qi$,ddlmZGddeZdgZy))PreTrainedConfigc1eZdZdZdZ ddeedzdeedzdeedzdeded ed ed ed ed ededede dede dededededede dzdededef0fd Z xZ S)EfficientLoFTRConfigad This is the configuration class to store the configuration of a [`EfficientLoFTRFromKeypointMatching`]. It is used to instantiate a EfficientLoFTR 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 EfficientLoFTR [zju-community/efficientloftr](https://huggingface.co/zju-community/efficientloftr) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: stage_num_blocks (`List`, *optional*, defaults to [1, 2, 4, 14]): The number of blocks in each stages out_features (`List`, *optional*, defaults to [64, 64, 128, 256]): The number of channels in each stage stage_stride (`List`, *optional*, defaults to [2, 1, 2, 2]): The stride used in each stage hidden_size (`int`, *optional*, defaults to 256): The dimension of the descriptors. activation_function (`str`, *optional*, defaults to `"relu"`): The activation function used in the backbone 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 num_attention_heads (`int`, *optional*, defaults to 8): The number of heads in the GNN layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. attention_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in the query, key, value and output projection layers during attention. 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 rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. 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 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 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 ``` efficientloftrNstage_num_blocks out_features stage_stride hidden_sizeactivation_functionq_aggregation_kernel_sizekv_aggregation_kernel_sizeq_aggregation_stridekv_aggregation_stridenum_attention_layersnum_attention_headsattention_dropoutattention_biasmlp_activation_functioncoarse_matching_skip_softmaxcoarse_matching_thresholdcoarse_matching_temperaturecoarse_matching_border_removalfine_kernel_sizebatch_norm_epsrope_parametersfine_matching_slice_dim!fine_matching_regress_temperatureinitializer_rangec ||ngd|_||ngd|_||ngd|_dg|jddz|_t |j|jDcgc]\}}|gdg|dz zzc}}|_t |jDcgc]\}}|j|g|zc}}|_tt|jDcgc]%}|j|g|j|ddz'c}|_ tt|jdd|_ ||_|j|jdk7r(td|jd|jd||_||_||_||_| |_| |_| |_| |_| |_|jdz|_||_||_||_||_||_||_||_ ||_!||_"| |_#||_$||_%|jMd d tO|d i|ycc}}wcc}}wcc}w) N))r!r r!r!)@r$r zMhidden_size should be equal to the last value in out_features. hidden_size = z, out_features = r!partial_rotary_factorg@))rr rstage_in_channelszipstage_block_stride enumeratestage_block_out_channelsrangelenstage_block_in_channelslistreversedfine_fusion_dimsr ValueErrorr r r rrrrrrintermediate_sizerrrrrrrrrnum_key_value_headsrr setdefaultsuper__init__)selfrrr r r r r rrrrrrrrrrrrrrrrrkwargsstride num_blocks stage_idx __class__s q/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/efficientloftr/configuration_efficientloftr.pyr:zEfficientLoFTRConfig.__init__as:5E4P 0Vc,8,DL,,8,DLJ\"#t'8'8"'=!=ILDL]L]_c_t_tHu# 2D&*VHsj1n- -# V__c_t_tUu) (  # #I . /$2O2OPY2Z[^\^2_ _( $ !%Xd.?.?%@ A#2 F&   t004 4_`d`p`p_qrCDHDUDUVXDYCZ[ $7 )B&*D'$8!%:"$8!#6 !2,!%!1!1A!5'>$,H))B&+F(.L+ 0,'>$1R.#6 !2.137 "6"[# ) ( s$II"*I)NNNr&relur"r"r"r"r"gF leaky_reluFg?g?r!rCgh㈵>NrCg$@g{Gz?) __name__ __module__ __qualname____doc__ model_typer2intstrfloatbooldictr: __classcell__)r@s@rArrsJX"J.2)-)-#))**+$%%&$%#$#&$'3-2+.-0./ ! $'+'(37#'3P#s)d*P#3i$&P#3i$& P#  P# ! P#$'P#%(P#"P# #P#"P#!P#!P#P#"%P# '+!P#"$)#P#$&+%P#&),'P#()P#*+P#,-P#."%/P#0,11P#2!3P#P#rN)configuration_utilsrr__all__r)rPrArSs$4_#+_#D " "rP