rhaddlmZmZddlmZddlmZddlmZerddl m Z eje Z Gdd eZd gZy ) ) TYPE_CHECKINGOptional)PretrainedConfig)logging)CONFIG_MAPPING)SuperPointConfigceZdZdZdZ ddddedeeedeeeded ed e d e ffd Z e d Z xZ 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 ``` supergluekeypoint_detector_configr hidden_sizekeypoint_encoder_sizesgnn_layers_typesnum_attention_headssinkhorn_iterationsmatching_thresholdinitializer_rangec  ||nddgdz|_td|jDs td||zdk7r td||ngd|_||_||_||_||_||_||_t|tr&|jd d |d <t|d d i|}| td }||_ ||_ d|_d |_t! |Dd i| y) Nselfcross c3$K|]}|dv yw))rrN).0 layer_types /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/superglue/configuration_superglue.py z+SuperGlueConfig.__init__..Vs[z:!22[sz5All gnn_layers_types must be either 'self' or 'cross'rz8hidden_size % num_attention_heads is different from zero) @ model_type superpointFr)rall ValueErrorrrrrr isinstancedictgetr rrattention_probs_dropout_prob is_decodersuper__init__) rrrrrrrrrkwargs __class__s rr.zSuperGlueConfig.__init__Hs-5E4P 0W]_fVgjkVk[TEZEZ[[TU U , , 1WX X'=&H "N` #'&<# 0#6 #6 "4 . 55M5Q5QR^`l5m $\ 2'56N|6\'](*( $ $ +'5l'C'E $(@%!2,-) "6"c0dt|jiS)Nr)typer)rs r sub_configszSuperGlueConfig.sub_configsus*D1N1N,OPPr1)Nr#NNdgg{Gz?)__name__ __module__ __qualname____doc__r$intrliststrfloatr.propertyr4 __classcell__)r0s@rr r s(TJ8<6:04#$#&$'#'+#"4+#+#!)c 3 +# #49- +# ! +#!+#"+#!+#ZQQr1r N)typingrrconfiguration_utilsrutilsrautor r%r get_loggerr7loggerr __all__rr1rrHsI+3!-   H %\Q&\Q~  r1