dev(narugo): add more docs (d8e0a9cd) · Commits · git-mirror / Imgutils

docs/source/api_doc/preprocess/pillow.rst

+4 −4

Original line number	Diff line number	Diff line
		@@ -13,17 +13,17 @@ register_pillow_transform



		create_pillow_transforms
		register_pillow_parse
		------------------------------------------------------------------------

		.. autofunction:: create_pillow_transforms
		.. autofunction:: register_pillow_parse



		register_pillow_parse
		create_pillow_transforms
		------------------------------------------------------------------------

		.. autofunction:: register_pillow_parse
		.. autofunction:: create_pillow_transforms

docs/source/api_doc/preprocess/torchvision.rst

+4 −4

Original line number	Diff line number	Diff line
		@@ -13,17 +13,17 @@ register_torchvision_transform



		create_torchvision_transforms
		register_torchvision_parse
		------------------------------------------------------------------------

		.. autofunction:: create_torchvision_transforms
		.. autofunction:: register_torchvision_parse



		register_torchvision_parse
		create_torchvision_transforms
		------------------------------------------------------------------------

		.. autofunction:: register_torchvision_parse
		.. autofunction:: create_torchvision_transforms

imgutils/preprocess/pillow.py

+79 −4

Original line number	Diff line number	Diff line
		@@ -285,7 +285,6 @@ class PillowCenterCrop:
		Initialize the PillowCenterCrop instance.

		:param size: The target size for cropping.
		:type size: Union[int, Tuple[int, int], List[int]]
		"""
		if isinstance(size, int):
		# noinspection PyTypeChecker
		@@ -546,9 +545,7 @@ class PillowNormalize:
		Normalizes an image by subtracting the mean and dividing by the standard deviation.

		:param mean: The mean value(s) for normalization.
		:type mean: np.ndarray
		:param std: The standard deviation value(s) for normalization.
		:type std: np.ndarray
		:param inplace: If True, perform normalization in-place.
		:type inplace: bool
		"""
		@@ -703,6 +700,36 @@ def create_pillow_transforms(tvalue: Union[list, dict]):
		:return: A transformation or a composition of transformations.
		:rtype: Union[PillowCompose, Any]
		:raises TypeError: If the input value is not a list or dictionary.

		:example:
		>>> from imgutils.preprocess import create_pillow_transforms
		>>>
		>>> create_pillow_transforms({
		... 'type': 'resize',
		... 'size': 384,
		... 'interpolation': 'bicubic',
		... })
		PillowResize(size=384, interpolation=bicubic, max_size=None, antialias=True)
		>>> create_pillow_transforms({
		... 'type': 'resize',
		... 'size': (224, 256),
		... 'interpolation': 'bilinear',
		... })
		PillowResize(size=(224, 256), interpolation=bilinear, max_size=None, antialias=True)
		>>> create_pillow_transforms({'type': 'center_crop', 'size': 224})
		PillowCenterCrop(size=(224, 224))
		>>> create_pillow_transforms({'type': 'to_tensor'})
		PillowToTensor()
		>>> create_pillow_transforms({'type': 'maybe_to_tensor'})
		PillowMaybeToTensor()
		>>> create_pillow_transforms({'type': 'normalize', 'mean': 0.5, 'std': 0.5})
		PillowNormalize(mean=[0.5], std=[0.5])
		>>> create_pillow_transforms({
		... 'type': 'normalize',
		... 'mean': [0.485, 0.456, 0.406],
		... 'std': [0.229, 0.224, 0.225],
		... })
		PillowNormalize(mean=[0.485 0.456 0.406], std=[0.229 0.224 0.225])
		"""
		if isinstance(tvalue, list):
		return PillowCompose([create_pillow_transforms(titem) for titem in tvalue])
		@@ -719,10 +746,58 @@ def parse_pillow_transforms(value):
		Parse transformations into a serializable format.

		:param value: The transformation or composition to parse.
		:type value: Union[PillowCompose, Any]
		:type value: Any
		:return: A serializable representation of the transformation.
		:rtype: Union[list, dict]
		:raises TypeError: If the transformation cannot be parsed.

		:example:
		>>> from PIL import Image
		>>>
		>>> from imgutils.preprocess import parse_pillow_transforms
		>>> from imgutils.preprocess.pillow import PillowResize, PillowCenterCrop, PillowMaybeToTensor, PillowToTensor, \
		... PillowNormalize
		>>>
		>>> parse_pillow_transforms(PillowResize(
		... size=384,
		... interpolation=Image.BICUBIC,
		... ))
		{'type': 'resize', 'size': 384, 'interpolation': 'bicubic', 'max_size': None, 'antialias': True}
		>>> parse_pillow_transforms(PillowResize(
		... size=(224, 256),
		... interpolation=Image.BILINEAR,
		... ))
		{'type': 'resize', 'size': (224, 256), 'interpolation': 'bilinear', 'max_size': None, 'antialias': True}
		>>> parse_pillow_transforms(PillowCenterCrop(size=224))
		{'type': 'center_crop', 'size': [224, 224]}
		>>> parse_pillow_transforms(PillowToTensor())
		{'type': 'to_tensor'}
		>>> parse_pillow_transforms(PillowMaybeToTensor())
		{'type': 'maybe_to_tensor'}
		>>> parse_pillow_transforms(PillowNormalize(mean=0.5, std=0.5))
		{'type': 'normalize', 'mean': [0.5], 'std': [0.5]}
		>>> parse_pillow_transforms(PillowNormalize(
		... mean=[0.485, 0.456, 0.406],
		... std=[0.229, 0.224, 0.225],
		... ))
		{'type': 'normalize', 'mean': [0.48500001430511475, 0.4560000002384186, 0.4059999883174896], 'std': [0.2290000021457672, 0.2240000069141388, 0.22499999403953552]}
		>>> parse_pillow_transforms(PillowCompose([
		... PillowResize(
		... size=384,
		... interpolation=Image.BICUBIC,
		... ),
		... PillowCenterCrop(size=224),
		... PillowMaybeToTensor(),
		... PillowNormalize(mean=0.5, std=0.5),
		... ]))
		[{'antialias': True,
		'interpolation': 'bicubic',
		'max_size': None,
		'size': 384,
		'type': 'resize'},
		{'size': [224, 224], 'type': 'center_crop'},
		{'type': 'maybe_to_tensor'},
		{'mean': [0.5], 'std': [0.5], 'type': 'normalize'}]
		"""
		if isinstance(value, PillowCompose):
		return [parse_pillow_transforms(trans) for trans in value.transforms]

