open-mmlab/mmdetection · error · RuntimeError

Please run "pip install openmim" and run "mim install mmpret

Error message

Please run "pip install openmim" and run "mim install mmpretrain" to install mmpretrain first.

What it means

ReIDDataPreprocessor.__init__ raises RuntimeError when the optional mmpretrain package is not importable. The ReID training pipeline (e.g. for MOT/DeepSORT) depends on mmpretrain for its loss utilities.

Source

Thrown at mmdet/models/data_preprocessors/reid_data_preprocessor.py:90

        to_onehot (bool): Whether to generate one-hot format gt-labels and set
            to data samples. Defaults to False.
        num_classes (int, optional): The number of classes. Defaults to None.
        batch_augments (dict, optional): The batch augmentations settings,
            including "augments" and "probs". For more details, see
            :class:`mmpretrain.models.RandomBatchAugment`.
    """

    def __init__(self,
                 mean: Sequence[Number] = None,
                 std: Sequence[Number] = None,
                 pad_size_divisor: int = 1,
                 pad_value: Number = 0,
                 to_rgb: bool = False,
                 to_onehot: bool = False,
                 num_classes: Optional[int] = None,
                 batch_augments: Optional[dict] = None):
        if mmpretrain is None:
            raise RuntimeError('Please run "pip install openmim" and '
                               'run "mim install mmpretrain" to '
                               'install mmpretrain first.')
        super().__init__()
        self.pad_size_divisor = pad_size_divisor
        self.pad_value = pad_value
        self.to_rgb = to_rgb
        self.to_onehot = to_onehot
        self.num_classes = num_classes

        if mean is not None:
            assert std is not None, 'To enable the normalization in ' \
                'preprocessing, please specify both `mean` and `std`.'
            # Enable the normalization in preprocessing.
            self._enable_normalize = True
            self.register_buffer('mean',
                                 torch.tensor(mean).view(-1, 1, 1), False)
            self.register_buffer('std',
                                 torch.tensor(std).view(-1, 1, 1), False)

View on GitHub (pinned to cfd5d3a985)

Solutions

1. pip install openmim && mim install mmpretrain
2. Verify with python -c 'import mmpretrain'
3. Or avoid ReID configs if mmpretrain is not needed

Example fix

// shell
pip install openmim
mim install mmpretrain

try:\n    import mmpretrain  # noqa\nexcept ImportError:\n    raise SystemExit('Run: mim install mmpretrain')

When it happens

Trigger: Instantiating ReIDDataPreprocessor in a tracking (ByteTrack/DeepSORT) training config without mmpretrain installed; only mmdet is installed in the environment.

Common situations: Setting up MOT ReID training environments; missing optional dependency after a fresh mmdet install.

Related errors

• Please run "pip install openmim" and run "mim install mmpret
• Please run "pip install openmim" and run "mim install mmpret
• only {num_videos} videos loaded,but {self.world_size} gpus w
• trackeval is not installed,please install it by: pip install
• metric must be a list or a str.

AI-assisted analysis of open-mmlab/mmdetection@cfd5d3a985 (2026-08-27). Data as JSON: /api/errors/200156d340a7b914. Report an issue: GitHub.