Hugging Face 的 LOGO

Transformers 文档

图像处理器工具

Hugging Face's logo
加入 Hugging Face 社区

并获得增强的文档体验

开始使用

图像处理器工具

此页面列出了图像处理器使用过的所有实用工具函数，主要是用于处理图像的功能性变换。

其中大部分仅在您研究库中图像处理器的代码时才有用。

图像变换

transformers.image_transforms.center_crop

< >

( image: ndarray size: tuple data_format: str | transformers.image_utils.ChannelDimension | None = None input_data_format: str | transformers.image_utils.ChannelDimension | None = None ) → np.ndarray

参数

  • image (np.ndarray) — 要裁剪的图像。
  • size (tuple[int, int]) — 裁剪后图像的目标尺寸。
  • data_format (str 或 ChannelDimension, 可选) — 输出图像的通道维度格式。可以是以下之一：
    • "channels_first" 或 ChannelDimension.FIRST: 图像格式为 (num_channels, height, width)。
    • "channels_last" 或 ChannelDimension.LAST: 图像格式为 (height, width, num_channels)。如果未设置，将使用输入图像推断出的格式。
  • input_data_format (str 或 ChannelDimension, 可选) — 输入图像的通道维度格式。可以是以下之一：
    • "channels_first" 或 ChannelDimension.FIRST: 图像格式为 (num_channels, height, width)。
    • "channels_last" 或 ChannelDimension.LAST: 图像格式为 (height, width, num_channels)。如果未设置，将使用输入图像推断出的格式。

返回

np.ndarray

裁剪后的图像。

使用中心裁剪将image裁剪到指定的size。请注意，如果图像太小而无法裁剪到给定大小，则会进行填充（因此返回的结果将始终是size的大小）。

transformers.image_transforms.center_to_corners_format

< >

( bboxes_center: TensorType )

将边界框从中心格式转换为角点格式。

中心格式：包含框的中心坐标及其宽度、高度维度 (center_x, center_y, width, height) 角点格式：包含框的左上角和右下角坐标 (top_left_x, top_left_y, bottom_right_x, bottom_right_y)

transformers.image_transforms.corners_to_center_format

< >

( bboxes_corners: TensorType )

将边界框从角点格式转换为中心格式。

角点格式：包含框的左上角和右下角坐标 (top_left_x, top_left_y, bottom_right_x, bottom_right_y) 中心格式：包含框的中心坐标及其宽度、高度维度 (center_x, center_y, width, height)

transformers.image_transforms.id_to_rgb

< >

( id_map )

将唯一 ID 转换为 RGB 颜色。

transformers.image_transforms.normalize

< >

( image: ndarray mean: float | collections.abc.Collection[float] std: float | collections.abc.Collection[float] data_format: transformers.image_utils.ChannelDimension | None = None input_data_format: str | transformers.image_utils.ChannelDimension | None = None )

参数

  • image (np.ndarray) — 要标准化的图像。
  • mean (float 或 Collection[float]) — 标准化要使用的平均值。
  • std (float 或 Collection[float]) — 标准化要使用的标准差。
  • data_format (ChannelDimension, 可选) — 输出图像的通道维度格式。如果未设置，将使用从输入推断出的格式。
  • input_data_format (ChannelDimension, 可选) — 输入图像的通道维度格式。如果未设置，将使用从输入推断出的格式。

使用指定的mean和std对image进行标准化。

image = (image - mean) / std

transformers.image_transforms.pad

< >

( image: ndarray padding: int | tuple[int, int] | collections.abc.Iterable[tuple[int, int]] mode: PaddingMode = <PaddingMode.CONSTANT: 'constant'> constant_values: float | collections.abc.Iterable[float] = 0.0 data_format: str | transformers.image_utils.ChannelDimension | None = None input_data_format: str | transformers.image_utils.ChannelDimension | None = None ) → np.ndarray

