o iݟ@sddlZddlZddlZddlmZddlmZddlmZddl m Z m Z ddl Z ddlmZmZddlmZdd lmZdd lmZmZdd lmZdd lmZmZmZdd lmZm Z ddl!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)m*Z*m+Z+m,Z,ddl-m.Z.ddl/m0Z0ddl1m2Z2m3Z3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9m:Z:e(rddl;Z;e*rddlm?Z@e+AeBZCdZDe&deDe0ddGdddeZEe'eEjFeE_FeEjFjGdureEjFjGjHddddeEjF_GdSdS)N)Callable)deepcopy)partial)AnyOptional) create_repois_offline_mode)validate_typed_dict)custom_object_save) BatchFeature get_size_dict)BaseImageProcessorFast)ChannelDimensionSizeDictvalidate_kwargs)Unpack VideosKwargs) IMAGE_PROCESSOR_NAMEPROCESSOR_NAMEVIDEO_PROCESSOR_NAME TensorTypeadd_start_docstrings copy_funcis_torch_availableis_torchcodec_availableis_torchvision_v2_availableloggingsafe_load_json_file cached_file)requires) VideoInput VideoMetadatagroup_videos_by_shapeinfer_channel_dimension_formatis_valid_video load_videomake_batched_metadatamake_batched_videosreorder_videosa 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. 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. video_metadata (`VideoMetadata`, *optional*): Metadata of the video containing information about total duration, fps and total number of frames. do_sample_frames (`int`, *optional*, defaults to `self.do_sample_frames`): Whether to sample frames from the video before processing or to process the whole video. num_frames (`int`, *optional*, defaults to `self.num_frames`): Maximum number of frames to sample when `do_sample_frames=True`. fps (`int` or `float`, *optional*, defaults to `self.fps`): Target frames to sample per second when `do_sample_frames=True`. 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. return_metadata (`bool`, *optional*): Whether to return video metadata or not. z!Constructs a base VideoProcessor.)vision torchvision)backendscseZdZdZdZdZdZdZdZdZ dZ dZ dZ dZ dZdZdZdZdZdZdZdZeZdgZdeeddffdd Zdefd d Zd d defddZ  dTdede dBde e!BdBfddZ"  dTdedee#Bde$dBde%dBde&d f ddZ'  dTdede(e)BdBde(dBde&d fddZ*e+e,dedeedefdd Z- dUde&d d!e$d"e$d#e.d$e/d%d&e$d'e.d(e$d)e!d*e$d+e!e&e!BdBd,e!e&e!BdBd-e(e0BdBdefd.d/Z1e2     0dVd1e(e3j4Bd2e(e3j4BdBd3e$d4e$d5e(e$BdBd6e(f d7d8Z5dWd9e(e3j4Bd:e$fd;d<Z6e2d1e(e3j4Bde7e#e(e8fe#e(e8fffd=d>Z9e2d?e#e(e8ffd@dAZ:de#e(e8ffdBdCZ;de(fdDdEZe2dKe(e3j4BfdLdMZ?e2dXdOdPZ@dUdQe(e&e(Be&e&e(BfdRdSZAZBS)YBaseVideoProcessorNTgp?Fpixel_values_videoskwargsreturnc s$t|dd|D](\}}zt|||Wqty7}ztd|d|d||d}~ww|d|j}|durNt ||d|j dnd|_|d|j }|durbt |dd nd|_ t |j j|_|jD]}||durt||||qqt||tt||dqqdS) Nprocessor_classz Can't set z with value z for sizedefault_to_square)r3r4 crop_size) param_name)super__init__popitemssetattrAttributeErrorloggererrorr3r r4r5list valid_kwargs__annotations__keysmodel_valid_processing_keysgetrgetattr)selfr0keyvalueerrr3r5 __class__e/sda-disk/www/egybert/egybert_env/lib/python3.10/site-packages/transformers/video_processing_utils.pyr8s.   zBaseVideoProcessor.__init__cKs|j|fi|SN) preprocess)rFvideosr0rLrLrM__call__szBaseVideoProcessor.__call__videoz torch.TensorcCst|}|jddks|ddddddfdks|S|ddddddfd}d|ddddddfd|ddddddf|dddddddf}|S)z Converts a video to RGB format. Args: video (`"torch.Tensor"`): The video to convert. Returns: `torch.Tensor`: The converted video. .Ngo@r )tvFgrayscale_to_rgbshapeany)rFrRalpharLrLrMconvert_to_rgbs .Tz!BaseVideoProcessor.convert_to_rgbmetadata num_framesfpscKs|dur |dur td|dur|n|j}|dur|n|j}|j}|dur?|dur?|dus2|jdur6tdt||j|}||krNtd|d|d|dur_td|||}|Std|}|S)a% Default sampling function which uniformly samples the desired number of frames between 0 and total number of frames. If `fps` is passed along with metadata, `fps` frames per second are sampled uniformty. Arguments `num_frames` and `fps` are mutually exclusive. Args: metadata (`VideoMetadata`): Metadata of the video containing information about total duration, fps and total number of frames. num_frames (`int`, *optional*): Maximum number of frames to sample. Defaults to `self.num_frames`. fps (`int` or `float`, *optional*): Target frames