o Zh8@slddlmZmZmZddlmZddlmZddlm Z er$ddl m Z e e ZGdd d eZd gZd S) ) TYPE_CHECKINGListOptional)PretrainedConfig)logging)CONFIG_MAPPING)SuperPointConfigcsheZdZdZdZ        dd d d ed eeed eeededede de ffdd Z Z S)SuperGlueConfiga This is the configuration class to store the configuration of a [`SuperGlueModel`]. It is used to instantiate a SuperGlue 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 SuperGlue [magic-leap-community/superglue_indoor](https://huggingface.co/magic-leap-community/superglue_indoor) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: keypoint_detector_config (`Union[AutoConfig, dict]`, *optional*, defaults to `SuperPointConfig`): The config object or dictionary of the keypoint detector. hidden_size (`int`, *optional*, defaults to 256): The dimension of the descriptors. keypoint_encoder_sizes (`List[int]`, *optional*, defaults to `[32, 64, 128, 256]`): The sizes of the keypoint encoder layers. gnn_layers_types (`List[str]`, *optional*, defaults to `['self', 'cross', 'self', 'cross', 'self', 'cross', 'self', 'cross', 'self', 'cross', 'self', 'cross', 'self', 'cross', 'self', 'cross', 'self', 'cross']`): The types of the GNN layers. Must be either 'self' or 'cross'. num_attention_heads (`int`, *optional*, defaults to 4): The number of heads in the GNN layers. sinkhorn_iterations (`int`, *optional*, defaults to 100): The number of Sinkhorn iterations. matching_threshold (`float`, *optional*, defaults to 0.0): The matching threshold. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Examples: ```python >>> from transformers import SuperGlueConfig, SuperGlueModel >>> # Initializing a SuperGlue superglue style configuration >>> configuration = SuperGlueConfig() >>> # Initializing a model from the superglue style configuration >>> model = SuperGlueModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` Z superglueNd{Gz?keypoint_detector_configr hidden_sizekeypoint_encoder_sizesgnn_layers_typesnum_attention_headssinkhorn_iterationsmatching_thresholdinitializer_rangec  s|dur|nddgd|_tdd|jDstd||dkr%td|dur+|ngd |_||_||_||_||_||_||_t|t r^d |vrO|d nd |d <t |d d i|}|durgt d }||_ ||_ d|_ d |_tjd i| dS)Nselfcross css|]}|dvVqdS))rrN).0Z layer_typerrd/var/www/auris/lib/python3.10/site-packages/transformers/models/superglue/configuration_superglue.py Vsz+SuperGlueConfig.__init__..z5All gnn_layers_types must be either 'self' or 'cross'rz8hidden_size % num_attention_heads is different from zero) @r model_type superpointFr)rall ValueErrorrrrrr isinstancedictr rrZattention_probs_dropout_probZ is_decodersuper__init__) rrrrrrrrrkwargs __class__rrr*Hs4    zSuperGlueConfig.__init__)Nr NNr rrr) __name__ __module__ __qualname____doc__r#intrrstrfloatr* __classcell__rrr,rr s8*   r N)typingrrrZconfiguration_utilsrutilsrautor r$r Z get_loggerr.loggerr __all__rrrrs      ]