Move image classes

CHANGELOG.md

@@ -26,7 +26,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   (<https://github.com/openvinotoolkit/datumaro/pull/534>)
 
 ### Deprecated
-- TBD
+- Using `Image`, `ByteImage` from `datumaro.util.image` - these classes
+  are moved to `datumaro.components.media`
+  (<https://github.com/openvinotoolkit/datumaro/pull/538>)
 
 ### Removed
 - TBD

datumaro/components/converter.py

@@ -12,7 +12,7 @@
 from datumaro.components.cli_plugin import CliPlugin
 from datumaro.components.dataset import DatasetPatch
 from datumaro.components.extractor import DatasetItem
-from datumaro.util.image import Image
+from datumaro.components.media import Image
 from datumaro.util.os_util import rmtree
 from datumaro.util.scope import on_error_do, scoped
 

datumaro/components/extractor.py

@@ -19,9 +19,9 @@
 from datumaro.components.format_detection import (
     FormatDetectionConfidence, FormatDetectionContext,
 )
+from datumaro.components.media import Image
 from datumaro.util import is_method_redefined
 from datumaro.util.attrs_util import default_if_none, not_empty
-from datumaro.util.image import Image
 
 # Re-export some names from .annotation for backwards compatibility.
 import datumaro.components.annotation # isort:skip

datumaro/components/media.py

@@ -0,0 +1,180 @@
+# Copyright (C) 2021 Intel Corporation
+#
+# SPDX-License-Identifier: MIT
+
+from typing import Callable, Optional, Tuple, Union
+import os
+import os.path as osp
+import shutil
+
+import numpy as np
+
+from datumaro.util.image import (
+    _image_loading_errors, decode_image, lazy_image, save_image,
+)
+
+
+class MediaElement:
+    def __init__(self, path: str) -> None:
+        self._path = path
+
+    @property
+    def path(self) -> str:
+        """Path to the media file"""
+        return self._path
+
+    @property
+    def ext(self) -> str:
+        """Media file extension"""
+        return osp.splitext(osp.basename(self.path))[1]
+
+    def __eq__(self, other: object) -> bool:
+        # We need to compare exactly with this type
+        if type(other) is not __class__: # pylint: disable=unidiomatic-typecheck
+            return False
+        return self._path == other._path
+
+class Image(MediaElement):
+    def __init__(self,
+            data: Union[np.ndarray, Callable[[str], np.ndarray], None] = None,
+            *,
+            path: Optional[str] = None,
+            size: Optional[Tuple[int, int]] = None):
+        assert size is None or len(size) == 2, size
+        if size is not None:
+            assert len(size) == 2 and 0 < size[0] and 0 < size[1], size
+            size = tuple(map(int, size))
+        self._size = size # (H, W)
+        if not self._size and isinstance(data, np.ndarray):
+            self._size = data.shape[:2]
+
+        assert path is None or isinstance(path, str), path
+        if path is None:
+            path = ''
+        elif path:
+            path = osp.abspath(path).replace('\\', '/')
+        self._path = path
+
+        if not isinstance(data, np.ndarray):
+            assert path or callable(data), "Image can not be empty"
+            assert data is None or callable(data)
+            if path and osp.isfile(path) or data:
+                data = lazy_image(path, loader=data)
+        self._data = data
+
+    @property
+    def data(self) -> np.ndarray:
+        """Image data in BGR HWC [0; 255] (float) format"""
+
+        if callable(self._data):
+            data = self._data()
+        else:
+            data = self._data
+
+        if self._size is None and data is not None:
