+
    œ°³jj  ã                   óh   € ^ RI Ht ^RIHt ^RIHt ]! RR7      ] ! R R]4      4       4       tR.tR# )	é    )Ústrict)ÚPreTrainedConfig)Úauto_docstringzzju-community/efficientloftr)Ú
checkpointc                   ó¬   a a€ ] tR t^t oRtRtRtRtRtRt	Rt
^t^t^t^t^t^tRtRtRtRtR	tR
t^t^tRtRt^tRtRtV 3R ltR tV3R lt Rt!Vt"V ;t## )ÚEfficientLoFTRConfiga²	  
stage_num_blocks (`List`, *optional*, defaults to [1, 2, 4, 14]):
    The number of blocks in each stages
stage_stride (`List`, *optional*, defaults to [2, 1, 2, 2]):
    The stride used in each stage
q_aggregation_kernel_size (`int`, *optional*, defaults to 4):
    The kernel size of the aggregation of query states in the fusion network
kv_aggregation_kernel_size (`int`, *optional*, defaults to 4):
    The kernel size of the aggregation of key and value states in the fusion network
q_aggregation_stride (`int`, *optional*, defaults to 4):
    The stride of the aggregation of query states in the fusion network
kv_aggregation_stride (`int`, *optional*, defaults to 4):
    The stride of the aggregation of key and value states in the fusion network
num_attention_layers (`int`, *optional*, defaults to 4):
    Number of attention layers in the LocalFeatureTransformer
mlp_activation_function (`str`, *optional*, defaults to `"leaky_relu"`):
    Activation function used in the attention mlp layer.
coarse_matching_skip_softmax (`bool`, *optional*, defaults to `False`):
    Whether to skip softmax or not at the coarse matching step.
coarse_matching_threshold (`float`, *optional*, defaults to 0.2):
    The threshold for the minimum score required for a match.
coarse_matching_temperature (`float`, *optional*, defaults to 0.1):
    The temperature to apply to the coarse similarity matrix
coarse_matching_border_removal (`int`, *optional*, defaults to 2):
    The size of the border to remove during coarse matching
fine_kernel_size (`int`, *optional*, defaults to 8):
    Kernel size used for the fine feature matching
batch_norm_eps (`float`, *optional*, defaults to 1e-05):
    The epsilon used by the batch normalization layers
fine_matching_slice_dim (`int`, *optional*, defaults to 8):
    The size of the slice used to divide the fine features for the first and second fine matching stages.
fine_matching_regress_temperature (`float`, *optional*, defaults to 10.0):
    The temperature to apply to the fine similarity matrix

Examples:
    ```python
    >>> from transformers import EfficientLoFTRConfig, EfficientLoFTRForKeypointMatching

    >>> # Initializing a EfficientLoFTR configuration
    >>> configuration = EfficientLoFTRConfig()

