U 9%e34@sdZddlmZddlmZmZmZmZddlm Z ddl m Z ddl m Z ddlmZdd lmZerdd 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.jsoncs&eZdZdZdZdfdd 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 ```Z layoutlmv3Y gelu皙?{Gz?h㈵>rT @rNc  stjf||||||||| | | | | ||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.r/r0r3r4r5r6r7r8r:r;r9r<r=r>r?r@rAkwargs __class__v/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/layoutlmv3/configuration_layoutlmv3.pyr2|sD"zLayoutLMv3Config.__init__)rrrrrrrrrrrrrrrrrrTrrrrTTTr rr!N)__name__ __module__ __qualname____doc__Z model_typer2 __classcell__rFrFrDrGr(sBQrc @seZdZedZeeeee effdddZ ee dddZ ee dddZ dde e eede e e eeefd ddZd S)LayoutLMv3OnnxConfigz1.12)returnc Cs|jdkrFtddddfddddfddddfddd d d d fgStddddfddddfddddfddd dfgSdS) N)zquestion-answeringzsequence-classificationZ input_idsbatchsequence)rrZattention_maskZbboxZ pixel_valuesr?heightwidth)rrrr)taskrrBrFrFrGinputss         zLayoutLMv3OnnxConfig.inputscCsdS)NrrFrTrFrFrGatol_for_validationsz(LayoutLMv3OnnxConfig.atol_for_validationcCsdS)NrrFrTrFrFrGdefault_onnx_opsetsz'LayoutLMv3OnnxConfig.default_onnx_opsetFNr(r r) processor batch_size seq_lengthis_pair frameworkr? image_width image_heightrNc Cst|jddt|tjdd}|j|} t|tj| d}d|jj g|gg|} dddd ggg|} | ||||} 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 Z apply_ocrFr)Zfixed_dimensionZnum_token_to_add 0TIr)textZboxesZreturn_tensors) setattrZimage_processorr r Zdefault_fixed_batchZ tokenizerZnum_special_tokens_to_addZdefault_fixed_sequencejoinZ unk_tokenZ_generate_dummy_imagesdict)rBrZr[r\r]r^r?r_r`Z token_to_addZ dummy_textZ dummy_bboxesZ dummy_imagerUrFrFrGgenerate_dummy_inputss0%  z*LayoutLMv3OnnxConfig.generate_dummy_inputs)rXrXFNrrYrY)rHrIrJrparseZtorch_onnx_minimum_versionpropertyrstrintrUfloatrVrWboolrrrirFrFrFrGrMs2   rMN)rK collectionsrtypingrrrr packagingrZconfiguration_utilsr Zonnxr Z onnx.utilsr utilsr Zprocessing_utilsr rZ get_loggerrHloggerZ(LAYOUTLMV3_PRETRAINED_CONFIG_ARCHIVE_MAPrrMrFrFrFrGs"