参数

  • image (np.ndarray) — 要填充的图像。
  • padding (int 或 tuple[int, int] 或 Iterable[tuple[int, int]]) — 要应用于高度、宽度轴的边缘的填充。可以是以下三种格式之一：
    • ((before_height, after_height), (before_width, after_width))：每个轴有不同的前后填充宽度。
    • ((before, after),)：为高度和宽度提供相同的之前和之后填充。
    • (pad,) 或 int：是所有轴的之前 = 之后 = 填充宽度的快捷方式。
  • mode (PaddingMode) — 要使用的填充模式。可以是以下之一：
    • "constant"：使用常量值进行填充。
    • "reflect"：使用向量在数组的每个轴上镜像反射值进行填充。
    • "replicate"：使用数组边缘的最后一个值进行复制填充。
    • "symmetric"：使用数组边缘镜像反射的向量进行填充。
  • constant_values (float 或 Iterable[float], 可选) — 如果mode为"constant"，则用于填充的值。
  • data_format (str 或 ChannelDimension, 可选) — 输出图像的通道维度格式。可以是以下之一：
    • "channels_first" 或 ChannelDimension.FIRST: 图像格式为 (num_channels, height, width)。
    • "channels_last" 或 ChannelDimension.LAST: 图像格式为 (height, width, num_channels)。如果未设置，将使用与输入图像相同的格式。
  • input_data_format (str 或 ChannelDimension, 可选) — 输入图像的通道维度格式。可以是以下之一：
    • "channels_first" 或 ChannelDimension.FIRST: 图像格式为 (num_channels, height, width)。
    • "channels_last" 或 ChannelDimension.LAST: 图像格式为 (height, width, num_channels)。如果未设置，将使用输入图像推断出的格式。

返回

np.ndarray

填充后的图像。

使用指定的padding和mode对image进行填充。

transformers.image_transforms.rgb_to_id

< >

( color )

将 RGB 颜色转换为唯一 ID。

transformers.image_transforms.rescale

< >

( image: ndarray scale: float data_format: transformers.image_utils.ChannelDimension | None = None dtype: dtype = <class 'numpy.float32'> input_data_format: str | transformers.image_utils.ChannelDimension | None = None ) → np.ndarray

参数

  • image (np.ndarray) — 要缩放的图像。
  • scale (float) — 用于缩放图像的比例。
  • data_format (ChannelDimension, optional) — 图像的通道维度格式。如果未提供，则与输入图像相同。
  • dtype (np.dtype, optional, defaults to np.float32) — 输出图像的 dtype。默认为 np.float32。用于向后兼容特征提取器。
  • input_data_format (ChannelDimension, optional) — 输入图像的通道维度格式。如果未提供，将从输入图像推断。

返回

np.ndarray

缩放后的图像。

使用 scale 缩放 image。

transformers.image_transforms.resize

< >

( image: ndarray size: tuple resample: typing.Optional[ForwardRef('PILImageResampling')] = None reducing_gap: int | None = None data_format: transformers.image_utils.ChannelDimension | None = None return_numpy: bool = True input_data_format: str | transformers.image_utils.ChannelDimension | None = None ) → np.ndarray

参数

  • image (np.ndarray) — 要调整大小的图像。
  • size (tuple[int, int]) — 用于调整图像大小的尺寸。
  • resample (int, optional, defaults to PILImageResampling.BILINEAR) — 用于重采样使用的过滤器。
  • reducing_gap (int, optional) — 通过分两步调整图像大小来优化。reducing_gap 越大，结果越接近公平重采样。有关更多详细信息，请参阅相应的 Pillow 文档。
  • data_format (ChannelDimension, optional) — 输出图像的通道维度格式。如果未设置，将使用从输入推断的格式。
  • return_numpy (bool, optional, defaults to True) — 是否将调整大小后的图像作为 numpy 数组返回。如果为 False，则返回 PIL.Image.Image 对象。
  • input_data_format (ChannelDimension, optional) — 输入图像的通道维度格式。如果未提供，将从输入图像推断。

返回

np.ndarray

调整大小后的图像。

使用 PIL 库将 image 调整为 size 指定的 (height, width)。

transformers.image_transforms.to_pil_image

< >

( image: typing.Union[numpy.ndarray, ForwardRef('PIL.Image.Image'), ForwardRef('torch.Tensor')] do_rescale: bool | None = None image_mode: str | None = None input_data_format: str | transformers.image_utils.ChannelDimension | None = None ) → PIL.Image.Image

