Method __init__

monai/data/dataset.py:551–613

Args: data: input data file paths to load and transform to generate dataset for model. `LMDBDataset` expects input data to be a list of serializable and hashes them as cache keys using `hash_func`. transform: transforms to execute oper

(
        self,
        data: Sequence,
        transform: Sequence[Callable] | Callable,
        cache_dir: Path | str = "cache",
        hash_func: Callable[..., bytes] = pickle_hashing,
        db_name: str = "monai_cache",
        progress: bool = True,
        pickle_protocol=DEFAULT_PROTOCOL,
        hash_transform: Callable[..., bytes] | None = None,
        reset_ops_id: bool = True,
        lmdb_kwargs: dict | None = None,
    )

    """

    def __init__(
        self,
        data: Sequence,
        transform: Sequence[Callable] | Callable,
        cache_dir: Path | str = "cache",
        hash_func: Callable[..., bytes] = pickle_hashing,
        db_name: str = "monai_cache",
        progress: bool = True,
        pickle_protocol=DEFAULT_PROTOCOL,
        hash_transform: Callable[..., bytes] | None = None,
        reset_ops_id: bool = True,
        lmdb_kwargs: dict | None = None,
    ) -> None:
        """
        Args:
            data: input data file paths to load and transform to generate dataset for model.
                `LMDBDataset` expects input data to be a list of serializable
                and hashes them as cache keys using `hash_func`.
            transform: transforms to execute operations on input data.
            cache_dir: if specified, this is the location for persistent storage
                of pre-computed transformed data tensors. The cache_dir is computed once, and
                persists on disk until explicitly removed.  Different runs, programs, experiments
                may share a common cache dir provided that the transforms pre-processing is consistent.
                If the cache_dir doesn't exist, will automatically create it. Defaults to "./cache".
            hash_func: a callable to compute hash from data items to be cached.
                defaults to `monai.data.utils.pickle_hashing`.
            db_name: lmdb database file name. Defaults to "monai_cache".
            progress: whether to display a progress bar.
            pickle_protocol: specifies pickle protocol when saving, with `torch.save`.
                Defaults to torch.serialization.DEFAULT_PROTOCOL. For more details, please check:
                https://pytorch.org/docs/stable/generated/torch.save.html#torch.save.
            hash_transform: a callable to compute hash from the transform information when caching.
                This may reduce errors due to transforms changing during experiments. Default to None (no hash).
                Other options are `pickle_hashing` and `json_hashing` functions from `monai.data.utils`.
            reset_ops_id: whether to set `TraceKeys.ID` to ``Tracekeys.NONE``, defaults to ``True``.
                When this is enabled, the traced transform instance IDs will be removed from the cached MetaTensors.
                This is useful for skipping the transform instance checks when inverting applied operations
                using the cached content and with re-created transform instances.
            lmdb_kwargs: additional keyword arguments to the lmdb environment.
                for more details please visit: https://lmdb.readthedocs.io/en/release/#environment-class
        """
        super().__init__(
            data=data,
            transform=transform,
            cache_dir=cache_dir,
            hash_func=hash_func,
            pickle_protocol=pickle_protocol,
            hash_transform=hash_transform,
            reset_ops_id=reset_ops_id,
        )
        self.progress = progress
        if not self.cache_dir:
            raise ValueError("cache_dir must be specified.")
        self.db_file = self.cache_dir / f"{db_name}.lmdb"
        self.lmdb_kwargs = lmdb_kwargs or {}
        if not self.lmdb_kwargs.get("map_size", 0):
            self.lmdb_kwargs["map_size"] = 1024**4  # default map_size
        # lmdb is single-writer multi-reader by default