`i;ddlmZmZddlZddlmZddlmZddl m Z m Z m Z m Z mZmZddlmZmZddlmZdd lmZejeZGd d ed ZGdde ZGdde d ZGdde ZdgZdS))OptionalUnionN) BatchFeature) ImageInput) ImagesKwargsMultiModalDataProcessingKwargsProcessorMixinUnpack VideosKwargs)PreTokenizedInput TextInput)logging) VideoInputc6eZdZUeeeefed<dS)Glm4vVideosProcessorKwargsfpsN)__name__ __module__ __qualname__rlistfloat__annotations__~/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/glm4v/processing_glm4v.pyrr$s, tE{E! """"""rrF)totalcReZdZUeeed<eeed<eeed<dS)Glm4vImagesKwargs patch_sizetemporal_patch_size merge_sizeN)rrrrintrrrrr r (sB !#&&& rr c:eZdZUeed<ddddddidZeed<dS) Glm4vProcessorKwargs images_kwargsF)paddingreturn_token_type_idsreturn_mm_token_type_idsreturn_metadataT) text_kwargs videos_kwargsr-N)rrrr r _defaultsrrrrr&r&.sW$$$$%*(-  ,T2 I.-----rr&c eZdZdZgdZdZdZdZdfd Z dde e d e e e ee ee fd e ed eed ef d ZddZ ddZxZS)Glm4vProcessora Constructs a GLM-4V processor which wraps a GLM-4V image processor and a GLM-4 tokenizer into a single processor. [`~Glm4vProcessor.__call__`] and [`~Glm4vProcessor.decode`] for more information. Args: image_processor ([`Glm4vProcessor`], *optional*): The image processor is a required input. tokenizer ([`PreTrainedTokenizerFast`], *optional*): The tokenizer is a required input. video_processor ([`Glm4vVideoProcessor`], *optional*): The video processor is a required input. chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. )image_processor tokenizervideo_processorAutoImageProcessorAutoVideoProcessor)PreTrainedTokenizerPreTrainedTokenizerFastNc t||||t|dsdn|j|_t|dsdn|j|_t |ddr|jn||j|_t |ddr|jn||j|_dS)N) chat_template image_tokenz <|image|> video_tokenz <|video|>image_token_idvideo_token_id) super__init__hasattrr:r;getattrr<convert_tokens_to_idsr=)selfr1r2r3r9kwargs __class__s rr?zGlm4vProcessor.__init__Ps )_Tabbb.5i.O.Oj;;U^Uj.5i.O.Oj;;U^Ujy"2D99 CI $ $001ABB y"2D99 CI $ $001ABB rimagestextvideosrDreturnc  |jtfd|jji|}||jdd|i|d}|d}ni}d}|@|jdd|i|d}d|vr|d } n|d } |d } ni}d} t|ts|g}| }||jj d z} d } tt|D]} |j || vrY|| | z}|| |j d |zd|| <| dz } |j || vY|| d |j || <| 8|jj d z} d }tt|D] } |j|| vr| |d }d}| |}|jt$d|jdn|j|_|jddd }g}td t|D]}||||d|}t||kr2||r|dnd t||k2t|D])}||}d|j dt-|}||z }*|| |j|d|| <| || z| |d z}t|D]9}|j || vr(|| |j d |zd|| <:|dz }|j|| v|| d |j || < |ddd}|ddd}|j|fi|d}|||ddg|rYt1j|d}t1j|d}d|||jk<||d<t;i||||S) a^ Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments to PreTrainedTokenizerFast's [`~PreTrainedTokenizerFast.__call__`] if `text` is not `None` to encode the text. Args: images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported. text (`str`, `List[str]`, `List[List[str]]`): The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). videos (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`): The image or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported. return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - `'jax'`: Return JAX `jnp.ndarray` objects. