UhKddlZddlZddlZddlZddlmZmZmZmZm Z m Z ddl Z ddl mZddlmZmZddlmZddlmZmZmZddlmZmZdd lmZmZmZmZm Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)m*Z*dd l+m,Z,dd l-m.Z.m/Z/m0Z0m1Z1m2Z2m3Z3e)rdd lm4Z4e&rddl5Z5e'rdd lm6Z6e(rddl7m8Z9nddl:m8Z9e*jve<Z=dZ>e de>e,dGddeZ?e"e?je?_@e?jj8e?jjjddde?j_Ayy)N)AnyDictListOptionalTupleUnion)custom_object_save) BatchFeature get_size_dict)BaseImageProcessorFast)ChannelDimensionSizeDictvalidate_kwargs)Unpack VideosKwargs)VIDEO_PROCESSOR_NAME TensorTypeadd_model_info_to_auto_map"add_model_info_to_custom_pipelinesadd_start_docstrings cached_file copy_func download_urlis_offline_mode is_remote_urlis_torch_availableis_torchvision_availableis_torchvision_v2_availableis_vision_availablelogging)requires) VideoInputgroup_videos_by_shape load_videomake_batched_videosreorder_videosto_channel_dimension_format)PILImageResampling)pil_torch_interpolation_mapping) functionalac Args: do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the video's (height, width) dimensions to the specified `size`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`dict`, *optional*, defaults to `self.size`): Size of the output video after resizing. Can be overridden by the `size` parameter in the `preprocess` method. size_divisor (`int`, *optional*, defaults to `self.size_divisor`): The size by which to make sure both the height and width can be divided. default_to_square (`bool`, *optional*, defaults to `self.default_to_square`): Whether to default to a square video when resizing, if size is an int. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the video. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `resample` parameter in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether to center crop the video to the specified `crop_size`. Can be overridden by `do_center_crop` in the `preprocess` method. do_pad (`bool`, *optional*): Whether to pad the video to the `(max_height, max_width)` of the videos in the batch. crop_size (`Dict[str, int]` *optional*, defaults to `self.crop_size`): Size of the output video after applying `center_crop`. Can be overridden by `crop_size` in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the video by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `self.rescale_factor`): Scale factor to use if rescaling the video. Only has an effect if `do_rescale` is set to `True`. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the video. Can be overridden by the `do_normalize` parameter in the `preprocess` method. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`): Mean to use if normalizing the video. This is a float or list of floats the length of the number of channels in the video. Can be overridden by the `image_mean` parameter in the `preprocess` method. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Standard deviation to use if normalizing the video. This is a float or list of floats the length of the number of channels in the video. Can be overridden by the `image_std` parameter in the `preprocess` method. Can be overridden by the `image_std` parameter in the `preprocess` method. do_convert_rgb (`bool`, *optional*, defaults to `self.image_std`): Whether to convert the video to RGB. return_tensors (`str` or `TensorType`, *optional*): Returns stacked tensors if set to `pt, otherwise returns a list of tensors. data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`): The channel dimension format for the output video. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: video in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: video in (height, width, num_channels) format. - Unset: Use the channel dimension format of the input video. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input video. If unset, the channel dimension format is inferred from the input video. