U 5Af@sRdZddlmZddlmZddlmZddlmZe e Z GdddeZ d S) zUperNet model configuration)PretrainedConfig)logging) verify_backbone_config_arguments)CONFIG_MAPPINGcsLeZdZdZdZdddddddddd d gd d d ddddffdd ZZS) 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. backbone (`str`, *optional*): Name of backbone to use when `backbone_config` is `None`. If `use_pretrained_backbone` is `True`, this will load the corresponding pretrained weights from the timm or transformers library. If `use_pretrained_backbone` is `False`, this loads the backbone's config and uses that to initialize the backbone with random weights. use_pretrained_backbone (`bool`, *optional*, `False`): Whether to use pretrained weights for the backbone. use_timm_backbone (`bool`, *optional*, `False`): Whether to load `backbone` from the timm library. If `False`, the backbone is loaded from the transformers library. backbone_kwargs (`dict`, *optional*): Keyword arguments to be passed to AutoBackbone when loading from a checkpoint e.g. `{'out_indices': (0, 1, 2, 3)}`. Cannot be specified if `backbone_config` is set. 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 ```ZupernetNFig{Gz?rrTg?ic stjf||dkr@|dkr@tdtdddddgd}n&t|trf|d}t|}||}t |||||d ||_ ||_ ||_ ||_ ||_||_||_||_| |_| |_| |_| |_| |_||_||_dS) NzX`backbone_config` is `None`. Initializing the config with the default `ResNet` backbone.ZresnetZstage1Zstage2Zstage3Zstage4)Z out_features model_type)use_timm_backboneuse_pretrained_backbonebackbonebackbone_configbackbone_kwargs)super__init__loggerinfor isinstancedictget from_dictrrrrr r hidden_sizeinitializer_range pool_scalesuse_auxiliary_headauxiliary_loss_weightauxiliary_in_channelsauxiliary_channelsauxiliary_num_convsauxiliary_concat_inputloss_ignore_index)selfrrrr rrrrrrrr r!r"r#kwargsZbackbone_model_typeZ config_class __class__U/tmp/pip-unpacked-wheel-zw5xktn0/transformers/models/upernet/configuration_upernet.pyrWs<    zUperNetConfig.__init__)__name__ __module__ __qualname____doc__r r __classcell__r(r(r&r)rs$: rN) r-Zconfiguration_utilsrutilsrZutils.backbone_utilsrZauto.configuration_autorZ get_loggerr*rrr(r(r(r)s