Skip to content

ImageDataset

ImageDataset loads and saves image data using the Pillow library.

kedro_datasets.pillow.ImageDataset 

ImageDataset(
    *,
    filepath,
    save_args=None,
    version=None,
    credentials=None,
    fs_args=None,
    metadata=None
)

Bases: AbstractVersionedDataset[Image, Image]

ImageDataset loads/saves image data as numpy from an underlying filesystem (e.g.: local, S3, GCS). It uses Pillow to handle image file.

Examples:

Using the Python API:

>>> from PIL import Image
>>> import tempfile
>>> from kedro_datasets.pillow import ImageDataset
>>>
>>> tmp = tempfile.NamedTemporaryFile(suffix=".jpg", delete=False)
>>> img = Image.new("RGB", (10, 10), color="red")
>>> img.save(tmp.name)
>>> tmp.close()
>>>
>>> dataset = ImageDataset(filepath=tmp.name)
>>> loaded_img = dataset.load()
>>> loaded_img.size
(10, 10)

Parameters:

  • filepath (str) –

    Filepath in POSIX format to an image file prefixed with a protocol like s3://. If prefix is not provided, file protocol (local filesystem) will be used. The prefix should be any protocol supported by fsspec. Note: http(s) doesn't support versioning.

  • save_args (dict[str, Any] | None, default: None ) –

    Pillow options for saving image files. Here you can find all available arguments: https://pillow.readthedocs.io/en/stable/reference/Image.html#PIL.Image.Image.save All defaults are preserved.

  • version (Version | None, default: None ) –

    If specified, should be an instance of kedro.io.core.Version. If its load attribute is None, the latest version will be loaded. If its save attribute is None, save version will be autogenerated.

  • credentials (dict[str, Any] | None, default: None ) –

    Credentials required to get access to the underlying filesystem. E.g. for GCSFileSystem it should look like {"token": None}.

  • fs_args (dict[str, Any] | None, default: None ) –

    Extra arguments to pass into underlying filesystem class constructor (e.g. {"project": "my-project"} for GCSFileSystem), as well as to pass to the filesystem's open method through nested keys open_args_load and open_args_save. Here you can find all available arguments for open: https://filesystem-spec.readthedocs.io/en/latest/api.html#fsspec.spec.AbstractFileSystem.open All defaults are preserved, except mode, which is set to wb when saving.

  • metadata (dict[str, Any] | None, default: None ) –

    Any arbitrary metadata. This is ignored by Kedro, but may be consumed by users or external plugins.

Source code in kedro_datasets/pillow/image_dataset.py 
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
def __init__(  # noqa: PLR0913
    self,
    *,
    filepath: str,
    save_args: dict[str, Any] | None = None,
    version: Version | None = None,
    credentials: dict[str, Any] | None = None,
    fs_args: dict[str, Any] | None = None,
    metadata: dict[str, Any] | None = None,
) -> None:
    """Creates a new instance of ``ImageDataset`` pointing to a concrete image file
    on a specific filesystem.

    Args:
        filepath: Filepath in POSIX format to an image file prefixed with a protocol like
            `s3://`. If prefix is not provided, `file` protocol (local filesystem) will be used.
            The prefix should be any protocol supported by ``fsspec``.
            Note: `http(s)` doesn't support versioning.
        save_args: Pillow options for saving image files.
            Here you can find all available arguments:
            https://pillow.readthedocs.io/en/stable/reference/Image.html#PIL.Image.Image.save
            All defaults are preserved.
        version: If specified, should be an instance of
            ``kedro.io.core.Version``. If its ``load`` attribute is
            None, the latest version will be loaded. If its ``save``
            attribute is None, save version will be autogenerated.
        credentials: Credentials required to get access to the underlying filesystem.
            E.g. for ``GCSFileSystem`` it should look like `{"token": None}`.
        fs_args: Extra arguments to pass into underlying filesystem class constructor
            (e.g. `{"project": "my-project"}` for ``GCSFileSystem``), as well as
            to pass to the filesystem's `open` method through nested keys
            `open_args_load` and `open_args_save`.
            Here you can find all available arguments for `open`:
            https://filesystem-spec.readthedocs.io/en/latest/api.html#fsspec.spec.AbstractFileSystem.open
            All defaults are preserved, except `mode`, which is set to `wb` when saving.
        metadata: Any arbitrary metadata.
            This is ignored by Kedro, but may be consumed by users or external plugins.
    """
    _fs_args = deepcopy(fs_args) or {}
    _fs_open_args_load = _fs_args.pop("open_args_load", {})
    _fs_open_args_save = _fs_args.pop("open_args_save", {})
    _credentials = deepcopy(credentials) or {}