to sample per second. Defaults to `self.fps`. Returns: np.ndarray: Indices to sample video frames. Nzc`num_frames`, `fps`, and `sample_indices_fn` are mutually exclusive arguments, please use only one!zAsked to sample `fps` frames per second but no video metadata was provided which is required when sampling with `fps`. Please pass in `VideoMetadata` object or use a fixed `num_frames` per input videoz(Video can't be sampled. The `num_frames=z` exceeds `total_num_frames=z`. r) ValueErrorr]r^total_num_framesinttorcharange)rFr\r]r^r0r`indicesrLrLrM sample_framess,z BaseVideoProcessor.sample_framesrPvideo_metadatado_sample_framessample_indices_fnc Cst|}t||d}t|dr<|r:szKBaseVideoProcessor._decode_and_sample_videos...r)dim)rbstack)rjimagesrLrLrMrl9sz@BaseVideoProcessor._decode_and_sample_videos..zUSampling frames from a list of images is not supported! Set `do_sample_frames=False`.rh) r)r(r&zipframes_indicesappend isinstancer? fetch_imagesr_ fetch_videos) rFrPrfrgrhsampled_videossampled_metadatarRr\rdrLrLrM_decode_and_sample_videoss2    z,BaseVideoProcessor._decode_and_sample_videosinput_data_formatdevicecCsvg}|D]4}t|tjrt|}|durt|}|tjkr*| dddd}|dur3| |}| |q|S)z: Prepare the input videos for processing. NrrTr ) rtnpndarrayrb from_numpy contiguousr%rLASTpermutetors)rFrPrzr{processed_videosrRrLrLrM_prepare_input_videosFs     z(BaseVideoProcessor._prepare_input_videosc Kst|t|jjdgdt|j||jjD] }||t||dq|d}|d}|d}|d}|rGt |j fi|nd}|j ||||d\}}|j |||d}|j d i|}|jd i||d |d } |jd d |i|} | r|| d<| S) Nreturn_tensors)captured_kwargsvalid_processor_keysrzrgr{rf)rfrgrh)rPrzr{ data_formatreturn_metadatarPrL)rrBr?r@rAr setdefaultrEr9rreryr_further_process_kwargs_validate_preprocess_kwargs _preprocess) rFrPr0 kwarg_namerzrgr{rfrhrpreprocessed_videosrLrLrMrOcs6         zBaseVideoProcessor.preprocessdo_convert_rgb do_resizer3 interpolationztvF.InterpolationModedo_center_cropr5 do_rescalerescale_factor do_normalize image_mean image_stdrc Kst|\}}i}|D]\}}|r||}|r!|j|||d}|||<q t||}t|\}}i}|D]\}}|rC|||}|||| | | | }|||<q7t||}td|i| dS)N)r3rr/)data tensor_type)r$r:r[resizer* center_croprescale_and_normalizer )rFrPrrr3rrr5rrrrrrr0grouped_videosgrouped_videos_indexresized_videos_groupedrXstacked_videosresized_videosprocessed_videos_groupedrrLrLrMrs(         zBaseVideoProcessor._preprocessmainpretrained_model_name_or_path cache_dirforce_downloadlocal_files_onlytokenrevisionc KsX||d<||d<||d<||d<|dur||d<|j|fi|\}}|j|fi|S)aR 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/video_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. 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. 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/video_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} ```rrrrNr)get_video_processor_dict from_dict) clsrrrrrrr0video_processor_dictrLrLrMfrom_pretrainedsWz"BaseVideoProcessor.from_pretrainedsave_directory push_to_hubcKstj|rtd|dtj|dd|r:|dd}|d|tjjd}t|fd di|j }| |}|j durFt |||d tj |t}||td ||ri|j|||||d d |gS)aq Save an video processor object to the directory `save_directory`, so that it can be re-loaded using the [`~video_processing_utils.VideoProcessorBase.from_pretrained`] class method. Args: save_directory (`str` or `os.PathLike`): Directory where the video 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*): Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method. zProvided path (z#) should be a directory, not a fileT)exist_okcommit_messageNrepo_idr)configzVideo processor saved in r)rr)ospathisfileAssertionErrormakedirsr9splitseprr_get_files_timestamps _auto_classr joinr to_json_filer=info_upload_modified_filesrD)rFrrr0rrfiles_timestampsoutput_video_processor_filerLrLrMsave_pretrained"s,     z"BaseVideoProcessor.save_pretrainedc s|dd|dd|dd|dd|dd|dd|d d |d d}|d d}d |d |durC| d<trOsOtddttj}tjrf}d}d}nLt }z-t t  dd } f dd|t fD} | r| dnd}Wnt ytyt ddd|dwd} |durt|} d| vr| d} |dur| durt|} | durt ddd|d|rtd|| |fStd|d|| |fS)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. rNrFproxiesrrr