U 4AfOn]@sUdZddlZddlZddlZddlZddlmZddlmZm Z m Z m Z m Z ddl mZddlmZmZddlmZmZdd lmZdd lmZmZmZmZmZmZd d lmZd d l m!Z!m"Z"m#Z#m$Z$e%e&Z'ereZ(ee)e e e)e e)ffe*d<nedddddddddddddddddd d!d"d#d$d%d&d'd(d)d*d+d,d-d.d/d0d1d2d3d4d5d6d7d8d9d:d;dd?d@dAdBdCdDdEdFdGdHdIdJdKdLdMdNdOdPdQdRdSdTdUdVdWdXdYdZd[d\d]d^d_d`dadbdcdddedfdgdhdidjg\Z(e(+D]T\Z,Z-e-^Z.Z/esdZ.e/re/ddksesdZ/ne/dZ/e.e/fe(e,<qee!e(Z0e)dkdldmZ1dve e)ej2fe e e)ej2fe3e e3e e e)e)fe e e3e)fe e)e3dodpdqZ4drdsZ5GdtduduZ6dS)wzAutoImageProcessor class.N) OrderedDict) TYPE_CHECKINGDictOptionalTupleUnion)PretrainedConfig)get_class_from_dynamic_moduleresolve_trust_remote_code)BaseImageProcessorImageProcessingMixin)BaseImageProcessorFast) CONFIG_NAMEIMAGE_PROCESSOR_NAMEget_file_from_repois_torchvision_availableis_vision_availablelogging)_LazyAutoMapping)CONFIG_MAPPING_NAMES AutoConfigmodel_type_to_module_name!replace_list_option_in_docstringsIMAGE_PROCESSOR_MAPPING_NAMES)ZalignZEfficientNetImageProcessor)ZbeitZBeitImageProcessor)bitZBitImageProcessor)ZblipZBlipImageProcessor)zblip-2r )Z bridgetower)ZBridgeTowerImageProcessor)Z chameleon)ZChameleonImageProcessor)Z chinese_clip)ZChineseCLIPImageProcessor)ZclipZCLIPImageProcessor)ZclipsegZViTImageProcessorZViTImageProcessorFast)Zconditional_detr)ZConditionalDetrImageProcessor)ZconvnextZConvNextImageProcessor)Z convnextv2r#)cvtr#)zdata2vec-visionr)Zdeformable_detr)ZDeformableDetrImageProcessor)Zdeit)ZDeiTImageProcessor)Zdepth_anythingZDPTImageProcessor)Zdeta)ZDetaImageProcessor)ZdetrZDetrImageProcessor)Zdinatr")Zdinov2r)z donut-swin)ZDonutImageProcessor)Zdptr%)Zefficientformer)ZEfficientFormerImageProcessor)Z efficientnetr)Zflava)ZFlavaImageProcessor)Zfocalnetr)Zfuyu)ZFuyuImageProcessor)gitr!)Zglpn)ZGLPNImageProcessor)zgrounding-dino)ZGroundingDinoImageProcessor)Zgroupvitr!)Zhierar)Zidefics)ZIdeficsImageProcessor)Zidefics2)ZIdefics2ImageProcessor)Zimagegpt)ZImageGPTImageProcessor)Z instructblipr )Zinstructblipvideo)ZInstructBlipVideoImageProcessor)zkosmos-2r!)Z layoutlmv2)ZLayoutLMv2ImageProcessor)Z layoutlmv3ZLayoutLMv3ImageProcessor)Zlevit)ZLevitImageProcessor)Zllavar!)zllava-next-video)ZLlavaNextVideoImageProcessor)Z llava_next)ZLlavaNextImageProcessor)Z mask2former)ZMask2FormerImageProcessor)Z maskformer)ZMaskFormerImageProcessor)zmgp-strr")Z mobilenet_v1)ZMobileNetV1ImageProcessor)Z mobilenet_v2)ZMobileNetV2ImageProcessor)Z mobilevitZMobileViTImageProcessor)Z mobilevitv2r))Znatr")Znougat)ZNougatImageProcessor)Z oneformer)ZOneFormerImageProcessor)Zowlv2)ZOwlv2ImageProcessor)Zowlvit)ZOwlViTImageProcessor)Z perceiver)ZPerceiverImageProcessor)Z pix2struct)ZPix2StructImageProcessor)Z poolformer)ZPoolFormerImageProcessor)ZpvtZPvtImageProcessor)Zpvt_v2r*)Zregnetr#)Zresnetr#)Zrt_detrZRTDetrImageProcessor)Zsam)ZSamImageProcessor)Z segformerZSegformerImageProcessor)Zseggpt)ZSegGptImageProcessor)Zsiglip)ZSiglipImageProcessor)Z swiftformerr")Zswinr")Zswin2sr)ZSwin2SRImageProcessor)Zswinv2r")ztable-transformerr&)Z timesformerZVideoMAEImageProcessor)Ztvlt)ZTvltImageProcessor)Ztvp)ZTvpImageProcessor)Zudopr()Zupernetr+)Zvanr#)Zvideomaer,)Zvilt)ZViltImageProcessor)Zvipllavar!)Zvitr")Z vit_hybrid)ZViTHybridImageProcessor)Zvit_maer")Zvit_msnr")Zvitmatte)ZVitMatteImageProcessor)Zxclipr!)Zyolos)ZYolosImageProcessor)Zzoedepth)ZZoeDepthImageProcessor) class_namec Cs|dkr tStD]T\}}||krt|}td|d}zt||WStk rfYqYqXqtj D].\}}|D] }t|dd|kr|Sqqttd}t ||rt||SdS)Nr.ztransformers.models__name__Z transformers) rritemsr importlib import_modulegetattrAttributeErrorIMAGE_PROCESSOR_MAPPING_extra_contenthasattr)r- module_nameZ extractorsmodule_Z extractorZ main_moduler;R/tmp/pip-unpacked-wheel-zw5xktn0/transformers/models/auto/image_processing_auto.pyimage_processor_class_from_names$    r=F)pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_onlyc Ks|dd} | dk r4tdt|dk r0td| }t|t|||||||d } | dkrdtdiSt | dd} t | W5QRSQRXdS) a Loads the image processor configuration from a pretrained model image processor configuration. Args: pretrained_model_name_or_path (`str` or `os.PathLike`): This can be either: - a string, the *model id* of a pretrained model configuration hosted inside a model repo on huggingface.co. - a path to a *directory* containing a configuration file saved using the [`~PreTrainedTokenizer.save_pretrained`] method, e.g., `./my_model_directory/`. cache_dir (`str` or `os.PathLike`, *optional*): Path to a directory in which a downloaded pretrained model configuration 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 configuration files and override the cached versions if they exist. resume_download: Deprecated and ignored. All downloads are now resumed by default when possible. Will be removed in v5 of Transformers. 