o h44@sdZddlmZddlmZmZmZmZddlm Z ddl m Z ddl m Z ddlmZdd lmZer@dd lmZdd lmZeeZd d iZGddde ZGddde ZdS)z LayoutLMv3 model configuration) OrderedDict) TYPE_CHECKINGAnyMappingOptional)version)PretrainedConfig) OnnxConfig) compute_effective_axis_dimension)logging)ProcessorMixin) TensorTypezmicrosoft/layoutlmv3-basezIhttps://huggingface.co/microsoft/layoutlmv3-base/resolve/main/config.jsoncsbeZdZdZdZ                        dfdd ZZS)LayoutLMv3Configa This is the configuration class to store the configuration of a [`LayoutLMv3Model`]. It is used to instantiate an LayoutLMv3 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the LayoutLMv3 [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 50265): Vocabulary size of the LayoutLMv3 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`LayoutLMv3Model`]. hidden_size (`int`, *optional*, defaults to 768): Dimension of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 512): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`LayoutLMv3Model`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-5): The epsilon used by the layer normalization layers. max_2d_position_embeddings (`int`, *optional*, defaults to 1024): The maximum value that the 2D position embedding might ever be used with. Typically set this to something large just in case (e.g., 1024). coordinate_size (`int`, *optional*, defaults to `128`): Dimension of the coordinate embeddings. shape_size (`int`, *optional*, defaults to `128`): Dimension of the width and height embeddings. has_relative_attention_bias (`bool`, *optional*, defaults to `True`): Whether or not to use a relative attention bias in the self-attention mechanism. rel_pos_bins (`int`, *optional*, defaults to 32): The number of relative position bins to be used in the self-attention mechanism. max_rel_pos (`int`, *optional*, defaults to 128): The maximum number of relative positions to be used in the self-attention mechanism. max_rel_2d_pos (`int`, *optional*, defaults to 256): The maximum number of relative 2D positions in the self-attention mechanism. rel_2d_pos_bins (`int`, *optional*, defaults to 64): The number of 2D relative position bins in the self-attention mechanism. has_spatial_attention_bias (`bool`, *optional*, defaults to `True`): Whether or not to use a spatial attention bias in the self-attention mechanism. visual_embed (`bool`, *optional*, defaults to `True`): Whether or not to add patch embeddings. input_size (`int`, *optional*, defaults to `224`): The size (resolution) of the images. num_channels (`int`, *optional*, defaults to `3`): The number of channels of the images. patch_size (`int`, *optional*, defaults to `16`) The size (resolution) of the patches. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Example: ```python >>> from transformers import LayoutLMv3Config, LayoutLMv3Model >>> # Initializing a LayoutLMv3 microsoft/layoutlmv3-base style configuration >>> configuration = LayoutLMv3Config() >>> # Initializing a model (with random weights) from the microsoft/layoutlmv3-base style configuration >>> model = LayoutLMv3Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` layoutlmv3Y gelu皙?{Gz?h㈵>rT @rNc  stjd||||||||| | | | | ||d|||_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ ||_||_||_dS)N) vocab_size hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_eps pad_token_id bos_token_id eos_token_id)super__init__max_2d_position_embeddingscoordinate_size shape_sizehas_relative_attention_bias rel_pos_bins max_rel_poshas_spatial_attention_biasrel_2d_pos_binsmax_rel_2d_pos text_embed visual_embed input_size num_channels patch_sizeclassifier_dropout) selfr#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r5r6r7r8r9r:r<r=r;r>r?r@rArBrCkwargs __class__r2m/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/layoutlmv3/configuration_layoutlmv3.pyr4}sD" zLayoutLMv3Config.__init__)rrrrrrrrrrrrrrrrrrTrrrr TTTr!rr"N)__name__ __module__ __qualname____doc__ model_typer4 __classcell__r2r2rFrHr(sDRrc@seZdZedZedeeee efffddZ ede fddZ ede fddZ dddde de dededde de de deeeffddZd S)LayoutLMv3OnnxConfigz1.12returnc Cs~|jdvr#tddddfddddfddddfddd d d d fgStddddfddddfddddfddd dfgS) N)zquestion-answeringzsequence-classification input_idsbatchsequence)rrattention_maskbbox pixel_valuesrAheightwidth)rrrr)taskrrDr2r2rHinputss        zLayoutLMv3OnnxConfig.inputscCdS)Nrr2rZr2r2rHatol_for_validationz(LayoutLMv3OnnxConfig.atol_for_validationcCr\)Nrr2rZr2r2rHdefault_onnx_opsetr^z'LayoutLMv3OnnxConfig.default_onnx_opsetFNr( processorr batch_size seq_lengthis_pair frameworkrrA image_width image_heightc Cst|jddt|tjdd}|j|} t|tj| d}d|jj g|gg|} gdgg|} | ||||} t || | | |d} | S)a Generate inputs to provide to the ONNX exporter for the specific framework Args: processor ([`ProcessorMixin`]): The processor associated with this model configuration. batch_size (`int`, *optional*, defaults to -1): The batch size to export the model for (-1 means dynamic axis). seq_length (`int`, *optional*, defaults to -1): The sequence length to export the model for (-1 means dynamic axis). is_pair (`bool`, *optional*, defaults to `False`): Indicate if the input is a pair (sentence 1, sentence 2). framework (`TensorType`, *optional*, defaults to `None`): The framework (PyTorch or TensorFlow) that the processor will generate tensors for. num_channels (`int`, *optional*, defaults to 3): The number of channels of the generated images. image_width (`int`, *optional*, defaults to 40): The width of the generated images. image_height (`int`, *optional*, defaults to 40): The height of the generated images. Returns: Mapping[str, Any]: holding the kwargs to provide to the model's forward function apply_ocrFr)fixed_dimensionnum_token_to_add )0TIr)textboxesreturn_tensors) setattrimage_processorr r default_fixed_batch tokenizernum_special_tokens_to_adddefault_fixed_sequencejoin unk_token_generate_dummy_imagesdict)rDrbrcrdrerfrArgrh token_to_add dummy_text dummy_bboxes dummy_imager[r2r2rHgenerate_dummy_inputss(%  z*LayoutLMv3OnnxConfig.generate_dummy_inputs)r`r`FNrrara)rIrJrKrparsetorch_onnx_minimum_versionpropertyrstrintr[floatr]r_boolrrrr2r2r2rHrOsD    rON)rL collectionsrtypingrrrr packagingrconfiguration_utilsr onnxr onnx.utilsr utilsr processing_utilsr r get_loggerrIlogger(LAYOUTLMV3_PRETRAINED_CONFIG_ARCHIVE_MAPrrOr2r2r2rHs"