imgutils/preprocess/torchvision.py

+88 −2

Original line number	Diff line number	Diff line
		@@ -310,8 +310,8 @@ def _parse_normalize(obj):

		obj: Normalize
		return {
		'mean': obj.mean.tolist(),
		'std': obj.std.tolist(),
		'mean': obj.mean.tolist() if hasattr(obj.mean, 'tolist') else obj.mean,
		'std': obj.std.tolist() if hasattr(obj.std, 'tolist') else obj.std,
		}


		@@ -322,6 +322,45 @@ def create_torchvision_transforms(tvalue: Union[list, dict]):
		:param tvalue: Transform configuration as list or dict
		:return: Composed transforms or single transform
		:raises TypeError: If tvalue has unsupported type

		:example:
		>>> from imgutils.preprocess import create_torchvision_transforms
		>>>
		>>> create_torchvision_transforms({
		... 'type': 'resize',
		... 'size': 384,
		... 'interpolation': 'bicubic',
		... })
		Resize(size=384, interpolation=bicubic, max_size=None, antialias=True)
		>>> create_torchvision_transforms({
		... 'type': 'resize',
		... 'size': (224, 256),
		... 'interpolation': 'bilinear',
		... })
		Resize(size=(224, 256), interpolation=bilinear, max_size=None, antialias=True)
		>>> create_torchvision_transforms({'type': 'center_crop', 'size': 224})
		CenterCrop(size=(224, 224))
		>>> create_torchvision_transforms({'type': 'to_tensor'})
		ToTensor()
		>>> create_torchvision_transforms({'type': 'maybe_to_tensor'})
		MaybeToTensor()
		>>> create_torchvision_transforms({'type': 'normalize', 'mean': 0.5, 'std': 0.5})
		Normalize(mean=0.5, std=0.5)
		>>> create_torchvision_transforms({
		... 'type': 'normalize',
		... 'mean': [0.485, 0.456, 0.406],
		... 'std': [0.229, 0.224, 0.225],
		... })
		Normalize(mean=tensor([0.4850, 0.4560, 0.4060]), std=tensor([0.2290, 0.2240, 0.2250]))

		.. note::
		Currently the following transforms are supported:

		- `torchvision.transforms.Resize`
		- `torchvision.transforms.CenterCrop`
		- `torchvision.transforms.ToTensor`
		- `timm.data.MaybeToTensor`
		- `torchvision.transforms.Normalize`
		"""
		_check_torchvision()

		@@ -343,6 +382,53 @@ def parse_torchvision_transforms(value):
		:param value: Transform object to parse
		:return: Transform configuration as list or dict
		:raises TypeError: If transform type is not supported

		:example:
		>>> from timm.data import MaybeToTensor
		>>> from torchvision.transforms import Resize, InterpolationMode, CenterCrop, ToTensor, Normalize
		>>>
		>>> from imgutils.preprocess import parse_torchvision_transforms
		>>>
		>>> parse_torchvision_transforms(Resize(
		... size=384,
		... interpolation=InterpolationMode.BICUBIC,
		... ))
		{'type': 'resize', 'size': 384, 'interpolation': 'bicubic', 'max_size': None, 'antialias': True}
		>>> parse_torchvision_transforms(Resize(
		... size=(224, 256),
		... interpolation=InterpolationMode.BILINEAR,
		... ))
		{'type': 'resize', 'size': (224, 256), 'interpolation': 'bilinear', 'max_size': None, 'antialias': True}
		>>> parse_torchvision_transforms(CenterCrop(size=224))
		{'type': 'center_crop', 'size': (224, 224)}
		>>> parse_torchvision_transforms(ToTensor())
		{'type': 'to_tensor'}
		>>> parse_torchvision_transforms(MaybeToTensor())
		{'type': 'maybe_to_tensor'}
		>>> parse_torchvision_transforms(Normalize(mean=0.5, std=0.5))
		{'type': 'normalize', 'mean': 0.5, 'std': 0.5}
		>>> parse_torchvision_transforms(Normalize(
		... mean=[0.485, 0.456, 0.406],
		... std=[0.229, 0.224, 0.225],
		... ))
		{'type': 'normalize', 'mean': [0.485, 0.456, 0.406], 'std': [0.229, 0.224, 0.225]}
		>>> parse_torchvision_transforms(Compose([
		... Resize(
		... size=384,
		... interpolation=Image.BICUBIC,
		... ),
		... CenterCrop(size=224),
		... MaybeToTensor(),
		... Normalize(mean=0.5, std=0.5),
		... ]))
		[{'antialias': True,
		'interpolation': 'bicubic',
		'max_size': None,
		'size': 384,
		'type': 'resize'},
		{'size': (224, 224), 'type': 'center_crop'},
		{'type': 'maybe_to_tensor'},
		{'mean': 0.5, 'std': 0.5, 'type': 'normalize'}]
		"""
		_check_torchvision()