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. - **pixel_values_videos** -- Pixel values of videos to be fed to a model. Returned when `videos` is not `None`. - **image_grid_thw** -- List of image 3D grid in LLM. Returned when `images` is not `None`. - **video_grid_thw** -- List of video 3D grid in LLM. Returned when `videos` is not `None`. tokenizer_init_kwargsNrFr'image_grid_thwrHr-r+video_metadatavideo_grid_thwrz<|placeholder|>aSmolVLM requires frame timestamps to construct prompts, but the `fps` of the input video could not be inferred. Probably `video_metadata` was missing from inputs and you passed pre-sampled frames. Defaulting to `fps=24`. Please provide `video_metadata` for more accurate results.z<|begin_of_image|>z<|end_of_image|>r,return_tensorsr*Fimagevideo) modalities input_idsmm_token_type_ids)data tensor_typer) _merge_kwargsr&r2 init_kwargsr1r3pop isinstancercopyr#rangelenr:prodreplacer;rlogger warning_once timestampsappendr$_check_special_mm_tokensnparray zeros_liker<tolistr)rCrFrGrHrD output_kwargs image_inputsrL videos_inputsrMrN merge_lengthindexinum_image_tokens video_index num_framesvideo_structuremetadatargunique_timestampsidxselected_timestamps frame_idx timestamp_secframe_structurerTr* text_inputs array_idsrYs r__call__zGlm4vProcessor.__call___seT+*   "&."<    /4/``v`A_``L)*:;NNL!N  0D0aaa-P_B`aaM ..!.!2!23C!D!D!./?!@*+;@QTd@dfghhDGQJE&$q'11q'//*;T=MNNQ  %/:A=LK3t99%%& O& O&$q'11!/ !QRSSDG&{388::lJn]hNijkNll%&+:%6%6qq +tAw66&*1good6FHY\lHlno&p&pDG1$KG&$q'11Jq'//*;T=MNNQ&}599:JDQQ#0#?#C#CD^`e#f#f $dnTJJ]=-IJJ  %%dKWgDV%WWW # J[!9::I " k+.F G G BC i4+>> ?/@/G/G/I/IK+ ,!QK!Qz=Glm4vProcessor._get_num_multimodal_tokens..E!!!A$@\*\m\\\!!!rc g|] }|dzz SrOrr num_patchesr#s rrz=Glm4vProcessor._get_num_multimodal_tokens.."ddd; A !=dddr)rtnum_image_patchesr-c8g|]}jjg|RSr)r3get_number_of_video_patches)r video_sizerCr-s rrz=Glm4vProcessor._get_num_multimodal_tokens..rrc g|] }|dzz Srrrs rrz=Glm4vProcessor._get_num_multimodal_tokens..rrnum_video_tokensr)r&r.getupdater1r#r ) rC image_sizes video_sizesrD vision_datarrtnum_video_patchesrr'r#r-s ` @@@r_get_num_multimodal_tokensz)Glm4vProcessor._get_num_multimodal_tokenssh  "0:>>PRSSM   ( ( (&**<>>a$BVBaJ!!!!!"-!!!  edddRcddd    4D[lmm n n n  "0:>>PRSSM   ( ( (!!!!!"-!!!  edddRcddd .>K* +,, ,,,rTFc .|jj|f||d|S)a Post-process the output of the model to decode the text. Args: generated_outputs (`torch.Tensor` or `np.ndarray`): The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)` or `(sequence_length,)`. skip_special_tokens (`bool`, *optional*, defaults to `True`): Whether or not to remove special tokens in the output. Argument passed to the tokenizer's `batch_decode` method. clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): Whether or not to clean up the tokenization spaces. Argument passed to the tokenizer's `batch_decode` method. **kwargs: Additional arguments to be passed to the tokenizer's `batch_decode method`. Returns: `list[str]`: The decoded text. )skip_special_tokensclean_up_tokenization_spaces)r2 batch_decode)rCgenerated_outputsrrrDs rpost_process_image_text_to_textz.Glm4vProcessor.post_process_image_text_to_text s:(+t~*  3)E      r)NNNN)NNN)NN)TF)rrr__doc__ attributesimage_processor_classvideo_processor_classtokenizer_classr?rrrrrrrr r&rrrr __classcell__)rEs@rr0r0;s(  EDDJ00HO       "(,^b'+ DoDo$DoI0$y/4HYCZZ[Do$ Do -. Do  DoDoDoDoL$-$-$-$-NY^        rr0)typingrrnumpyrjfeature_extraction_utilsr image_utilsrprocessing_utilsrr r r r r tokenization_utils_baserrutilsr video_utilsr get_loggerrrerr r&r0__all__rrrrs*#"""""""444444%%%%%%ttttttttttttttttCCCCCCCC%%%%%%  H % %#####U####  . . . . .+5 . . . .i i i i i ^i i i X  r