o Zh}@sldZddlZddlmZddlmZddlmZddlm Z dd l m Z e e ZGd d d eZd gZdS) zVitMatte model configurationN)List)PretrainedConfig)logging) verify_backbone_config_arguments)CONFIG_MAPPINGcsleZdZdZdZddddddddgdgd f d ed ed ed edeedeef fdd Z ddZ Z S)VitMatteConfiga This is the configuration class to store the configuration of [`VitMatteForImageMatting`]. It is used to instantiate a ViTMatte 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 ViTMatte [hustvl/vitmatte-small-composition-1k](https://huggingface.co/hustvl/vitmatte-small-composition-1k) 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 `VitDetConfig()`): 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*, defaults to `False`): Whether to use pretrained weights for the backbone. use_timm_backbone (`bool`, *optional*, defaults to `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 384): The number of input channels of the decoder. batch_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the batch norm layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. convstream_hidden_sizes (`List[int]`, *optional*, defaults to `[48, 96, 192]`): The output channels of the ConvStream module. fusion_hidden_sizes (`List[int]`, *optional*, defaults to `[256, 128, 64, 32]`): The output channels of the Fusion blocks. Example: ```python >>> from transformers import VitMatteConfig, VitMatteForImageMatting >>> # Initializing a ViTMatte hustvl/vitmatte-small-composition-1k style configuration >>> configuration = VitMatteConfig() >>> # Initializing a model (with random weights) from the hustvl/vitmatte-small-composition-1k style configuration >>> model = VitMatteForImageMatting(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ZvitmatteNFigh㈵>g{Gz?)0`)@ backbone_config hidden_sizebatch_norm_epsinitializer_rangeconvstream_hidden_sizesfusion_hidden_sizesc  stjdi| |dur|durtdtddgd}nt|tr2|d} t| } | |}t |||||d||_ ||_ ||_ ||_ ||_||_||_||_| |_| |_dS)NzX`backbone_config` is `None`. Initializing the config with the default `VitDet` backbone.ZvitdetZstage4)Z out_features model_type)use_timm_backboneuse_pretrained_backbonebackbonerbackbone_kwargs)super__init__loggerinfor isinstancedictget from_dictrrrrrrrrrrr)selfrrrrrrrrrrkwargsZbackbone_model_typeZ config_class __class__rb/var/www/auris/lib/python3.10/site-packages/transformers/models/vitmatte/configuration_vitmatte.pyrRs2     zVitMatteConfig.__init__cCs*t|j}|j|d<|jj|d<|S)z Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`]. Returns: `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance, rr)copydeepcopy__dict__rto_dictr(r)r%outputrrr)r-}s  zVitMatteConfig.to_dict) __name__ __module__ __qualname____doc__rrintfloatrrr- __classcell__rrr'r)r s62   +r )r2r*typingrZconfiguration_utilsrutilsrZutils.backbone_utilsrZauto.configuration_autorZ get_loggerr/rr __all__rrrr)s       k