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: video in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: video in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: video in (height, width) format. device (`torch.device`, *optional*): The device to process the videos on. If unset, the device is inferred from the input videos.z!Constructs a base VideoProcessor.)vision torchvision)backendsc"veZdZdZdZdZdZdZdZdZ dZ dZ dZ dZ dZdZdZdZeZdgZdeeddffd ZdefdZd d defd Z d9d ed eeeefdedded fdZ e!e"d edeedefdZ# d:d ed de$de$de%dee&dedde$de%de$de$de'de$deee'ee'fdeee'ee'fd eeee(fdef d!Z)e* d;d"eee+jXfd#eeee+jXfd$e$d%e$d&eeee$fd'ef d(Z-dBaseVideoProcessorNTgp?pixel_values_videoskwargsreturnc t||jdd|_|j D]\}} t ||||jd|j}|'t||jd|jnd|_ |jd|j}| t|d nd|_ t|jjj!|_|j"D]<}|j%|t ||||%t ||t'||d>y#t $r%}tjd|d|d||d}~wwxYw) Nprocessor_classz Can't set z with value z for sizedefault_to_square)r6r7 crop_size) param_name)super__init__pop_processor_classitemssetattrAttributeErrorloggererrorr6r r7r8list valid_kwargs__annotations__keysmodel_valid_processing_keysgetgetattr)selfr2keyvalueerrr6r8 __class__s u/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/video_processing_utils.pyr;zBaseVideoProcessor.__init__sc  & +t |t j |}tj|j}||j|}|j||S)z: Prepare the input videos for processing. ) r& isinstancenpndarrayr(rFIRSTtorch from_numpy contiguoustoappend)rJrSrarbprocessed_videosrVs rO_prepare_input_videosz(BaseVideoProcessor._prepare_input_videoss%V, +E%,3E;K;Q;QSde((/::<!(  # #E * + rUc vt|j|jjj|jjD]}|j |t ||d!|j d}|j d}|j|||}|jd i|}|jd i||j d}t|ttfr t|n||d<|j d|j d|jd d |i|S) N)captured_kwargsvalid_processor_keysrarb)rSrarbresample interpolationr7 data_formatrS)rrFrDrE setdefaultrIr<rn_further_process_kwargs_validate_preprocess_kwargsrdr)intr* _preprocess)rJrSr2 kwarg_namerarbrrs rOrRzBaseVideoProcessor.preprocesss.  DL]L]LmLmLrLrLtu++;; KJ   j'$ D*I J K#JJ':;H%++6M^gm+n---77(((262::j)9CHOacfNg9h +H 5nv   &' =!t8v888rUdo_convert_rgb do_resizer6 size_divisorrszF.InterpolationModedo_center_cropr8 do_rescaledo_padrescale_factor do_normalize image_mean image_stdreturn_tensorsc t|\}}i}|jD]4\}}|r|j|}|r|j||||}|||<6t ||}t|\}}i}|jD]4\}}|r|j ||}|j || | | | |}|||<6t ||}|rtj|dn|}td|i|S)N)r6r~rsr)dimr1)data tensor_type) r$r>r`resizer' center_croprescale_and_normalizerhstackr )rJrSr|r}r6r~rsrr8rrrrrrrgrouped_videosgrouped_videos_indexresized_videos_groupedr]stacked_videosresized_videosprocessed_videos_groupedrms rOrzzBaseVideoProcessor._preprocesss;&0EV/L,,!#%3%9%9%; ; !E>!%!4!4^!D!%"LXe"-"-; "5 ) ;((>@TU0E^/T,,#% %3%9%9%; = !E>!%!1!1.)!L!77 NL*V_N/= $U + =**BDXYCQ5;;'7Q?Wg"79I!JXfggrUpretrained_model_name_or_path cache_dirforce_downloadlocal_files_onlytokenrevisionc ||d<||d<||d<||d<|jdd}|)tjdt| t d|}|||d <|j |fi|\} }|j | fi|S) a Instantiate a type of [`~video_processing_utils.VideoProcessorBase`] from an video processor. Args: pretrained_model_name_or_path (`str` or `os.PathLike`): This can be either: - a string, the *model id* of a pretrained video hosted inside a model repo on huggingface.co. - a path to a *directory* containing a video processor file saved using the [`~video_processing_utils.VideoProcessorBase.save_pretrained`] method, e.g., `./my_model_directory/`. - a path or url to a saved video 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 video 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 video 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`, or not specified, 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. To test a pull request you made on the Hub, you can pass `revision="refs/pr/"`. return_unused_kwargs (`bool`, *optional*, defaults to `False`): If `False`, then this function returns just the final video processor object. If `True`, then this functions returns a `Tuple(video_processor, unused_kwargs)` where *unused_kwargs* is a dictionary consisting of the key/value pairs whose keys are not video processor attributes: i.e., the part of `kwargs` which has not been used to update `video_processor` and is otherwise ignored. 