    protocol, path = get_protocol_and_path(filepath, version)
    if protocol == "file":
        _fs_args.setdefault("auto_mkdir", True)

    self._protocol = protocol
    self._fs = fsspec.filesystem(self._protocol, **_credentials, **_fs_args)

    self.metadata = metadata

    super().__init__(
        filepath=PurePosixPath(path),
        version=version,
        exists_function=self._fs.exists,
        glob_function=self._fs.glob,
    )

    # Handle default save and fs arguments
    self._save_args = {**self.DEFAULT_SAVE_ARGS, **(save_args or {})}
    self._fs_open_args_load = {
        **self.DEFAULT_FS_ARGS.get("open_args_load", {}),
        **(_fs_open_args_load or {}),
    }
    self._fs_open_args_save = {
        **self.DEFAULT_FS_ARGS.get("open_args_save", {}),
        **(_fs_open_args_save or {}),
    }

DEFAULT_FS_ARGS class-attribute instance-attribute 

DEFAULT_FS_ARGS = {'open_args_save': {'mode': 'wb'}}

DEFAULT_SAVE_ARGS class-attribute instance-attribute 

DEFAULT_SAVE_ARGS = {}

_fs instance-attribute 

_fs = filesystem(_protocol, **_credentials, **_fs_args)

_fs_open_args_load instance-attribute 

_fs_open_args_load = {
    None: get("open_args_load", {}),
    None: _fs_open_args_load or {},
}

_fs_open_args_save instance-attribute 

_fs_open_args_save = {
    None: get("open_args_save", {}),
    None: _fs_open_args_save or {},
}

_protocol instance-attribute 

_protocol = protocol

_save_args instance-attribute 

_save_args = {
    None: DEFAULT_SAVE_ARGS,
    None: save_args or {},
}

metadata instance-attribute 

metadata = metadata

_describe 

_describe()
Source code in kedro_datasets/pillow/image_dataset.py 
118
119
120
121
122
123
124
def _describe(self) -> dict[str, Any]:
    return {
        "filepath": self._filepath,
        "protocol": self._protocol,
        "save_args": self._save_args,
        "version": self._version,
    }

_exists 

_exists()
Source code in kedro_datasets/pillow/image_dataset.py 
149
150
151
152
153
154
155
def _exists(self) -> bool:
    try:
        load_path = get_filepath_str(self._get_load_path(), self._protocol)
    except DatasetError:
        return False

    return self._fs.exists(load_path)

_get_format staticmethod 

_get_format(file_path)
Source code in kedro_datasets/pillow/image_dataset.py 
142
143
144
145
146
147
@staticmethod
def _get_format(file_path: PurePosixPath):
    ext = file_path.suffix.lower()
    if ext not in Image.EXTENSION:
        Image.init()
    return Image.EXTENSION.get(ext)

_invalidate_cache 

_invalidate_cache()

Invalidate underlying filesystem caches.

Source code in kedro_datasets/pillow/image_dataset.py 
161
162
163
164
def _invalidate_cache(self) -> None:
    """Invalidate underlying filesystem caches."""
    filepath = get_filepath_str(self._filepath, self._protocol)
    self._fs.invalidate_cache(filepath)

_release 

_release()
Source code in kedro_datasets/pillow/image_dataset.py 
157
158
159
def _release(self) -> None:
    super()._release()
    self._invalidate_cache()

load 

load()
Source code in kedro_datasets/pillow/image_dataset.py 
126
127
128
129
130
def load(self) -> Image.Image:
    load_path = get_filepath_str(self._get_load_path(), self._protocol)

    with self._fs.open(load_path, **self._fs_open_args_load) as fs_file:
        return Image.open(fs_file).copy()

save 

save(data)
Source code in kedro_datasets/pillow/image_dataset.py 
132
133
134
135
136
137
138
139
140
def save(self, data: Image.Image) -> None:
    save_path = self._get_save_path()

    with self._fs.open(
        get_filepath_str(save_path, self._protocol), **self._fs_open_args_save
    ) as fs_file:
        data.save(fs_file, format=self._get_format(save_path), **self._save_args)

    self._invalidate_cache()
Copyright © Kedro, a Series of LF Projects, LLC