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`, will use the token generated when running `huggingface-cli 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. local_files_only (`bool`, *optional*, defaults to `False`): If `True`, will only try to load the image processor configuration from local files. Passing `token=True` is required when you want to use a private model. Returns: `Dict`: The configuration of the image processor. Examples: ```python # Download configuration from huggingface.co and cache. image_processor_config = get_image_processor_config("google-bert/bert-base-uncased") # This model does not have a image processor config so the result will be an empty dict. image_processor_config = get_image_processor_config("FacebookAI/xlm-roberta-base") # Save a pretrained image processor locally and you can reload its config from transformers import AutoTokenizer image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k") image_processor.save_pretrained("image-processor-test") image_processor_config = get_image_processor_config("image-processor-test") ```use_auth_tokenNrThe `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.V`token` and `use_auth_token` are both specified. Please set only the argument `token`.)r?r@rArBrCrDrEzbCould not locate the image processor configuration file, will try to use the model config instead.zutf-8)encoding) popwarningswarn FutureWarning ValueErrorrrloggerinfoopenjsonload) r>r?r@rArBrCrDrEkwargsrFZresolved_config_filereaderr;r;r<get_image_processor_configs6E  rVcCstd|ddS)NzFast image processor class zz is available for this model. Using slow image processor class. To use the fast image processor class set `use_fast=True`.)rOwarning)Z fast_classr;r;r<'_warning_fast_image_processor_available's rXc@s:eZdZdZddZeeeddZe d dd Z dS) AutoImageProcessora% This is a generic image processor class that will be instantiated as one of the image processor classes of the library when created with the [`AutoImageProcessor.from_pretrained`] class method. This class cannot be instantiated directly using `__init__()` (throws an error). cCs tddS)NzAutoImageProcessor is designed to be instantiated using the `AutoImageProcessor.from_pretrained(pretrained_model_name_or_path)` method.)EnvironmentError)selfr;r;r<__init__6szAutoImageProcessor.__init__cOsp|dd}|dk r@tdt|dddk r8td||d<|dd}|dd}|dd}d |d <tj|f|\}} |d d} d} d |d ikr|d d } | dkr| dkr|dd} | dk r| dd} d|d ikr|d d} | dd} | dkrd| dkrdt |t s6t j |f|}t |d d} t|d rdd |jkrd|jd } | dk r|dk r|r| ds| d7} n|s| dr| dd} t| } | dk }| dk pt|tk}t||||}| dk rt | ts| df} |r|r|s0| ddk r0t| d|rN| ddk rN| d}n| d}t||f|} |dd} tj|r| | j|f|S| dk r| j|f|St|tkr2tt|}|\}}|s|dk rt||r|s|dkr|j |f||S|dk r*|j |f||Stdtd|dtdtdtddddt !D dS) a Instantiate one of the image processor classes of the library from a pretrained model vocabulary. The image processor class to instantiate is selected based on the `model_type` property of the config object (either passed as an argument or loaded from `pretrained_model_name_or_path` if possible), or when it's missing, by falling back to using pattern matching on `pretrained_model_name_or_path`: List options Params: 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 [`~image_processing_utils.ImageProcessingMixin.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. resume_download: Deprecated and ignored. All downloads are now resumed by default when possible. Will be removed in v5 of Transformers. 