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. kwargs (`Dict[str, Any]`, *optional*): The values in kwargs of any keys which are video processor attributes will be used to override the loaded values. Behavior concerning key/value pairs whose keys are *not* video processor attributes is controlled by the `return_unused_kwargs` keyword parameter. Returns: A video processor of type [`~video_processing_utils.ImagVideoProcessorBase`]. Examples: ```python # We can't instantiate directly the base class *VideoProcessorBase* so let's show the examples on a # derived class: *LlavaOnevisionVideoProcessor* video_processor = LlavaOnevisionVideoProcessor.from_pretrained( "llava-hf/llava-onevision-qwen2-0.5b-ov-hf" ) # Download video_processing_config from huggingface.co and cache. video_processor = LlavaOnevisionVideoProcessor.from_pretrained( "./test/saved_model/" ) # E.g. video processor (or model) was saved using *save_pretrained('./test/saved_model/')* video_processor = LlavaOnevisionVideoProcessor.from_pretrained("./test/saved_model/preprocessor_config.json") video_processor = LlavaOnevisionVideoProcessor.from_pretrained( "llava-hf/llava-onevision-qwen2-0.5b-ov-hf", do_normalize=False, foo=False ) assert video_processor.do_normalize is False video_processor, unused_kwargs = LlavaOnevisionVideoProcessor.from_pretrained( "llava-hf/llava-onevision-qwen2-0.5b-ov-hf", do_normalize=False, foo=False, return_unused_kwargs=True ) assert video_processor.do_normalize is False assert unused_kwargs == {"foo": False} ```rrrruse_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<warningswarn FutureWarning ValueErrorget_video_processor_dict from_dict) clsrrrrrrr2rvideo_processor_dicts rOfrom_pretrainedz"BaseVideoProcessor.from_pretrainedIst({#1 %5!"%z$4d;  % MME   l#E  #F7O'Cs'C'CDa'lek'l$fs}}1>. ) ?>2BBe!fg g NT2 #ZZ(8$?NjjN,@,@,Mb,QRG'd'':6:G#99.I     ' t^D A')ggll>CW&X# 56 /0K/LMN   ' ' -jj) ( ,,,rUc |jdd}|jdd}|jdd}|jdd}|jdd}|jdd}|jd d} |jd d} |jd d } |jd d} |jdd} |)tjdt| t d|}d| d}| | |d<t r| st jdd} t|}tjj|}tjj|r|}d}n6t|r|}t|}n t}t!||||||| ||| |  } t)|dd5}|j+}dddt-j.}|rt jd"|nt jd"d#||s,d$|vrt3|d$||d$<d%|vrt5|d%||d%<||fS#t"$r0d}t!||||||| ||| |  }t j%dYt"$rt&$rt#d|d|dtdwxYw#1swYxYw#t,j0$rt#d |d!wxYw)&a From a `pretrained_model_name_or_path`, resolve to a dictionary of parameters, to be used for instantiating a video processor of type [`~video_processing_utils.VideoProcessorBase`] using `from_dict`. Parameters: 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. Returns: `Tuple[Dict, Dict]`: The dictionary(ies) that will be used to instantiate the video processor object. rNrFresume_downloadproxiesrrrr subfolder_from_pipeline _from_autorrvideo processor) file_typefrom_auto_classusing_pipelinez+Offline mode: forcing local_files_only=TrueT) rrrrrr user_agentrrzpreprocessor_config.jsonaAYou have video processor config saved in `preprocessor.json` file which is deprecated. Video processor configs should be saved in their own `video_preprocessor.json` file. You can rename the file or load and save the processor back which renames it automatically. Loading from `preprocessor.json` will be removed in v5.0.z Can't load video processor for 'z'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'z2' is the correct path to a directory containing a z filerutf-8encodingz"It looks like the config file at 'z' is not a valid JSON file.zloading configuration file z from cache at auto_mapcustom_pipelines)r<rrrrrrArstrrrisdirrrrrrEnvironmentError warning_once ExceptionopenreadjsonloadsJSONDecodeErrorrr)rrr2rrrrrrrrr from_pipelinerris_localresolved_video_processor_filevideo_processor_filereadertextrs rOrz+BaseVideoProcessor.get_video_processor_dictsp$JJ{D1 $4e< **%6=**Y- 7D)$4d;!::&8%@::j$/JJ{B/  #3T:  **\59  % MME   l#E#4Y  $+8J' (  %5 KKE F# (+,I(J%77==!