ó <±haãó’•SSKJrJr SSKJr SSKJr SSKJr \(aSSK J r \R"\5r "SS \5rS /rg )é)Ú TYPE_CHECKINGÚOptionalé)ÚPretrainedConfig)Úloggingé)ÚCONFIG_MAPPING)ÚSuperPointConfigcó^•\rSrSrSrSrSSSS\S\\\S\\\ S \S \S\ S\ 4U4S jjjr\S5r SrU=r$)ÚSuperGlueConfigéa€ 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 ``` Ú superglueÚkeypoint_detector_configr Úhidden_sizeÚkeypoint_encoder_sizesÚgnn_layers_typesÚnum_attention_headsÚsinkhorn_iterationsÚmatching_thresholdÚinitializer_rangec óø>•UbUOSS/S-Ul[SUR55(d[S5eX%-S:wa[S5eUbUO/SQUlX lX0lX@lXPlX`lXpl[U[5(a'URS S 5US '[US "S0UD6nUc[S "5nXlX€l SUlSUl[ T U]D"S0U D6 g) NÚselfÚcrossé c3ó(# •UH oS;v• M g7f))rrN©)Ú.0Ú layer_types Úm/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/superglue/configuration_superglue.pyÚ Ú+SuperGlueConfig.__init__..Vsé€Ð[ÑEZ°zÐ!2Ö2ÒEZùs‚z5All gnn_layers_types must be either 'self' or 'cross'rz8hidden_size % num_attention_heads is different from zero)é é@é€éÚ model_typeÚ superpointFr)rÚallÚ ValueErrorrrrrrÚ isinstanceÚdictÚgetr rrÚattention_probs_dropout_probÚ is_decoderÚsuperÚ__init__)rrrrrrrrrÚkwargsÚ __class__s €rr0ÚSuperGlueConfig.__init__Hs ø€ð5EÑ4PÑ 0ÐW]Ð_fÐVgÐjkÑVkˆÔäÑ[ÀT×EZÒEZÓ[×[Ñ[ÜÐTÓUÐUàÑ,°Ó1ÜÐWÓXÐXð'=Ñ&HÑ"ÒN`ð Ô#ð'ÔØ&<Ô#Ø 0ÔØ#6Ô Ø#6Ô Ø"4ÔäÐ.´×5Ñ5Ø5M×5QÑ5QÐR^Ð`lÓ5mÐ$ \Ñ2Ü'5Ð6NÈ|Ñ6\Ò']ñ(Ø*ñ(Ð$ð$Ñ+Ü'5°lÒ'CÓ'EÐ$à(@Ô%Ø!2ÔØ,-ˆÔ)ØˆŒä ‰ÒÑ"˜6Ó"ócó0•S[UR50$)Nr)Útyper)rs rÚsub_configsÚSuperGlueConfig.sub_configsus€à*¬D°×1NÑ1NÓ,OÐPÐPr4) r-rrrr.rrrrr)Nr%NNéédgg{®Gáz”?)Ú__name__Ú __module__Ú__qualname__Ú__firstlineno__Ú__doc__r&ÚintrÚlistÚstrÚfloatr0Úpropertyr7Ú__static_attributes__Ú __classcell__)r2s@rrrs«ø†ñ(ðT€Jð8<ØØ6:Ø04Ø#$Ø#&Ø$'Ø#'ñ+#à"4ð+#ðð+#ð!)¨¨c©Ñ 3ð +#ð # 4¨¡9Ñ-ð+#ð!ð +#ð!ð+#ð"ð+#ð!÷+#ð+#ðZñQóöQr4rN)ÚtypingrrÚconfiguration_utilsrÚutilsrÚautor r'r Ú get_loggerr;ÚloggerrÚ__all__rr4rÚrNsGð÷+å3ÝÝ!öÝ-à × Ò ˜HÓ %€ô\QÐ&ô\Qð~Ð r4