sgdZddlmZddlmZddlmZddlmZddl m Z ddl m Z e jeZGd d eZGd d e Zy )zViT model configuration OrderedDict)Mapping)version)PretrainedConfig) OnnxConfig)loggingcDeZdZdZdZ dfd ZxZS) ViTConfiga This is the configuration class to store the configuration of a [`ViTModel`]. It is used to instantiate an ViT 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 ViT [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: 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"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. 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. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. encoder_stride (`int`, *optional*, defaults to 16): Factor to increase the spatial resolution by in the decoder head for masked image modeling. Example: ```python >>> from transformers import ViTConfig, ViTModel >>> # Initializing a ViT vit-base-patch16-224 style configuration >>> configuration = ViTConfig() >>> # Initializing a model (with random weights) from the vit-base-patch16-224 style configuration >>> model = ViTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```vitc t|di|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_y)N)super__init__ hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_biasencoder_stride)selfrrrrrrrrrrrrrrkwargs __class__s \/var/www/html/venv/lib/python3.12/site-packages/transformers/models/vit/configuration_vit.pyrzViTConfig.__init__Ys$ "6"&!2#6 !2$#6 ,H)!2,$$(  ,)i r%i gelur'g{Gz?g-q=rTr))__name__ __module__ __qualname____doc__ model_typer __classcell__)r"s@r#r r sF6 pJ%(!-!-r$r cpeZdZejdZedeeee efffdZ ede fdZ y) ViTOnnxConfigz1.11returnc(tddddddfgS)N pixel_valuesbatchrheightwidth)rrrr s r#inputszViTOnnxConfig.inputss&WHQX!YZ   r$cy)Ng-C6?rr:s r#atol_for_validationz!ViTOnnxConfig.atol_for_validationsr$N) r*r+r,rparsetorch_onnx_minimum_versionpropertyrstrintr;floatr=rr$r#r1r1}sZ!.v!6  WS#X%6 67  Ur$r1N)r- collectionsrtypingr packagingrconfiguration_utilsronnxr utilsr get_loggerr*loggerr r1rr$r#rLsL#3   H %\- \-~ J r$