sg$dZddlmZddlmZddlmZddlmZddl m Z ddl m Z e jeZGd d eZGd d e Zy )z"Data2VecVision model configuration OrderedDict)Mapping)version)PretrainedConfig) OnnxConfig)loggingcfeZdZdZdZddddddddd d d d d d d d dddgdgdddddd dffd ZxZS)Data2VecVisionConfigaJ This is the configuration class to store the configuration of a [`Data2VecVisionModel`]. It is used to instantiate an Data2VecVision 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 Data2VecVision [facebook/data2vec-vision-base](https://huggingface.co/facebook/data2vec-vision-base) architecture. 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. use_mask_token (`bool`, *optional*, defaults to `False`): Whether to use a mask token for masked image modeling. use_absolute_position_embeddings (`bool`, *optional*, defaults to `False`): Whether to use BERT-style absolute position embeddings. use_relative_position_bias (`bool`, *optional*, defaults to `False`): Whether to use T5-style relative position embeddings in the self-attention layers. use_shared_relative_position_bias (`bool`, *optional*, defaults to `False`): Whether to use the same relative position embeddings across all self-attention layers of the Transformer. layer_scale_init_value (`float`, *optional*, defaults to 0.1): Scale to use in the self-attention layers. 0.1 for base, 1e-5 for large. Set 0 to disable layer scale. drop_path_rate (`float`, *optional*, defaults to 0.1): Stochastic depth rate per sample (when applied in the main path of residual layers). use_mean_pooling (`bool`, *optional*, defaults to `True`): Whether to mean pool the final hidden states of the patches instead of using the final hidden state of the CLS token, before applying the classification head. out_indices (`List[int]`, *optional*, defaults to `[3, 5, 7, 11]`): Indices of the feature maps to use for semantic segmentation. pool_scales (`Tuple[int]`, *optional*, defaults to `[1, 2, 3, 6]`): Pooling scales used in Pooling Pyramid Module applied on the last feature map. use_auxiliary_head (`bool`, *optional*, defaults to `True`): Whether to use an auxiliary head during training. auxiliary_loss_weight (`float`, *optional*, defaults to 0.4): Weight of the cross-entropy loss of the auxiliary head. auxiliary_channels (`int`, *optional*, defaults to 256): Number of channels to use in the auxiliary head. auxiliary_num_convs (`int`, *optional*, defaults to 1): Number of convolutional layers to use in the auxiliary head. auxiliary_concat_input (`bool`, *optional*, defaults to `False`): Whether to concatenate the output of the auxiliary head with the input before the classification layer. semantic_loss_ignore_index (`int`, *optional*, defaults to 255): The index that is ignored by the loss function of the semantic segmentation model. Example: ```python >>> from transformers import Data2VecVisionConfig, Data2VecVisionModel >>> # Initializing a Data2VecVision data2vec_vision-base-patch16-224-in22k style configuration >>> configuration = Data2VecVisionConfig() >>> # Initializing a model (with random weights) from the data2vec_vision-base-patch16-224-in22k style configuration >>> model = Data2VecVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```zdata2vec-visioni i gelugg{Gz?g-q=rFg?T)r )rg?rc 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_channelsuse_mask_token use_absolute_position_embeddingsuse_relative_position_bias!use_shared_relative_position_biaslayer_scale_init_valuedrop_path_rateuse_mean_pooling out_indices pool_scalesuse_auxiliary_headauxiliary_loss_weightauxiliary_channelsauxiliary_num_convsauxiliary_concat_inputsemantic_loss_ignore_index)selfrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4r5r6r7kwargs __class__s m/var/www/html/venv/lib/python3.12/site-packages/transformers/models/data2vec/configuration_data2vec_vision.pyrzData2VecVisionConfig.__init__ps> "6"&!2#6 !2$#6 ,H)!2,$$(,0P-*D'1R.&<#, 0&&"4%:""4#6 &<#*D')__name__ __module__ __qualname____doc__ model_typer __classcell__)r:s@r;r r spM ^#J%().#(*/"! !$#&9>E>Er<r cpeZdZejdZedeeee efffdZ ede fdZ y)Data2VecVisionOnnxConfigz1.11returnc(tddddddfgS)N pixel_valuesbatchr(heightwidth)rrrrrr8s r;inputszData2VecVisionOnnxConfig.inputss&WHQX!YZ   r<cy)Ng-C6?rrKs r;atol_for_validationz,Data2VecVisionOnnxConfig.atol_for_validationsr<N) r=r>r?rparsetorch_onnx_minimum_versionpropertyrstrintrLfloatrNrr<r;rDrDsZ!.v!6  WS#X%6 67  Ur<rDN)r@ collectionsrtypingr packagingrconfiguration_utilsronnxr utilsr get_loggerr=loggerr rDrr<r;r]sN)#3   H %PE+PEh z r<