+            self._size =  tuple(map(int, data.shape[:2]))
+        return data
+
+    @property
+    def has_data(self) -> bool:
+        return self._data is not None
+
+    @property
+    def has_size(self) -> bool:
+        return self._size is not None or isinstance(self._data, np.ndarray)
+
+    @property
+    def size(self) -> Optional[Tuple[int, int]]:
+        """Returns (H, W)"""
+
+        if self._size is None:
+            try:
+                data = self.data
+            except _image_loading_errors:
+                return None
+            if data is not None:
+                self._size = tuple(map(int, data.shape[:2]))
+        return self._size
+
+    def __eq__(self, other):
+        if isinstance(other, np.ndarray):
+            return self.has_data and np.array_equal(self.data, other)
+
+        if not isinstance(other, __class__):
+            return False
+        return \
+            (np.array_equal(self.size, other.size)) and \
+            (self.has_data == other.has_data) and \
+            (self.has_data and np.array_equal(self.data, other.data) or \
+                not self.has_data)
+
+    def save(self, path):
+        cur_path = osp.abspath(self.path)
+        path = osp.abspath(path)
+
+        cur_ext = self.ext.lower()
+        new_ext = osp.splitext(osp.basename(path))[1].lower()
+
+        os.makedirs(osp.dirname(path), exist_ok=True)
+        if cur_ext == new_ext and osp.isfile(cur_path):
+            if cur_path != path:
+                shutil.copyfile(cur_path, path)
+        else:
+            save_image(path, self.data)
+
+class ByteImage(Image):
+    def __init__(self,
+            data: Union[bytes, Callable[[str], bytes], None] = None,
+            *,
+            path: Optional[str] = None,
+            ext: Optional[str] = None,
+            size: Optional[Tuple[int, int]] = None):
+        if not isinstance(data, bytes):
+            assert path or callable(data), "Image can not be empty"
+            assert data is None or callable(data)
+            if path and osp.isfile(path) or data:
+                data = lazy_image(path, loader=data)
+
+        super().__init__(path=path, size=size,
+            data=lambda _: decode_image(self.get_bytes()))
+        if data is None:
+            # We don't expect decoder to produce images from nothing,
+            # otherwise using this class makes no sense. We undefine
+            # data to avoid using default image loader for loading binaries
+            # from the path, when no data is provided.
+            self._data = None
+
+        self._bytes_data = data
+        if ext:
+            ext = ext.lower()
+            if not ext.startswith('.'):
+                ext = '.' + ext
+        self._ext = ext
+
+    def get_bytes(self):
+        if callable(self._bytes_data):
+            return self._bytes_data()
+        return self._bytes_data
+
+    @property
+    def ext(self):
+        if self._ext:
+            return self._ext
+        return super().ext
+
+    def save(self, path):
+        cur_path = osp.abspath(self.path)
+        path = osp.abspath(path)
+
+        cur_ext = self.ext.lower()
+        new_ext = osp.splitext(osp.basename(path))[1].lower()
+
+        os.makedirs(osp.dirname(path), exist_ok=True)
+        if cur_ext == new_ext and osp.isfile(cur_path):
+            if cur_path != path:
+                shutil.copyfile(cur_path, path)
+        elif cur_ext == new_ext:
+            with open(path, 'wb') as f:
+                f.write(self.get_bytes())
+        else:
+            save_image(path, self.data)

