qiG`dZddlmZddlmZej eZGddeZdgZ y)zYOLOS model configuration)PreTrainedConfig)loggingcXeZdZdZdZddddddddd d d gd d ddddddddddffd ZxZS) YolosConfiga This is the configuration class to store the configuration of a [`YolosModel`]. It is used to instantiate a YOLOS 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 YOLOS [hustvl/yolos-base](https://huggingface.co/hustvl/yolos-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: 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 (`list[int]`, *optional*, defaults to `[512, 864]`): 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. num_detection_tokens (`int`, *optional*, defaults to 100): The number of detection tokens. use_mid_position_embeddings (`bool`, *optional*, defaults to `True`): Whether to use the mid-layer position encodings. auxiliary_loss (`bool`, *optional*, defaults to `False`): Whether auxiliary decoding losses (loss at each decoder layer) are to be used. class_cost (`float`, *optional*, defaults to 1): Relative weight of the classification error in the Hungarian matching cost. bbox_cost (`float`, *optional*, defaults to 5): Relative weight of the L1 error of the bounding box coordinates in the Hungarian matching cost. giou_cost (`float`, *optional*, defaults to 2): Relative weight of the generalized IoU loss of the bounding box in the Hungarian matching cost. bbox_loss_coefficient (`float`, *optional*, defaults to 5): Relative weight of the L1 bounding box loss in the object detection loss. giou_loss_coefficient (`float`, *optional*, defaults to 2): Relative weight of the generalized IoU loss in the object detection loss. eos_coefficient (`float`, *optional*, defaults to 0.1): Relative classification weight of the 'no-object' class in the object detection loss. Example: ```python >>> from transformers import YolosConfig, YolosModel >>> # Initializing a YOLOS hustvl/yolos-base style configuration >>> configuration = YolosConfig() >>> # Initializing a model (with random weights) from the hustvl/yolos-base style configuration >>> model = YolosModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```yolosi i gelugg{Gz?g-q=ii`rTdFg?c Xt|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_biasnum_detection_tokensuse_mid_position_embeddingsauxiliary_loss class_cost bbox_cost giou_costbbox_loss_coefficientgiou_loss_coefficienteos_coefficient)selfrrrrrrrrrrrrrr r!r"r#r$r%r&r'r(kwargs __class__s _/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/yolos/configuration_yolos.pyrzYolosConfig.__init__as4 "6"&!2#6 !2$#6 ,H)!2,$$(  $8!+F(,$""%:"%:".)__name__ __module__ __qualname____doc__ model_typer __classcell__)r+s@r,rrscE NJ%(: $(/3/3/r-rN) r1configuration_utilsrutilsr get_loggerr.loggerr__all__rr-r,r9s= 3   H %}/"}/@ /r-