tensorflow/models · error · ClassifierError

Checkpoint is missing required key 'model_state_dict'.

Error message

Checkpoint is missing required key 'model_state_dict'.

What it means

Key-presence check in _load_checkpoint_state_dict: torch.load succeeded, but the loaded object is a dict without the 'model_state_dict' entry. Training code saves checkpoints as {'model_state_dict': ..., plus optimizer/epoch metadata}; its absence means the file is not a training checkpoint for this module — e.g. a raw state_dict saved directly, a torch.hub weight file, or an optimizer-only checkpoint.

Solutions

1. Point checkpoint_path at the checkpoint saved by the training script (contains model_state_dict)
2. If you have a raw state dict, re-wrap it: torch.save({'model_state_dict': sd}, path)
3. Verify the file was produced by the matching fine-tuning code, not a different pipeline

When it happens

Trigger: Thrown at official/projects/waste_identification_ml/model_inference_with_tracking/sam3_dinov3_tracking_pipeline/dinov3_classifier.py:157 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tensorflow/models@e006f5f0d5 (2026-08-24). Data as JSON: /api/errors/10ca522be21b0970. Report an issue: GitHub.

Appendix: source

Thrown at official/projects/waste_identification_ml/model_inference_with_tracking/sam3_dinov3_tracking_pipeline/dinov3_classifier.py:157

    checkpoint_path: pathlib.Path | str, device: torch.device
) -> dict[str, torch.Tensor]:
  """Loads the model state dict from a checkpoint file.

  Args:
    checkpoint_path: Filesystem path to the checkpoint.
    device: Target device for `map_location`.

  Returns:
    The `model_state_dict` mapping from parameter name to tensor.

  Raises:
    ClassifierError: If the checkpoint is missing required keys.
  """
  checkpoint = torch.load(
      checkpoint_path, map_location=device, weights_only=True
  )
  if "model_state_dict" not in checkpoint:
    raise ClassifierError(
        "Checkpoint is missing required key 'model_state_dict'."
    )
  saved_state_dict = checkpoint["model_state_dict"]
  if "head.weight" not in saved_state_dict:
    raise ClassifierError(
        "Checkpoint state dict is missing required key 'head.weight'."
    )
  return saved_state_dict


def _build_image_transform(config: config_loader.DINOv3Config) -> v2.Compose:
  """Builds the preprocessing pipeline used to feed PIL images to the model.

  Args:
    config: DINOv3 model configuration providing image size and normalization
      statistics.

  Returns:

View on GitHub (pinned to e006f5f0d5)