subfolder_from_pipeline _from_autovideo processor) file_typefrom_auto_classusing_pipelinez+Offline mode: forcing local_files_only=TrueT filenamerrrrr user_agentrr%_raise_exceptions_for_missing_entriescs6g|]}t| dd durqS)FrNr)rjr rrrrr resolved_filerrrrrLrMrls&z?BaseVideoProcessor.get_video_processor_dict..rz 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 filevideo_processorzloading configuration file z from cache at )r9rr=rstrrrisdirrrr rrOSError Exceptionr) rrr0 from_pipelineris_localresolved_video_processor_fileresolved_processor_filevideo_processor_fileresolved_video_processor_filesrprocessor_dictrLrrMrRs                  z+BaseVideoProcessor.get_video_processor_dictrcKs|}|dd}d|vrd|vr|d|d<d|vr(d|vr(|d|d<|di|}g}|D]\}}t||rIt|||||q5|D]}||dqLtd||rc||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_kwargsFr3r5NzVideo processor rL)copyr9r:hasattrr;rsr=r)rrr0rr to_removerGrHrLrLrMrs&    zBaseVideoProcessor.from_dictcCst|j}i}|D]!\}}|dur(tt||d}|dkr'|dur'|||<q |||<q |dd|dd|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. N NOT_FOUNDrC_valid_kwargs_namesvideo_processor_type)r__dict__r:rEtyper9rK__name__)rFoutput filtered_dictrGrH class_defaultrLrLrMto_dicts     zBaseVideoProcessor.to_dictcCsF|}|D]\}}t|tjr|||<qtj|ddddS)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|T)indent sort_keys )rr:rtr}r~tolistjsondumps)rF dictionaryrGrHrLrLrMto_json_strings   z!BaseVideoProcessor.to_json_stringjson_file_pathcCsBt|ddd}||WddS1swYdS)z Save this instance to a JSON file. Args: json_file_path (`str` or `os.PathLike`): Path to the JSON file in which this image_processor instance's parameters will be saved. wutf-8encodingN)openwriter)rFrwriterrLrLrMr$s"zBaseVideoProcessor.to_json_filecCs|jjd|S)N )rKrr)rFrLrLrM__repr__/szBaseVideoProcessor.__repr__ json_filecCsNt|ddd }|}Wdn1swYt|}|di|S)a Instantiates a video processor of type [`~video_processing_utils.VideoProcessorBase`] from the path to a JSON file of parameters. Args: json_file (`str` or `os.PathLike`): Path to the JSON file containing the parameters. Returns: A video processor of type [`~video_processing_utils.VideoProcessorBase`]: The video_processor object instantiated from that JSON file. rrrNrL)rreadrloads)rrreadertextrrLrLrMfrom_json_file2s   z!BaseVideoProcessor.from_json_fileAutoVideoProcessorcCsDt|ts|j}ddlmm}t||st|d||_dS)a  Register this class with a given auto class. This should only be used for custom video processors as the ones in the library are already mapped with `AutoVideoProcessor `. 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.) rtrrtransformers.models.automodelsautorr_r)r auto_class auto_modulerLrLrMregister_for_auto_classEs   z*BaseVideoProcessor.register_for_auto_classvideo_url_or_urlscsLd}ts tdd}t|trttfdd|DSt||dS)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. torchcodecz`torchcodec` is not installed and cannot be used to decode the video by default. Falling back to `torchvision`. Note that `torchvision` decoding is deprecated and will be removed in future versions. r,csg|] }j|dqS)rp)rv)rjxrhrFrLrMrlosz3BaseVideoProcessor.fetch_videos..)backendrh)rwarningswarnrtr?rqr')rFrrhrrLrrMrv_s zBaseVideoProcessor.fetch_videos)NNrN)NFFNr)F)r )Cr __module__ __qualname__rresamplerrr3 size_divisorr4r5rrrrrrrgr^r]rfrrr@model_input_namesrr8r rQr"r[r#rafloatredictboolrr?ryrrrrBASE_VIDEO_PROCESSOR_DOCSTRINGrOrrrr classmethodrPathLikerrtuplerrrrrrrr rrv __classcell__rLrLrJrMr.s   9 +   :       -   b0 },  ,r.rr zvideo processor file)object object_class object_files)Irrrcollections.abcrrr functoolsrtypingrrnumpyr}huggingface_hubrrhuggingface_hub.dataclassesr dynamic_module_utilsr image_processing_utilsr r image_processing_utils_fastr image_utilsrrrprocessing_utilsrrutilsrrrrrrrrrrr utils.hubr utils.import_utilsr! video_utilsr"r#r$r%r&r'r(r)r*rb$torchvision.transforms.v2.functional transformsv2 functionalrV get_loggerrr=r r.r__doc__formatrLrLrLrMsT      4 ,  D c