参数

  • image (PIL.Image.Image or numpy.ndarray or torch.Tensor) — 要转换为 PIL.Image 格式的图像。
  • do_rescale (bool, optional) — 是否应用缩放因子（使像素值成为 0 到 255 之间的整数）。如果图像类型为浮点类型且转换为 int 会导致精度损失，则默认为 True，否则为 False。
  • image_mode (str, optional) — 用于 PIL 图像的模式。如果未设置，将使用输入图像类型的默认模式。
  • input_data_format (ChannelDimension, optional) — 输入图像的通道维度格式。如果未提供，将从输入图像推断。

返回

PIL.Image.Image

转换后的图像。

将 image 转换为 PIL 图像。可选地对其进行缩放，并在需要时将通道维度放回作为最后一个轴。

ImageProcessingMixin

class transformers.ImageProcessingMixin

< >

( **kwargs )

这是一个图像处理器 mixin，用于为顺序和图像特征提取器提供保存/加载功能。

fetch_images

< >

( image_url_or_urls: str | list[str] | list[list[str]] )

将单个或多个 URL 转换为相应的 PIL.Image 对象。

如果传入单个 URL，则返回值将是单个对象。如果传入列表，则返回对象列表。

from_dict

< >

( image_processor_dict: dict **kwargs ) → ImageProcessingMixin

参数

  • image_processor_dict (dict[str, Any]) — 将用于实例化图像处理器对象的字典。通过利用 to_dict() 方法，可以从预训练的检查点检索这样的字典。
  • kwargs (dict[str, Any]) — 用于实例化图像处理器对象的其他参数。

返回

ImageProcessingMixin

从这些参数实例化的图像处理器对象。

从 Python 字典参数实例化一种 ImageProcessingMixin。

from_json_file

< >

( json_file: str | os.PathLike ) → 类型为 ImageProcessingMixin 的图像处理器

参数

  • json_file (str or os.PathLike) — Path to the JSON file containing the parameters.

返回

A image processor of type ImageProcessingMixin

The image_processor object instantiated from that JSON file.

Instantiates a image processor of type ImageProcessingMixin from the path to a JSON file of parameters.

from_pretrained

< >

( pretrained_model_name_or_path: str | os.PathLike cache_dir: str | os.PathLike | None = None force_download: bool = False local_files_only: bool = False token: str | bool | None = None revision: str = 'main' **kwargs )

参数

  • pretrained_model_name_or_path (str or os.PathLike) — This can be either:

    • a string, the model id of a pretrained image_processor hosted inside a model repo on huggingface.co.
    • a path to a directory containing a image processor file saved using the save_pretrained() method, e.g., ./my_model_directory/.
    • a path or url to a saved image processor JSON file, e.g., ./my_model_directory/preprocessor_config.json.
  • cache_dir (str or os.PathLike, optional) — Path to a directory in which a downloaded pretrained model image processor should be cached if the standard cache should not be used.
  • force_download (bool, optional, defaults to False) — Whether or not to force to (re-)download the image processor files and override the cached versions if they exist.
  • proxies (dict[str, str], optional) — A dictionary of proxy servers to use by protocol or endpoint, e.g., {'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}. The proxies are used on each request.
  • token (str or bool, optional) — The token to use as HTTP bearer authorization for remote files. If True, or not specified, will use the token generated when running hf auth login (stored in ~/.huggingface).
  • revision (str, optional, defaults to "main") — The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so revision can be any identifier allowed by git.

Instantiate a type of ImageProcessingMixin from an image processor.

示例

# We can't instantiate directly the base class *ImageProcessingMixin* so let's show the examples on a
# derived class: *CLIPImageProcessor*
image_processor = CLIPImageProcessor.from_pretrained(
    "openai/clip-vit-base-patch32"
)  # Download image_processing_config from huggingface.co and cache.
image_processor = CLIPImageProcessor.from_pretrained(
    "./test/saved_model/"
)  # E.g. image processor (or model) was saved using *save_pretrained('./test/saved_model/')*
image_processor = CLIPImageProcessor.from_pretrained("./test/saved_model/preprocessor_config.json")
image_processor = CLIPImageProcessor.from_pretrained(
    "openai/clip-vit-base-patch32", do_normalize=False, foo=False
)
assert image_processor.do_normalize is False
image_processor, unused_kwargs = CLIPImageProcessor.from_pretrained(
    "openai/clip-vit-base-patch32", do_normalize=False, foo=False, return_unused_kwargs=True
)
assert image_processor.do_normalize is False
assert unused_kwargs == {"foo": False}

get_image_processor_dict

< >

( pretrained_model_name_or_path: str | os.PathLike **kwargs ) → tuple[Dict, Dict]