    >>> # Initializing a model from the EfficientLoFTR configuration
    >>> model = EfficientLoFTRForKeypointMatching(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```
ÚefficientloftrNé   Úrelug        FÚ
leaky_relugš™™™™™É?gš™™™™™¹?gñhãˆµøä>g      $@g{®Gáz”?c                ó  <€ V P                   e   V P                   M. ROV n         V P                  e   V P                  M. ROV n        V P                  e   V P                  M. ROV n        ^.V P                  R R ,           V n        \	        V P                  V P                   4       UUu. uF  w  r#V.^.V^,
          ,          ,           NK   	  uppV n        \        V P                   4       UUu. uF   w  rCV P                  V,          .V,          NK"  	  uppV n        \        \        V P                   4      4       Uu. uF2  pV P                  V,          .V P                  V,          R R ,           NK4  	  upV n
        V P                  V n        \        \        V P                  4      4      R R V n        V P                   ^,          V n        VP%                  RR4       \&        SV `P  ! R/ VB  R # u uppi u uppi u upi )NÚpartial_rotary_factorg      @)é   é   é   é   )r   r   r   r   )é@   r   é€   r
   éÿÿÿÿ© )Ústage_num_blocksÚstage_strideÚout_featuresÚstage_in_channelsÚzipÚstage_block_strideÚ	enumerateÚstage_block_out_channelsÚrangeÚlenÚstage_block_in_channelsÚnum_attention_headsÚnum_key_value_headsÚlistÚreversedÚfine_fusion_dimsÚhidden_sizeÚintermediate_sizeÚ
setdefaultÚsuperÚ__post_init__)ÚselfÚkwargsÚstrideÚ
num_blocksÚ	stage_idxÚ	__class__s   &,   €Ú€/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/efficientloftr/configuration_efficientloftr.pyr+   Ú"EfficientLoFTRConfig.__post_init__e   sÕ  ø€ à9=×9NÑ9NÒ9Z × 5Ò 5Ò`mˆÔØ15×1BÑ1BÒ1N˜D×-Ò-ÒT`ˆÔØ15×1BÑ1BÒ1N˜D×-Ò-ÒTfˆÔØ"#  t×'8Ñ'8¸¸"Ð'=Õ!=ˆÔô ILÈD×L]ÑL]Ð_c×_tÑ_tÔHuô#
ÙHuÑ2D°&ˆVˆH˜�s˜j¨1�nÕ-×-Ð-ÑHuò#
ˆÔô V_Ð_c×_tÑ_tÔUuô)
ÙUuÑ<Q¸IˆT×Ñ˜yÕ)Ð*¨Z×7Ð7ÑUuò)
ˆÔ%ô
 #¤3 t×'<Ñ'<Ó#=Ô>ó(
á>�	ð ×#Ñ# IÕ.Ð/°$×2OÑ2OÐPYÕ2ZÐ[^Ð\^Ð2_×_Ð_Ù>ñ(
ˆÔ$ð
 $(×#;Ñ#;ˆÔ Ü $¤X¨d×.?Ñ.?Ó%@Ó AÀ#À2Ð FˆÔØ!%×!1Ñ!1°AÕ!5ˆÔØ×ÑÐ1°3Ô7Ü‰ÒÑ' Ô'ùó#
ùó)
ùò(
s   Â*$G1Ã/&G7Ä>8G=c                ó¢   € V P                   V P                  R,          8w  d-   \        RV P                    RV P                  R,           24      hR# )zOPart of `@strict`-powered validation. Validates the architecture of the config.zMhidden_size should be equal to the last value in out_features. hidden_size = z, out_features = Nr   )r'   r   Ú
ValueError)r,   s   &r2   Úvalidate_architectureÚ*EfficientLoFTRConfig.validate_architecture~   ss   € à×Ñ˜t×0Ñ0°Õ4Ô4ÜØ_Ð`d×`pÑ`pÐ_qð  rCð  DH÷  DUñ  DUð  VXõ  DYð  CZð  [óð ñ 5ó    c                ó²  <€ V ^8„  d   Qh/ S[ S[,          R,          ;R&   S[ S[,          R,          ;R&   S[ S[,          R,          ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R	&   S[;R
&   S[;R&   S[;R&   S[S[,          ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[R,          ;R&   S[;R&   S[;R&   S[;R&   # )r   Nr   r   r   r'   Úactivation_functionÚq_aggregation_kernel_sizeÚkv_aggregation_kernel_sizeÚq_aggregation_strideÚkv_aggregation_strideÚnum_attention_layersr"   Úattention_dropoutÚattention_biasÚmlp_activation_functionÚcoarse_matching_skip_softmaxÚcoarse_matching_thresholdÚcoarse_matching_temperatureÚcoarse_matching_border_removalÚfine_kernel_sizeÚbatch_norm_epsÚrope_parametersÚfine_matching_slice_dimÚ!fine_matching_regress_temperatureÚinitializer_range)r$   ÚintÚstrÚfloatÚboolÚdict)ÚformatÚ__classdict__s   "€r2   Ú__annotate__Ú!EfficientLoFTRConfig.__annotate__   s�  ø‡ ‚ ñl ™3•i $Õ&Ñ-ñm ñn ‘s•)˜dÕ"Ñ)ño ñp ‘s•)˜dÕ"Ñ)ñq ñr Ññs ñt Ñ%ñu ñv  #Ñ&ñw ñx !$Ñ'ñy ñz Ñ!ñ{ ñ| Ñ"ñ} ñ~ Ñ!ñ ñ@ Ñ ñA ñB ™s•{Ñ(ñC ñD Ñ ñE ñF !Ñ/ñG ñH #'Ñ.ñI ñJ  %Ñ*ñK ñL "'Ñ,ñM ñN %(Ñ+ñO ñP ÑñQ ñR Ñ ñS ñT ˜D•[Ñ'ñU ñV !Ñ$ñW ñX (-Ñ3ñY ñZ Ñ#ò[ r8   )
r&   r(   r#   r   r!   r   r   r   r   r   )$Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typer   r   r   r'   r:   r;   r<   r=   r>   r?   r"   r@   rA   rB   rC   rD   rE   rF   rG   rH   rI   rJ   rK   rL   r+   r6   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r1   rS   s   @@r2   r   r      s®   ù‡ € ñ/ðb "€Jà)-ÐØ%)€LØ%)€LØ€KØ%ÐØ%&ÐØ&'ÐØ !ÐØ!"ÐØ !ÐØ ÐØ%(ÐØ €NØ#/ÐØ).Ð Ø'*ÐØ),ÐØ*+Ð"ØÐØ €NØ#'€OØ#$ÐØ/3Ð%Ø#Ðõ(ò2÷Q … r8   r   N)Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r   r8   r2   Ú<module>rd      sH   ðõ  /å 3Ý #ñ Ð9Ô:ØôkÐ+ó kó ó ;ðkð\ "Ð
"‚r8   