tao-train-pose-classification
Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-13
- Stars
- ★ 2
- Forks
- 2
01 前言 Front Matter
- name
- tao-train-pose-classification
- tags
- [ "pose", "classification" ]
- license
- Apache-2.0
- version
- 1.0.0 into action categories from pose-keypoint data. Use when training, evaluating, exporting, or running inference for a TAO pose-classification model. Trigger phrases include "train pose classification", "skeleton action recognition", "ST-GCN", "keypoint sequence classifier".
- category
- development-code
- metadata
- { "author": "NVIDIA Corporation", "version": "0.1.0" }
- description
- Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences
- allowed-tools
- Read Bash
- compatibility
- Requires docker + nvidia-container-toolkit.
02 资源文件 14
- 参考文档BENCHMARK.md4.3 KB
- 参考文档evals/evals.json805 B
- 参考文档references/skill_info.yaml1.5 KB
- 参考文档references/spec_template_evaluate.yaml1.3 KB
- 参考文档references/spec_template_export.yaml1.2 KB
- 参考文档references/spec_template_inference.yaml1.4 KB
- 参考文档references/spec_template_train.yaml1.2 KB
- 参考文档schemas/evaluate.schema.json25.1 KB
- 参考文档schemas/export.schema.json23.0 KB
- 参考文档schemas/inference.schema.json25.3 KB
- 参考文档schemas/manifest.json6.3 KB
- 参考文档schemas/train.schema.json21.5 KB
- 参考文档skill-card.md3.9 KB
- 其他skill.oms.sig6.9 KB
03 SKILL.md 正文
Pose Classification
Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences into action categories from pose keypoint data.
Typically trained from scratch on skeleton data.
Dataclass Schemas
Generated TAO Core schemas are packaged in schemas/<action>.schema.json, with schemas/manifest.json listing available actions. Each generated schema also emits references/spec_template_<action>.yaml from the schema top-level default field. AutoML enablement is declared at the model layer in references/skill_info.yaml via automl_enabled. Runnable AutoML still requires schemas/train.schema.json and references/spec_template_train.yaml to exist and parse. Use the packaged train schema for automl_default_parameters, automl_disabled_parameters, defaults, min/max bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect ~/tao-core at runtime; maintainers regenerate schemas/templates before packaging the skill bank.
Train Action Policy
This model is AutoML-enabled at the model layer. Before handling any train-stage request, read references/skill_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/train.schema.json and references/spec_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/application overrides for datasets, specs, output directories, GPU/platform settings, parent checkpoints, and automl_policy. Use direct model training only when automl_policy: off or the packaged train schema/template is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.
Non-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.
Training Requirements
- Dataset type: pose_classification
- Formats: default
- Monitoring metric: val_acc
Per-Action Dataset Requirements
| Action | Spec Key | Source | Files | List? |
|---|---|---|---|---|
| evaluate | evaluate.test_dataset.data_path | train_datasets | No | |
| evaluate | evaluate.test_dataset.label_path | train_datasets | No | |
| inference | inference.test_dataset.data_path | train_datasets | No | |
| train | dataset.train_dataset.data_path | train_datasets | No | |
| train | dataset.train_dataset.label_path | train_datasets | No | |
| train | dataset.val_dataset.data_path | train_datasets | No | |
| train | dataset.val_dataset.label_path | train_datasets | No |
Typical Spec Overrides
Data 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.
S3_TRAIN = "s3://bucket/data/train"
train (mandatory data sources):
{
"train.num_epochs": 30,
"train.checkpoint_interval": 10,
"train.validation_interval": 10,
"train.num_gpus": 1,
"num_classes": 6,
"graph_layout": "nvidia",
"dataset.train_dataset.data_path": f"{S3_TRAIN}",
"dataset.train_dataset.label_path": f"{S3_TRAIN}",
"dataset.val_dataset.data_path": f"{S3_TRAIN}",
"dataset.val_dataset.label_path": f"{S3_TRAIN}",
}
evaluate (mandatory data sources):
{
"evaluate.test_dataset.data_path": f"{S3_TRAIN}",
"evaluate.test_dataset.label_path": f"{S3_TRAIN}",
}
inference (mandatory data sources):
{
"inference.test_dataset.data_path": f"{S3_TRAIN}",
}
Eval Dataset
Optional. Validation data is provided alongside training as val_data.npy / val_label.pkl.
