qi#xdZddlmZddlmZddlmZddlmZeje Z GddeZ dgZ y ) zUperNet model configuration)%consolidate_backbone_kwargs_to_config)PreTrainedConfig)logging) AutoConfigc JeZdZdZdZdeiZdddgddd dd d d d f fd ZxZS) UperNetConfiga This is the configuration class to store the configuration of an [`UperNetForSemanticSegmentation`]. It is used to instantiate an UperNet 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 UperNet [openmmlab/upernet-convnext-tiny](https://huggingface.co/openmmlab/upernet-convnext-tiny) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: backbone_config (`PreTrainedConfig` or `dict`, *optional*, defaults to `ResNetConfig()`): The configuration of the backbone model. hidden_size (`int`, *optional*, defaults to 512): The number of hidden units in the convolutional layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. 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. loss_ignore_index (`int`, *optional*, defaults to 255): The index that is ignored by the loss function. Examples: ```python >>> from transformers import UperNetConfig, UperNetForSemanticSegmentation >>> # Initializing a configuration >>> configuration = UperNetConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = UperNetForSemanticSegmentation(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```upernetbackbone_configNig{Gz?)rrTg?r Fc  td|ddgdid| \}} ||_||_||_||_||_||_||_||_| |_ | |_ | |_ t |4di| y)Nresnet out_features)stage1stage2stage3stage4)r default_config_typedefault_config_kwargs)rr hidden_sizeinitializer_range pool_scalesuse_auxiliary_headauxiliary_loss_weightauxiliary_in_channelsauxiliary_channelsauxiliary_num_convsauxiliary_concat_inputloss_ignore_indexsuper__init__)selfr rrrrrrr r!r"r#kwargs __class__s c/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/upernet/configuration_upernet.pyr%zUperNetConfig.__init__Ks#H# + ( H##  #  /&!2&"4%:"%:""4#6 &<#!2 "6") __name__ __module__ __qualname____doc__ model_typer sub_configsr% __classcell__)r(s@r)r r sG, \J$j1K !"$$#$#r*r N)r.backbone_utilsrconfiguration_utilsrutilsrauto.configuration_autor get_loggerr+loggerr __all__rr*r)r9sD"C30   H %V#$V#r  r*