o Zh@sddZddlmZddlmZddlmZddlmZddl m Z e e Z Gd d d eZd gZd S) zVitPose model configuration)Optional)PretrainedConfig)logging) verify_backbone_config_arguments)CONFIG_MAPPINGcsdeZdZdZdZ        ddeed eed ed ed ee d e de deffdd Z Z S) VitPoseConfiga This is the configuration class to store the configuration of a [`VitPoseForPoseEstimation`]. It is used to instantiate a VitPose 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 VitPose [usyd-community/vitpose-base-simple](https://huggingface.co/usyd-community/vitpose-base-simple) 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 `VitPoseBackboneConfig()`): The configuration of the backbone model. Currently, only `backbone_config` with `vitpose_backbone` as `model_type` is supported. 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. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. scale_factor (`int`, *optional*, defaults to 4): Factor to upscale the feature maps coming from the ViT backbone. use_simple_decoder (`bool`, *optional*, defaults to `True`): Whether to use a `VitPoseSimpleDecoder` to decode the feature maps from the backbone into heatmaps. Otherwise it uses `VitPoseClassicDecoder`. Example: ```python >>> from transformers import VitPoseConfig, VitPoseForPoseEstimation >>> # Initializing a VitPose configuration >>> configuration = VitPoseConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = VitPoseForPoseEstimation(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ZvitposeNF{Gz?Tbackbone_configbackboneuse_pretrained_backboneuse_timm_backbonebackbone_kwargsinitializer_range scale_factoruse_simple_decoderc  stjd i| |rtd|rtd|dur,|dur,tdtddgd}nt|tr?|d} t| } | |}t |||||d||_ ||_ ||_ ||_||_||_||_||_dS) Nzl`use_pretrained_backbone` is `True`. For the pure inference purpose of VitPose weight do not set this value.zs       b