Important Parameters
- dataset.num_classes: Number of pose action classes. Default 6.
- model.graph_layout: Skeleton graph layout. Options: nvidia, openpose. Determines joint connectivity.
- model.graph_strategy: Graph partitioning strategy for GCN.
- train.optim.lr: Learning rate. Default 0.1 (SGD). Higher than vision models due to graph convolution properties.
- model.dropout: Dropout rate for regularization.
Multi-GPU / Multi-Node
Launch method: Lightning-managed (single python process, Lightning spawns workers).
| Spec Key | Description | Default |
|---|---|---|
train.num_gpus |
Number of GPUs | 1 |
train.gpu_ids |
GPU device indices | [0] |
- Strategy:
auto(Lightning picks best strategy automatically) - No explicit
num_nodesordistributed_strategyconfig — single-node only - Lightweight model, single GPU typically sufficient
Hardware
Minimum 1 GPU(s), recommended 1 GPU(s). 8GB+ VRAM per GPU. Pose classification is very lightweight — skeleton data is small. Single GPU is sufficient.
Error Patterns
Graph layout mismatch: Ensure model.graph_layout matches the skeleton format in your .npy data files.
Label shape mismatch: train_label.pkl class indices must be in range [0, num_classes).
Spec Param / Parent Model Inference
Model-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.
Inference mappings from TAO Core pose_classification.config.json:
| Action | Spec Field | Inference Function | Meaning |
|---|---|---|---|
| evaluate | encryption_key |
key |
encryption key |
| evaluate | evaluate.checkpoint |
parent_model |
model file inferred from the parent job results folder |
| evaluate | results_dir |
output_dir |
current job results directory |
| export | encryption_key |
key |
encryption key |
| export | export.checkpoint |
parent_model |
model file inferred from the parent job results folder |
| export | export.onnx_file |
create_onnx_file |
output ONNX path |
| export | results_dir |
output_dir |
current job results directory |
| inference | encryption_key |
key |
encryption key |
| inference | inference.checkpoint |
parent_model |
model file inferred from the parent job results folder |
| inference | inference.output_file |
create_inference_result_file_pose |
pose inference result file |
| inference | results_dir |
output_dir |
current job results directory |
| train | encryption_key |
key |
encryption key |
| train | model.pretrained_model_path |
ptm_if_no_resume_model |
PTM when no resume checkpoint exists |
| train | results_dir |
output_dir |
current job results directory |
| train | train.resume_training_checkpoint_path |
resume_model |
model file inferred from the current job results folder |
For parent_model or parent_model_folder, pass the upstream train/export/AutoML 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.
04 同仓库更多 Skills
yingmi-skill
当用户需要查询基金、策略、公告、财经资讯,做资产配置、组合诊断、风险回测、现金流分析,或生成图表、PDF 时,优先使用本 Skill 获取真实数据与可执行能力。
web-access
所有联网操作必须通过此 skill 处理,包括:搜索、网页抓取、登录后操作、网络交互等。
tencentmap-map-assistant
腾讯位置服务·地图助手 Skill,一句自然语言调用腾讯地图全套能力,无需开发者账号、开箱即用。提供 AI 旅游攻略、地点搜索(含评分/人均/营业时间)、关键词提示、路线规划(驾车/步行/公交/骑行)、地址解析与逆解析、行政区划、IP 定位、距离计算、天气查询,并可将行程或多 POI 渲染成网页地图。涉及找地点、规划路线、旅游行程、查天气、坐标转换等出行场景时使用。
skill-scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描, 检查 skill 安全, audit skill, scan skill, check skill safety, analyze skill, inspect skill, verify skill, skill security, skill supply chain. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.
shader-dev
Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.