>? 77>>7 8,I )H 8 9#@ ,89V,W )2 (<$0;1('#1#$3%5)%' 1-^ 3S7K %v{{} %#'::d#3   KK56S5TU V KK-.B-C?SpRqr 113M(46S4$Z0"%99;]();<>[<$%78$V++{$ 'A$0;1('#1#$3%5)%' 1-##P $  &67T6UV99V8WX//C.DEK  % %## "45R4SSno  s6 I &J<4J0J< 6J-+J-0J95J<<#Krc |j}|jdd}d|vrd|vr|jd|d<d|vrd|vr|jd|d<|di|}g}|jD]0\}}t||st ||||j |2|D]}|j|dt jd||r||fS|S)a Instantiates a type of [`~video_processing_utils.VideoProcessorBase`] from a Python dictionary of parameters. Args: video_processor_dict (`Dict[str, Any]`): Dictionary that will be used to instantiate the video processor object. Such a dictionary can be retrieved from a pretrained checkpoint by leveraging the [`~video_processing_utils.VideoProcessorBase.to_dict`] method. kwargs (`Dict[str, Any]`): Additional parameters from which to initialize the video processor object. Returns: [`~video_processing_utils.VideoProcessorBase`]: The video processor object instantiated from those parameters. return_unused_kwargsFr6r8NzVideo processor ru)copyr<r>hasattrr?rlrAr)rrr2rvideo_processor to_removerKrLs rOrzBaseVideoProcessor.from_dicts " 488:%zz*@%H V *> >+1::f+=  ( & [4H%H06 ;0G  -5 45  ,,. &JC,e4  % & "C JJsD ! "  &&789 "F* *" "rUcvtj|j}|jj|d<|S)z Serializes this instance to a Python dictionary. Returns: `Dict[str, Any]`: Dictionary of all the attributes that make up this video processor instance. video_processor_type)rdeepcopy__dict__rN__name__)rJoutputs rOto_dictzBaseVideoProcessor.to_dicts0t}}-)-)@)@%& rUc|j}|jD]3\}}t|tjs!|j ||<5|j dd}|||d<tj|dddzS)z Serializes this instance to a JSON string. Returns: `str`: String containing all the attributes that make up this feature_extractor instance in JSON format. r=Nr5T)indent sort_keys ) rr>rdrerftolistr<rdumps)rJ dictionaryrKrLr=s rOto_json_stringz!BaseVideoProcessor.to_json_strings\\^ $**, 1JC%,"',,. 3 1 &>>* This API is experimental and may have some slight breaking changes in the next releases. Args: auto_class (`str` or `type`, *optional*, defaults to `"AutoVideoProcessor "`): The auto class to register this new video processor with. rNz is not a valid auto class.) rdrrtransformers.models.automodelsautorrr)r auto_class auto_modules rOregister_for_auto_classz*BaseVideoProcessor.register_for_auto_classsC *c*#,,J66{J/ |+FGH H$rUvideo_url_or_urlsct|tr|Dcgc]}|j|c}St|tr t |St dt |cc}w)z Convert a single or a list of urls into the corresponding `np.array` objects. If a single url is passed, the return value will be a single object. If a list is passed a list of objects is returned. z=only a single or a list of entries is supported but got type=)rdrC fetch_videosrr% TypeErrortype)rJr xs rOr zBaseVideoProcessor.fetch_videos sc ' .2CDQD%%a(D D )3 //0 0[\`ar\s[tuv v EsA")NNrQ)NFFNmain)F)AutoVideoProcessor)1L1 8EI+/   $E#/?*?$@A (  n   28999&9  9:9\<@!/h^$/h/h /h  /h sm /h 56/h/h/h/h/h/h/hU5$u+#567/hE%e"456/h !sJ!78!/h" #/hb8<$!&,0o=',S"++-='>o=E#r{{"234o= o=  o= c4i() o=o=o=b;-eC4D.E;-TX;-zI,,1#r{{2B,CI, tCH~tCH~- .I,I,V*#T#s(^*#*#X c3h GG* 05bkk1A+B 0D+uS"++-='>++$%%2 weCcN.C wrUr0rrzvideo processor file)object object_class object_files)Crrrrtypingrrrrrrnumpyredynamic_module_utilsr image_processing_utilsr r image_processing_utils_fastr image_utilsrrrprocessing_utilsrrutilsrrrrrrrrrrrrrr r!utils.import_utilsr" video_utilsr#r$r%r&r'r(r)rhr*torchvision.transforms.v2r+r[torchvision.transforms get_loggerrrArr0r__doc__formatrurUrOr.sG  ::4@ 3")/<"$=:   H %8"lv'" ,-H w/H w.  H wV"++=+I+I!J!!))5-?-K-K-S-S-Z-Z /CRh.[.""*6rU