# OpenPI: Dataset normalization statistics

Compute dataset mean and standard deviation for an OpenPI training configuration and save normalization assets. Inspect the pinned source and setup before use.

ID: `openpi-scripts-compute-norm-stats-py`

Record version: `source-8a64773495b714d6b18eded99d7cf87eb19d1bb3dd4a9fb47172b03de5d56a38`

Hub commit: `703369d7a095afb46da723634a9d983d2eda3054`

## Access

Fetch the pinned repository, verify this source checksum, and use upstream installation and invocation. This record does not install or execute code.

Optional inert file retrieval: `python /PATH_TO_SKILL/scripts/rsh.py fetch-source openpi-scripts-compute-norm-stats-py --project ./experiment --expected-source-revision 215abfb217dbac7d5f1273282331b9b1866c0479 --expected-source-sha256 8a64773495b714d6b18eded99d7cf87eb19d1bb3dd4a9fb47172b03de5d56a38 --json`. This verifies one file, preserves provenance and never installs or runs it. See [source-file retrieval](https://hub.superfastrobotics.com/source-files.md).

Hub preparation adapter: **false**. Runtime verification: **not_run**.

Upstream setup: https://github.com/Physical-Intelligence/openpi/blob/215abfb217dbac7d5f1273282331b9b1866c0479/README.md

## Source and license

- Repository: https://github.com/Physical-Intelligence/openpi
- Pinned source: https://github.com/Physical-Intelligence/openpi/blob/215abfb217dbac7d5f1273282331b9b1866c0479/scripts/compute_norm_stats.py
- Revision: `215abfb217dbac7d5f1273282331b9b1866c0479`
- Path: `scripts/compute_norm_stats.py`
- Source SHA256: `8a64773495b714d6b18eded99d7cf87eb19d1bb3dd4a9fb47172b03de5d56a38`
- Source bytes: 4042
- Original authors: Physical Intelligence team
- License: [Apache-2.0](https://github.com/Physical-Intelligence/openpi/blob/215abfb217dbac7d5f1273282331b9b1866c0479/LICENSE)
- License scope: Selected first-party workflow Python source only; preserve all upstream copyright, author and per-file notices. This does not relicense model weights, datasets, Gemma or other third-party model code, robot firmware, simulator binaries, meshes, dependencies or external services; their separate terms and access requirements remain applicable.

License SHA256: `43070e2d4e532684de521b885f385d0841030efa2b1a20bafb76133a5e1379c1`

## Artifact

```json
{
  "kind": "workflow",
  "format": "python",
  "workflow_role": "dataset-preparation"
}
```

## Requirements

```json
{
  "python": "Python >=3.11 as declared by the pinned pyproject.toml",
  "packages": [
    "Pinned OpenPI checkout and openpi-client",
    "Upstream uv environment; JAX/CUDA or PyTorch backend as selected",
    "Environment-specific ALOHA, DROID or LIBERO dependencies when selected"
  ],
  "display": "Upstream supports Ubuntu 22.04. Policy inference/training requires suitable NVIDIA GPU memory and separately obtained checkpoints/data; real robot clients additionally require the exact upstream robot setup and a configured policy server.",
  "execution_domain": "computation",
  "source_imports": [
    "numpy",
    "openpi.models.model",
    "openpi.shared.normalize",
    "openpi.training.config",
    "openpi.training.data_loader",
    "openpi.transforms",
    "tqdm",
    "tyro"
  ]
}
```

## Invocation

```json
{
  "entrypoint": "uv run scripts/compute_norm_stats.py",
  "notes": "Use the pinned upstream environment and CLI configuration, dataset/checkpoint paths and platform-specific README. Some upstream workflows can download assets or publish datasets; inspect flags before use. No checkpoint licensing, robot compatibility or runtime success is established by this source reference."
}
```

## Compatibility

```json
[]
```

Missing environment fields remain unknown. Source discovery labels do not establish robot compatibility.

## Evidence

Level: **source_reviewed**. Runtime verification: **not_run**.

Verified exact source, applicable license and author/setup document bytes at a full Git commit; parsed the Python AST and reviewed this guarded operational entrypoint and its explicit license notices. No upstream code, installation, robot command, dataset, mesh or checkpoint was executed or loaded.

Source review and contributor reports do not establish task completion. Preserve upstream attribution and licenses.