datumaro/plugins/coco_format/extractor.py

@@ -17,7 +17,8 @@
 from datumaro.components.extractor import (
     DEFAULT_SUBSET_NAME, DatasetItem, SourceExtractor,
 )
-from datumaro.util.image import Image, lazy_image, load_image
+from datumaro.components.media import Image
+from datumaro.util.image import lazy_image, load_image
 from datumaro.util.mask_tools import bgr2index
 from datumaro.util.os_util import suppress_output
 

datumaro/plugins/cvat_format/extractor.py

@@ -11,7 +11,7 @@
     AnnotationType, Bbox, Label, LabelCategories, Points, Polygon, PolyLine,
 )
 from datumaro.components.extractor import DatasetItem, Importer, SourceExtractor
-from datumaro.util.image import Image
+from datumaro.components.media import Image
 
 from .format import CvatPath
 

datumaro/plugins/datumaro_format/extractor.py

@@ -10,7 +10,7 @@
     MaskCategories, Points, PointsCategories, Polygon, PolyLine, RleMask,
 )
 from datumaro.components.extractor import DatasetItem, Importer, SourceExtractor
-from datumaro.util.image import Image
+from datumaro.components.media import Image
 
 from .format import DatumaroPath
 

datumaro/plugins/image_zip_format.py

@@ -10,8 +10,9 @@
 
 from datumaro.components.converter import Converter
 from datumaro.components.extractor import DatasetItem, Importer, SourceExtractor
+from datumaro.components.media import ByteImage
 from datumaro.util import parse_str_enum_value
-from datumaro.util.image import IMAGE_EXTENSIONS, ByteImage, encode_image
+from datumaro.util.image import IMAGE_EXTENSIONS, encode_image
 
 
 class Compression(Enum):

datumaro/plugins/labelme_format.py

@@ -17,8 +17,9 @@
 )
 from datumaro.components.converter import Converter
 from datumaro.components.extractor import DatasetItem, Extractor, Importer
+from datumaro.components.media import Image
 from datumaro.util import cast, escape, unescape
-from datumaro.util.image import Image, save_image
+from datumaro.util.image import save_image
 from datumaro.util.mask_tools import find_mask_bbox, load_mask
 from datumaro.util.os_util import split_path
 

datumaro/plugins/mot_format.py

@@ -16,8 +16,9 @@
 from datumaro.components.annotation import AnnotationType, Bbox, LabelCategories
 from datumaro.components.converter import Converter
 from datumaro.components.extractor import DatasetItem, Importer, SourceExtractor
+from datumaro.components.media import Image
 from datumaro.util import cast
-from datumaro.util.image import Image, find_images
+from datumaro.util.image import find_images
 
 MotLabel = Enum('MotLabel', [
     ('pedestrian', 1),

datumaro/plugins/open_images_format.py

@@ -28,10 +28,11 @@
     DatasetError, RepeatedItemError, UndefinedLabel,
 )
 from datumaro.components.extractor import DatasetItem, Extractor, Importer
+from datumaro.components.media import Image
 from datumaro.components.validator import Severity
 from datumaro.util.annotation_util import find_instances
 from datumaro.util.image import (
-    DEFAULT_IMAGE_META_FILE_NAME, Image, find_images, lazy_image, load_image,
+    DEFAULT_IMAGE_META_FILE_NAME, find_images, lazy_image, load_image,
     load_image_meta_file, save_image, save_image_meta_file,
 )
 from datumaro.util.os_util import make_file_name, split_path

datumaro/plugins/tf_detection_api_format/converter.py

@@ -12,10 +12,11 @@
 
 from datumaro.components.annotation import AnnotationType, LabelCategories
 from datumaro.components.converter import Converter
+from datumaro.components.media import ByteImage
 from datumaro.util.annotation_util import (
     find_group_leader, find_instances, max_bbox,
 )
-from datumaro.util.image import ByteImage, encode_image
+from datumaro.util.image import encode_image
 from datumaro.util.mask_tools import merge_masks
 from datumaro.util.tf_util import import_tf as _import_tf
 

datumaro/plugins/tf_detection_api_format/extractor.py

@@ -12,7 +12,8 @@
     AnnotationType, Bbox, LabelCategories, Mask,
 )
 from datumaro.components.extractor import DatasetItem, Importer, SourceExtractor
-from datumaro.util.image import ByteImage, decode_image, lazy_image
+from datumaro.components.media import ByteImage
+from datumaro.util.image import decode_image, lazy_image
 from datumaro.util.tf_util import import_tf as _import_tf
 
 from .format import DetectionApiPath

datumaro/plugins/voc_format/extractor.py

@@ -12,7 +12,8 @@
     AnnotationType, Bbox, CompiledMask, Label, Mask,
 )
 from datumaro.components.extractor import DatasetItem, SourceExtractor
-from datumaro.util.image import Image, find_images
+from datumaro.components.media import Image
+from datumaro.util.image import find_images
 from datumaro.util.mask_tools import invert_colormap, lazy_mask
 
 from .format import (

datumaro/plugins/yolo_format/extractor.py

@@ -10,8 +10,9 @@
 from datumaro.components.extractor import (
     DatasetItem, Extractor, Importer, SourceExtractor,
 )
+from datumaro.components.media import Image
 from datumaro.util.image import (
-    DEFAULT_IMAGE_META_FILE_NAME, Image, load_image_meta_file,
+    DEFAULT_IMAGE_META_FILE_NAME, load_image_meta_file,
 )
 from datumaro.util.os_util import split_path