Diffusion Policy: Checkpoint simulation evaluation

Pinned evaluation entrypoint that loads a selected policy checkpoint and runs the checkpoint-configured simulation environment runner. Statically reviewed source only; not run and no Hub preparation adapter.

diffusion-policy-eval-py | Record version: source-e62694214cce4265ad783d1352713e25e963fb6684365ff1f0f4db08e57ade12

Record JSON | Markdown | Pinned upstream source

Access

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

Hub preparation adapter: false. Follow the upstream setup and invocation contract.

Source and license

Repository: https://github.com/real-stanford/diffusion_policy
Revision: 5ba07ac6661db573af695b419a7947ecb704690f
Path: eval.py
Source SHA256: e62694214cce4265ad783d1352713e25e963fb6684365ff1f0f4db08e57ade12
Original authors: Cheng Chi, Siyuan Feng, Yilun Du, Zhenjia Xu, Eric Cousineau, Benjamin Burchfiel, Shuran Song
License: MIT
License scope: Selected first-party Python workflow source only. Preserve upstream copyright and per-file notices. Model weights, datasets, third-party code, robot drivers/firmware and services retain separate terms; no rights for those assets are inferred.
License SHA256: 304e99a48271e10820f71a1b86ef395c06c100d7f68dd1d308790d1064fc4d41
Hub commit: 1d6d9eb134e397d910265a8d6e7d8f257f9e8d7f

Artifact

{
  "kind": "workflow",
  "format": "python",
  "workflow_role": "policy-evaluation"
}

Requirements

{
  "python": "Python 3.9 in upstream conda environment.",
  "packages": [
    "Pinned diffusion_policy checkout",
    "Workflow-specific conda environment with PyTorch1.12.1 and CUDA toolkit11.6",
    "Configured simulator or real-robot dependencies"
  ],
  "display": "Hardware: CLI device defaults to cuda:0. README benchmark setup is Linux/NVIDIA GPU; alternate device flag does not establish CPU compatibility. Weights: Required local checkpoint is loaded with torch.load and dill; it contains the workspace configuration. No checkpoint was downloaded, deserialized or trusted during review. Datasets: Environment/assets are selected by the checkpoint's env_runner configuration; no standalone training-data download is required by this selected evaluator. Services/auth: Imports W&B for video-object handling but contains no wandb.init/login call. No mandatory online API authentication is declared in this selected script.",
  "execution_domain": "simulation",
  "source_imports": [
    "click",
    "diffusion_policy.workspace.base_workspace",
    "dill",
    "hydra",
    "json",
    "os",
    "pathlib",
    "sys",
    "torch",
    "wandb"
  ],
  "notes": "Checkpoint metadata drives dynamic workspace/environment loading. This is a source-only pointer; local checkpoint loading was not performed. Code licensing does not establish model, checkpoint, dataset or service permission.",
  "declared_requirements": {
    "python": "Python 3.9 in upstream conda environment.",
    "weights": "Required local checkpoint is loaded with torch.load and dill; it contains the workspace configuration. No checkpoint was downloaded, deserialized or trusted during review.",
    "datasets": "Environment/assets are selected by the checkpoint's env_runner configuration; no standalone training-data download is required by this selected evaluator.",
    "hardware": "CLI device defaults to cuda:0. README benchmark setup is Linux/NVIDIA GPU; alternate device flag does not establish CPU compatibility.",
    "external_services_and_auth": "Imports W&B for video-object handling but contains no wandb.init/login call. No mandatory online API authentication is declared in this selected script.",
    "evidence": [
      {
        "anchor": "pickle_module=dill",
        "line": 31
      },
      {
        "anchor": "default='cuda:0'",
        "line": 24
      },
      {
        "anchor": "env_runner.run(policy)",
        "line": 51
      }
    ],
    "license_scopes": {
      "code": "MIT for selected first-party workflow source.",
      "weights": "README links separately downloadable trained checkpoints but the reviewed repository text does not separately establish their license. Do not extend first-party-code MIT to weights.",
      "datasets": "README links separate task demonstration datasets and dependencies such as robomimic. Individual dataset licenses were not reviewed; code MIT does not grant dataset rights.",
      "third_party_code": "External dependencies retain their own licenses."
    },
    "interpretation": "Pinned upstream declarations only; no dependency resolution, model/data access, compatibility inference or runtime validation was performed."
  }
}

Invocation

{
  "entrypoint": "python eval.py --checkpoint <approved-local-checkpoint> --output_dir <local-output> --device <reviewed-device>",
  "notes": "Checkpoint metadata drives dynamic workspace/environment loading. This is a source-only pointer; local checkpoint loading was not performed."
}

Explicit compatibility

[]

Missing environment fields remain unknown. 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.