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`, will use the token generated when running `huggingface-cli 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. use_fast (`bool`, *optional*, defaults to `False`): Use a fast torchvision-base image processor if it is supported for a given model. If a fast tokenizer is not available for a given model, a normal numpy-based image processor is returned instead. return_unused_kwargs (`bool`, *optional*, defaults to `False`): If `False`, then this function returns just the final image processor object. If `True`, then this functions returns a `Tuple(image_processor, unused_kwargs)` where *unused_kwargs* is a dictionary consisting of the key/value pairs whose keys are not image processor attributes: i.e., the part of `kwargs` which has not been used to update `image_processor` and is otherwise ignored. trust_remote_code (`bool`, *optional*, defaults to `False`): Whether or not to allow for custom models defined on the Hub in their own modeling files. This option should only be set to `True` for repositories you trust and in which you have read the code, as it will execute code present on the Hub on your local machine. kwargs (`Dict[str, Any]`, *optional*): The values in kwargs of any keys which are image processor attributes will be used to override the loaded values. Behavior concerning key/value pairs whose keys are *not* image processor attributes is controlled by the `return_unused_kwargs` keyword parameter. Passing `token=True` is required when you want to use a private model. Examples: ```python >>> from transformers import AutoImageProcessor >>> # Download image processor from huggingface.co and cache. >>> image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k") >>> # If image processor files are in a directory (e.g. image processor was saved using *save_pretrained('./test/saved_model/')*) >>> # image_processor = AutoImageProcessor.from_pretrained("./test/saved_model/") ```rFNrGrCrHconfiguse_fasttrust_remote_codeTZ _from_autoZimage_processor_typerYauto_mapZfeature_extractor_typeZFeatureExtractorZImageProcessorZAutoFeatureExtractorZFastrrZ code_revisionzZThis image processor cannot be instantiated. Please make sure you have `Pillow` installed.z Unrecognized image processor in z2. Should have a `image_processor_type` key in its z of z3, or one of the following `model_type` keys in its z: z, css|] }|VqdS)Nr;).0cr;r;r< sz5AutoImageProcessor.from_pretrained..)"rJrKrLrMgetrNr Zget_image_processor_dictreplace isinstancer rfrom_pretrainedr3r7r`endswithr=typer5r tuplerXr ospathisdirZregister_for_auto_class from_dictrrjoinrkeys)clsr>inputsrTrFr]r^r_Z config_dictr:image_processor_classZimage_processor_auto_mapZfeature_extractor_classZfeature_extractor_auto_mapZhas_remote_codeZhas_local_codeZ class_refZimage_processor_tupleZimage_processor_class_pyZimage_processor_class_fastr;r;r<rh<sM                        4z"AutoImageProcessor.from_pretrainedNFcCs|dk r(|dk rtdtdt|}|dkr@|dkr@td|dk rZt|trZtd|dk rtt|trttd|dk r|dk rt|tr|j|krtd|jd|d |tj krt|\}}|dkr|}|dkr|}tj |||f|d dS) a) Register a new image processor for this class. Args: config_class ([`PretrainedConfig`]): The configuration corresponding to the model to register. image_processor_class ([`ImageProcessingMixin`]): The image processor to register. NzHCannot specify both image_processor_class and slow_image_processor_classzThe image_processor_class argument is deprecated and will be removed in v4.42. Please use `slow_image_processor_class`, or `fast_image_processor_class` insteadzSYou need to specify either slow_image_processor_class or fast_image_processor_classzIYou passed a fast image processor in as the `slow_image_processor_class`.zIYou passed a slow image processor in as the `fast_image_processor_class`.zThe fast processor class you are passing has a `slow_image_processor_class` attribute that is not consistent with the slow processor class you passed (fast tokenizer has z and you passed z!. Fix one of those so they match!)exist_ok) rNrKrLrM issubclassrr slow_image_processor_classr5r6register)Z config_classrtrwfast_image_processor_classruZ existing_slowZ existing_fastr;r;r<rxsH  zAutoImageProcessor.register)NNNF) r/ __module__ __qualname____doc__r\ classmethodrrrh staticmethodrxr;r;r;r<rY.s 1rY)NFNNNNF)7r|r1rRrlrK collectionsrtypingrrrrrZconfiguration_utilsr Zdynamic_module_utilsr r Zimage_processing_utilsr r Zimage_processing_utils_fastrutilsrrrrrrZ auto_factoryrZconfiguration_autorrrrZ get_loggerr/rOrstr__annotations__r0Z model_typeZimage_processorsrwryr5r=PathLikeboolrVrXrYr;r;r;r<s      (a   d