o i @sdZddlmZddlmZddlmZmZddlm Z m Z ddl m Z m Z ddlmZmZmZeeZGd d d e ZGd d d e Zd d gZd S)zLayoutLM model configuration OrderedDict)Mapping)AnyOptional)PretrainedConfigPreTrainedTokenizer) OnnxConfig PatchingSpec) TensorTypeis_torch_availableloggingcsDeZdZdZdZ          dfdd ZZS)LayoutLMConfiga? This is the configuration class to store the configuration of a [`LayoutLMModel`]. It is used to instantiate a LayoutLM 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 LayoutLM [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) architecture. Configuration objects inherit from [`BertConfig`] and can be used to control the model outputs. Read the documentation from [`BertConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the LayoutLM model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`LayoutLMModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality 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): Dimensionality 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"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability 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 into [`LayoutLMModel`]. 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-12): The epsilon used by the layer normalization layers. pad_token_id (`int`, *optional*, defaults to 0): The value used to pad input_ids. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. max_2d_position_embeddings (`int`, *optional*, defaults to 1024): The maximum value that the 2D position embedding might ever used. Typically set this to something large just in case (e.g., 1024). Examples: ```python >>> from transformers import LayoutLMConfig, LayoutLMModel >>> # Initializing a LayoutLM configuration >>> configuration = LayoutLMConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = LayoutLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```layoutlm:w gelu皙?{Gz?-q=rTc sntjdd| i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_dS)N pad_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_eps use_cachemax_2d_position_embeddings)selfr r!r"r#r%r$r&r'r(r)r*r+rr,r-kwargs __class__rg/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/layoutlm/configuration_layoutlm.pyr^s zLayoutLMConfig.__init__)rrrrrrrrrrrrrTr)__name__ __module__ __qualname____doc__ model_typer __classcell__rrr0r2rs&>rcseZdZ  ddededeeeffdd Ze de ee e efffd d Z dd e de de dedeede eeff fdd ZZS)LayoutLMOnnxConfigdefaultNconfigtaskpatching_specscs"tj|||d|jd|_dS)N)r<r=)rrr-max_2d_positions)r.r;r<r=r0rr2rszLayoutLMOnnxConfig.__init__returncCs8tddddfddddfddddfddddfgS)N input_idsbatchsequence)rr>bboxattention_masktoken_type_idsr)r.rrr2inputss    zLayoutLMOnnxConfig.inputsF tokenizer batch_size seq_lengthis_pair frameworkc sztj|||||d}gd}|tjkstdtstdddl}|dj\}}| g|g| |dd|d <|S) a Generate inputs to provide to the ONNX exporter for the specific framework Args: tokenizer: The tokenizer associated with this model configuration batch_size: The batch size (int) to export the model for (-1 means dynamic axis) seq_length: The sequence length (int) to export the model for (-1 means dynamic axis) is_pair: Indicate if the input is a pair (sentence 1, sentence 2) framework: The framework (optional) the tokenizer will generate tensor for Returns: Mapping[str, Tensor] holding the kwargs to provide to the model's forward function )rJrKrLrM)0TIzCExporting LayoutLM to ONNX is currently only supported for PyTorch.z7Cannot generate dummy inputs without PyTorch installed.rNrAr>rD) rgenerate_dummy_inputsr PYTORCHNotImplementedErrorr ValueErrortorchshapetensortile) r.rIrJrKrLrM input_dictboxrVr0rr2rRs  "z(LayoutLMOnnxConfig.generate_dummy_inputs)r:N)rHrHFN)r3r4r5rstrrlistr rpropertyrintrGr boolr rrRr8rrr0r2r9s:    r9N)r6 collectionsrcollections.abcrtypingrrrr onnxr r utilsr r r get_loggerr3loggerrr9__all__rrrr2s   e >