T^(hurdZddlmZddlmZddlmZmZeje Z GddeeZ dgZ y)zVitDet model configuration)PretrainedConfig)logging)BackboneConfigMixin*get_aligned_output_features_output_indicescReZdZdZdZdddddddd d d d d d dggd ddddffd ZxZS) VitDetConfiga This is the configuration class to store the configuration of a [`VitDetModel`]. It is used to instantiate an VitDet 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 VitDet [google/vitdet-base-patch16-224](https://huggingface.co/google/vitdet-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. mlp_ratio (`int`, *optional*, defaults to 4): Ratio of mlp hidden dim to embedding dim. 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. dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. 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-06): The epsilon used by the layer normalization layers. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. pretrain_image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image during pretraining. 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. drop_path_rate (`float`, *optional*, defaults to 0.0): Stochastic depth rate. window_block_indices (`List[int]`, *optional*, defaults to `[]`): List of indices of blocks that should have window attention instead of regular global self-attention. residual_block_indices (`List[int]`, *optional*, defaults to `[]`): List of indices of blocks that should have an extra residual block after the MLP. use_absolute_position_embeddings (`bool`, *optional*, defaults to `True`): Whether to add absolute position embeddings to the patch embeddings. use_relative_position_embeddings (`bool`, *optional*, defaults to `False`): Whether to add relative position embeddings to the attention maps. window_size (`int`, *optional*, defaults to 0): The size of the attention window. out_features (`List[str]`, *optional*): If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc. (depending on how many stages the model has). If unset and `out_indices` is set, will default to the corresponding stages. If unset and `out_indices` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. out_indices (`List[int]`, *optional*): If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and `out_features` is set, will default to the corresponding stages. If unset and `out_features` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. Example: ```python >>> from transformers import VitDetConfig, VitDetModel >>> # Initializing a VitDet configuration >>> configuration = VitDetConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = VitDetModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```vitdeti gelugg{Gz?gư>rTFNc t|di|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_||_dgt+d|jdzDcgc]}d| c}z|_t/|||j,\|_|_ycc}w)Nstemstage) out_features out_indices stage_names)super__init__ hidden_sizenum_hidden_layersnum_attention_heads mlp_ratio hidden_act dropout_probinitializer_rangelayer_norm_eps image_sizepretrain_image_size patch_size num_channelsqkv_biasdrop_path_ratewindow_block_indicesresidual_block_indices use_absolute_position_embeddings use_relative_position_embeddings window_sizerangerr _out_features _out_indices)selfrrrrrrr r!r"r#r$r%r&r'r(r)r*r+r,rrkwargsidx __class__s m/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/vitdet/configuration_vitdet.pyrzVitDetConfig.__init__gs2 "6"&!2#6 "$(!2,$#6 $(  ,$8!&<#0P-0P-&"8aI_I_bcIc@d&ese}&ee0Z%;DL\L\1 -D-'fs3 C/)__name__ __module__ __qualname____doc__ model_typer __classcell__)r3s@r4rrs\I VJ!)-).-2 2 rN) r8configuration_utilsrutilsrutils.backbone_utilsrr get_loggerr5loggerr__all__rr;r4rBsD!3c   H %@ &(8@ F  r;