Tao Train Pose Classification

Pose Classification

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

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.

The packaged PyTorch Pose Classification CLI supports dataset_convert, train, evaluate, export, and inference. dataset_convert is conditional: run it only when the input is raw DeepStream BodyPose JSON. If the dataset is already converted to TAO-ready .npy / .pkl files, start directly with train on those files and mark dataset conversion as not run: preconverted dataset provided in validation reports. This model does not expose deploy, prune, quantize, or standalone retrain actions. Resume/retrain behavior uses pose_classification train -e ... with train.resume_training_checkpoint_path populated.

Quick Start (docker run)

Docker-native launch — no TAO SDK and no Python on the host. Use the local Docker/platform skill instead when it gives a stricter environment-specific command (non-root UID mapping, cache redirects, remote daemons).

TAO_PYT_IMAGE_DEFAULT=nvcr.io/nvidia/tao/tao-toolkit:7.2.0-pyt  # versions-key: images.tao_toolkit.pyt
TAO_PYT_IMAGE="${TAO_PYT_IMAGE:-$TAO_PYT_IMAGE_DEFAULT}"
RUN_ROOT="${RUN_ROOT:-$PWD}"
DOCKER_COMMON=(
  --rm --gpus all --shm-size=8g
  --shm-size=8g
  --ulimit memlock=-1
  --ulimit stack=67108864
  -v "$RUN_ROOT/data:/data:ro"
  -v "$RUN_ROOT/specs:/specs:ro"
  -v "$RUN_ROOT/results:/results"
)

Dataset convert:

docker run "${DOCKER_COMMON[@]}" "$TAO_PYT_IMAGE" \
  pose_classification dataset_convert -e /specs/dataset_convert.yaml

Train:

docker run "${DOCKER_COMMON[@]}" "$TAO_PYT_IMAGE" \
  pose_classification train -e /specs/train.yaml

Evaluate:

docker run "${DOCKER_COMMON[@]}" "$TAO_PYT_IMAGE" \
  pose_classification evaluate -e /specs/evaluate.yaml

Inference:

docker run "${DOCKER_COMMON[@]}" "$TAO_PYT_IMAGE" \
  pose_classification inference -e /specs/inference.yaml

Export:

docker run "${DOCKER_COMMON[@]}" "$TAO_PYT_IMAGE" \
  pose_classification export -e /specs/export.yaml

Every action takes its spec with -e; results_dir is set in the spec or overridden on the command line. Mount any pretrained-weights directory the spec references, and keep every in-container path consistent across actions.

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 for an action requires schemas/<action>.schema.json and references/spec_template_<action>.yaml to exist and parse. Use the packaged selected-action 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. Use automl_policy: on by default and only expose on / 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/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
• AutoML training metric: val_loss, with direction=minimize
• Standalone evaluation metric: accuracy, with direction=maximize. Use val_loss to rank train-stage AutoML recommendations and use accuracy only to verify that the selected checkpoint loads and evaluates successfully.

Per-Action Dataset Requirements

Typical Spec Overrides

Data source overrides are mandatory for every action being run — the agent MUST construct data source paths from the Per-Action Dataset Requirements table above and include them in spec_overrides. Do not run dataset_convert when the supplied dataset is already converted to .npy / .pkl files.

S3_TRAIN = "s3://bucket/data/purpose_built_models_pose_classification_train/nvidia"
CHECKPOINT = "/results/{train_job_id}/results_dir/model_epoch_000_step_00007.pth"

dataset_convert (optional; raw DeepStream BodyPose JSON only):

{
    "dataset_convert.data": "s3://bucket/data/<deepstream-bodypose-output>.json",
}

train (mandatory data sources):

{
    "train.num_epochs": 30,
    "train.checkpoint_interval": 10,
    "train.validation_interval": 10,
    "train.num_gpus": 1,
    "wandb.enable": False,
    "dataset.num_classes": 6,
    "dataset.label_map": {
        "class_0": 0,
        "class_1": 1,
        "class_2": 2,
        "class_3": 3,
        "class_4": 4,
        "class_5": 5,
    },
    "model.graph_layout": "nvidia",
    "dataset.train_dataset.data_path": f"{S3_TRAIN}/train_data.npy",
    "dataset.train_dataset.label_path": f"{S3_TRAIN}/train_label.pkl",
    "dataset.val_dataset.data_path": f"{S3_TRAIN}/val_data.npy",
    "dataset.val_dataset.label_path": f"{S3_TRAIN}/val_label.pkl",
}

resume train (mandatory checkpoint):

{
    "train.num_epochs": 31,
    "train.resume_training_checkpoint_path": CHECKPOINT,
    "dataset.train_dataset.data_path": f"{S3_TRAIN}/train_data.npy",
    "dataset.train_dataset.label_path": f"{S3_TRAIN}/train_label.pkl",
    "dataset.val_dataset.data_path": f"{S3_TRAIN}/val_data.npy",
    "dataset.val_dataset.label_path": f"{S3_TRAIN}/val_label.pkl",
}

evaluate (mandatory data sources):

{
    "evaluate.test_dataset.data_path": f"{S3_TRAIN}/val_data.npy",
    "evaluate.test_dataset.label_path": f"{S3_TRAIN}/val_label.pkl",
    "evaluate.checkpoint": CHECKPOINT,
}

export (mandatory checkpoint and output):

{
    "export.checkpoint": CHECKPOINT,
    "export.onnx_file": "/results/{export_job_id}/results_dir/pose_classification.onnx",
}

inference (mandatory data sources):

{
    "inference.test_dataset.data_path": f"{S3_TRAIN}/test_data.npy",
    "inference.test_dataset.label_path": f"{S3_TRAIN}/test_label.pkl",
    "inference.checkpoint": CHECKPOINT,
    "inference.output_file": "/results/pose_classification_inference.txt",
}

Dataset Convert

Dataset conversion is optional for Pose Classification. Run pose_classification dataset_convert only when the user supplies raw DeepStream BodyPose JSON. For the common S3 validation dataset, the data is already converted to train_data.npy, train_label.pkl, val_data.npy, val_label.pkl, test_data.npy, and test_label.pkl; use those files directly for train/evaluate/inference/export flows and do not synthesize fake BodyPose JSON.

Eval Dataset

Optional. Validation data is provided alongside training as val_data.npy / val_label.pkl. TAO training emits val_loss as the TensorBoard validation scalar for this model; use val_loss with minimize direction for AutoML selection unless a custom evaluation hook supplies a different metric. The standalone evaluate action emits accuracy; compare that value with the selected checkpoint's evaluation result, but do not substitute it for the train-stage val_loss ranking KPI.

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.