`i6'dZddlmZmZddlZddlmZddlm Z m Z m Z ddl m Z mZmZmZddlmZmZdd lmZejeZGd d ed ZGddeZdgZdS)z Processor class for Llava. )OptionalUnionN) BatchFeature) ImageInputget_image_sizeto_numpy_array)MultiModalDataProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)loggingceZdZdddidZdS)LlavaProcessorKwargsF)paddingreturn_mm_token_type_ids) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaults~/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/llava/processing_llava.pyrr&s(#(eLLIIIrrF)totalc eZdZdZddgZdZdZ dfd Z dd ee d e e e e e e e fd eed efdZddZxZS)LlavaProcessoram Constructs a LLaVa processor which wraps a LLaVa image processor and a LLaMa tokenizer into a single processor. [`LlavaProcessor`] offers all the functionalities of [`LlavaImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~LlavaProcessor.__call__`] and [`~LlavaProcessor.decode`] for more information. Args: image_processor ([`LlavaImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`], *optional*): The tokenizer is a required input. patch_size (`int`, *optional*): Patch size from the vision tower. vision_feature_select_strategy (`str`, *optional*): The feature selection strategy used to select the vision feature from the vision backbone. Should be same as in model's config chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. image_token (`str`, *optional*, defaults to `""`): Special token used to denote image location. num_additional_image_tokens (`int`, *optional*, defaults to 0): Number of additional tokens added to the image embeddings, such as CLS (+1). If the backbone has no CLS or other extra tokens appended, no need to set this arg. image_processor tokenizerAutoImageProcessor AutoTokenizerNrc ||_||_||_t|dr|jn||_||jdd|_t|||dS)N image_tokenF)add_special_tokensr) chat_template) patch_sizenum_additional_image_tokensvision_feature_select_strategyhasattrr'encodeimage_token_idsuper__init__) selfr!r"r*r,r)r'r+kwargs __class__s rr1zLlavaProcessor.__init__Ks%+F(.L+4;I}4U4Uf900[f'..t/?TY.ZZ[\] )=QQQQQrimagestextr3returnc Z||td|jtfd|jji|}||j|fi|d}ni}t |tr|g}n?t |ts*t |dtstd|}| d|d} tt| d\} } | |j z| |j zz|jz} |jdkr| d z} g}|D]:} | |j|j| z} || ;|d d d}|d d d }|j|fi|d d di}|||dg|rYt+j|d}t+j|d}d |||jk<||d<t5i|||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 LlamaTokenizerFast's [`~LlamaTokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` and `kwargs` arguments to CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the docstring of the above two methods for more information. 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). 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`. Nz7You have to specify at least one of `images` or `text`.tokenizer_init_kwargsrrzAInvalid input text. Please provide a string, or a list of strings pixel_valuesdefaultrreturn_tensorsrFimage) modalities input_idsmm_token_type_ids)data tensor_type) ValueError _merge_kwargsrr" init_kwargsr! isinstancestrlist TypeErrorgetrr r*r+r,replacer'appendpop_check_special_mm_tokensnparray zeros_liker/tolistr)r2r5r6audiovideosr3 output_kwargs image_inputsprompt_stringsr:heightwidthnum_image_tokenssampler=r text_inputs array_idsrAs r__call__zLlavaProcessor.__call__]sN >dlVWW W**   "&."<    /4/YY-:XYYLLL dC  a6DDD$'' a 47C0H0H a_`` `   N + + 7'7L*>,q/+J+JKKMFE &$/ 9( 0 1 2i?? A% N . .(8$:JM]:]^^%%f----&}599:JDQQ#0#?#C#CD^`e#f#f $dn^ii}]7Siidhiii  %%nkwi%XXX # J[!9::I " k+.F G G BC i4+>> ?/@/G/G/I/IK+ ,!@K!@>PRSSM   ( ( (%))+t<<^@T@^I,5h,?7ASMN .$/ AmW[WfFfg   @ @ 2i?? A% 01C 4D4DD !"c+&6&6 6    4D[lmm n n n,, ,,,r)NNNNNr%r)NNNN)N)rrr__doc__ attributesimage_processor_classtokenizer_classr1rrrrrrIr rrr_ri __classcell__)r4s@rr r -s2$[1J0%O'+$%RRRRRR((,^b U^U^$U^I0$y/4HYCZZ[U^ -. U^ U^U^U^U^n--------rr )rjtypingrrnumpyrPfeature_extraction_utilsr image_utilsrrr processing_utilsr r r r tokenization_utils_baserrutilsr get_loggerrloggerrr __all__rrrrysU#"""""""444444EEEEEEEEEE DCCCCCCC  H % %+5d-d-d-d-d-^d-d-d-N  r