882a0d08","catalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent#readme","https:\u002F\u002Fgithub.com\u002Fmatheussluzz","2026-08-27 05:21:51",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add matheussluzz\u002FZeuZ-Agent --skill tao-train-fast-foundation-stereo",{"tool":47,"command":48},"bunx","bunx skills add matheussluzz\u002FZeuZ-Agent --skill tao-train-fast-foundation-stereo",{"tool":50,"command":51},"pnpm","pnpm dlx skills add matheussluzz\u002FZeuZ-Agent --skill tao-train-fast-foundation-stereo","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002FSKILL.md",true,[55,61,65,69,73,77,81,85,89,93,97,101,105,109,113,117,123],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"BENCHMARK.md","REFERENCE","参考文档",4035,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002FBENCHMARK.md",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ferror-patterns.md",3315,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Ferror-patterns.md",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fimportant-parameters.md",7474,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fimportant-parameters.md",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fparent-model-inference.md",3052,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fparent-model-inference.md",{"path":74,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fsetup-and-run.md",5602,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fsetup-and-run.md",{"path":78,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fskill_info.yaml",4479,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fskill_info.yaml",{"path":82,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fspec_template_deploy.yaml",2733,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fspec_template_deploy.yaml",{"path":86,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fspec_template_evaluate.yaml",1890,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fspec_template_evaluate.yaml",{"path":90,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fspec_template_export.yaml",1870,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fspec_template_export.yaml",{"path":94,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fspec_template_inference.yaml",1835,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fspec_template_inference.yaml",{"path":98,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fspec_template_train.yaml",2707,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fspec_template_train.yaml",{"path":102,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fspec-overrides.md",3497,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Fspec-overrides.md",{"path":106,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Ftao-deploy-fast-foundation-stereo.md",19675,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Ftao-deploy-fast-foundation-stereo.md",{"path":110,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Ftao-deploy-fast-foundation-stereo.skill_info.yaml",3741,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Freferences\u002Ftao-deploy-fast-foundation-stereo.skill_info.yaml",{"path":114,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":115,"sourceHtmlUrl":116},"skill-card.md",4105,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Fskill-card.md",{"path":118,"resourceType":119,"resourceTypeDesc":120,"sizeBytes":121,"sourceHtmlUrl":122},"skill.oms.sig","OTHER","其他",7889,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Fskill.oms.sig",{"path":124,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":125,"sourceHtmlUrl":126},"zeuz.manifest.yaml",172,"https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fcatalog\u002Fbundles\u002Fnvidia\u002Ftao-train-fast-foundation-stereo\u002Fzeuz.manifest.yaml",[128,136,143,150,157,164],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":132,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":18},"01M78JQ2R0QR8H2Z6662RFX804","gamma","Fixture skill gamma for discovery benchmarks.","MIT","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-registry-mini\u002Fskills\u002Fgamma\u002FSKILL.md",[],[],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":132,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":18},"01M78JQ1KCVZ15APZG3FFF29K0","beta","Fixture skill beta for discovery benchmarks.","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-registry-mini\u002Fskills\u002Fbeta\u002FSKILL.md",[],[],{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":132,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":18},"01M78JQ0FJTK4Q9JKZMX9SVSEN","alpha","Fixture skill alpha for discovery benchmarks.","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-registry-mini\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":132,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":18},"01M78JPYVYPY7R8QS10KADQPWE","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":132,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":18},"01M78JPVYHB88RF5ATZVGX84RR","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":132,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"publishedAt":18},"01M78JPSSWNTZW89DWGJTX7716","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fmatheussluzz\u002FZeuZ-Agent\u002Fblob\u002Fmain\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[]]