参数

  • pretrained_model_name_or_path (str or os.PathLike) — The identifier of the pre-trained checkpoint from which we want the dictionary of parameters.
  • subfolder (str, optional, defaults to "") — In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can specify the folder name here.
  • image_processor_filename (str, optional, defaults to "config.json") — The name of the file in the model directory to use for the image processor config.

返回

tuple[Dict, Dict]

The dictionary(ies) that will be used to instantiate the image processor object.

From a pretrained_model_name_or_path, resolve to a dictionary of parameters, to be used for instantiating a image processor of type ~image_processor_utils.ImageProcessingMixin using from_dict.

push_to_hub

< >

( repo_id: str commit_message: str | None = None commit_description: str | None = None private: bool | None = None token: bool | str | None = None revision: str | None = None create_pr: bool = False max_shard_size: int | str | None = '50GB' tags: list[str] | None = None )

参数

  • repo_id (str) — The name of the repository you want to push your image processor to. It should contain your organization name when pushing to a given organization.
  • commit_message (str, optional) — Message to commit while pushing. Will default to "Upload image processor".
  • commit_description (str, optional) — The description of the commit that will be created
  • private (bool, optional) — Whether to make the repo private. If None (default), the repo will be public unless the organization’s default is private. This value is ignored if the repo already exists.
  • token (bool or str, optional) — The token to use as HTTP bearer authorization for remote files. If True (default), will use the token generated when running hf auth login (stored in ~/.huggingface).
  • revision (str, optional) — Branch to push the uploaded files to.
  • create_pr (bool, optional, defaults to False) — Whether or not to create a PR with the uploaded files or directly commit.
  • max_shard_size (int or str, optional, defaults to "50GB") — Only applicable for models. The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size lower than this size. If expressed as a string, needs to be digits followed by a unit (like "5MB").
  • tags (list[str], optional) — List of tags to push on the Hub.

Upload the image processor file to the 🤗 Model Hub.

示例

from transformers import AutoImageProcessor

image processor = AutoImageProcessor.from_pretrained("google-bert/bert-base-cased")

# Push the image processor to your namespace with the name "my-finetuned-bert".
image processor.push_to_hub("my-finetuned-bert")

# Push the image processor to an organization with the name "my-finetuned-bert".
image processor.push_to_hub("huggingface/my-finetuned-bert")

register_for_auto_class

< >

( auto_class = 'AutoImageProcessor' )

参数

  • auto_class (str or type, optional, defaults to "AutoImageProcessor ") — The auto class to register this new image processor with.

Register this class with a given auto class. This should only be used for custom image processors as the ones in the library are already mapped with AutoImageProcessor .

save_pretrained

< >

( save_directory: str | os.PathLike push_to_hub: bool = False **kwargs )

参数

  • save_directory (str or os.PathLike) — Directory where the image processor JSON file will be saved (will be created if it does not exist).
  • push_to_hub (bool, optional, defaults to False) — Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with repo_id (will default to the name of save_directory in your namespace).
  • kwargs (dict[str, Any], optional) — 附加关键字参数将传递给 push_to_hub() 方法。

将图像处理器对象保存到目录 save_directory，以便可以使用 from_pretrained() 类方法重新加载。

to_dict

< >

( ) → dict[str, Any]

返回

dict[str, Any]

构成此图像处理器实例的所有属性的字典。

将此实例序列化为 Python 字典。

to_json_file

< >

( json_file_path: str | os.PathLike )

参数

  • json_file_path (str 或 os.PathLike) — 将保存此 image_processor 实例参数的 JSON 文件的路径。

将此实例保存到 JSON 文件。

to_json_string

< >

( ) → str

返回

字符串

包含此 feature_extractor 实例的所有属性的 JSON 格式字符串。

将此实例序列化为 JSON 字符串。

在 GitHub 上更新

←用于生成的实用程序 用于音频处理的实用程序→
© . This site is unofficial and not affiliated with Hugging Face, Inc.