`i(LddlmZddlmZddlmZGddeZdgZdS))Optional)PretrainedConfig)rope_config_validationc5eZdZdZdZ d.deeedeeedeeededededededededede de d ed!e d"e d#e d$ed%ed&e d'e d(e d)ee d*ed+e d,e f4fd- Z xZ S)/EfficientLoFTRConfiga 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_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. partial_rotary_factor (`float`, *optional*, defaults to 4.0): Dim factor for the RoPE embeddings, in EfficientLoFTR, frequencies should be generated for the whole hidden_size, so this factor is used to compensate. rope_scaling (`Dict`, *optional*): Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value accordingly. Expected contents: `rope_type` (`str`): The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope', 'llama3', '2d'], with 'default' being the original RoPE implementation. `dim` (`int`): The dimension of the RoPE 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 ``` efficientloftrNreluF leaky_relu皙?皙?h㈵>@@$@{Gz?stage_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_eps rope_thetapartial_rotary_factor rope_scalingfine_matching_slice_dim!fine_matching_regress_temperatureinitializer_rangec $||ngd_||ngd_||ngd_dgjddz_dt jjD_fdt jD_fdttjD_ ttjdd_ |_jjdkr%td jd jd|_|_|_|_| _| _| _| _| _jd z_|_|_|_|_|_|_|_ |_!|_"| _#|_$||nd d i_%|_&tO|_(tSj*di|dS)N)rr )rr3rr)@r5r r3c.g|]\}}|gdg|dz zzS)r3).0stride num_blockss /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/efficientloftr/configuration_efficientloftr.py z1EfficientLoFTRConfig.__init__..s;# # # 2D&*VHsj1n- -# # # c8g|]\}}j|g|zSr9)r)r: stage_idxr<selfs r=r>z1EfficientLoFTRConfig.__init__..s:) ) ) z1EfficientLoFTRConfig.__init__..sN( ( (  #I . /$2OPY2Z[^\^[^2_ _( ( ( r?zMhidden_size should be equal to the last value in out_features. hidden_size = z, out_features = r rope_typedefaultr9)+rrrrDzipstage_block_stride enumeraterErangelenstage_block_in_channelslistreversedfine_fusion_dimsr ValueErrorrrrrr r!r"r#r$intermediate_sizer%r&r'r(r)r*r+r/r0num_key_value_headsr,r.r-rr1super__init__)rBrrrrrrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1kwargs __class__s` r=rUzEfficientLoFTRConfig.__init__ms>5E4P 0 0VcVcVc,8,DLL,,,,8,DLLJ\J\J\"#t'8"'=!=# # HKDL]_c_tHuHu# # # ) ) ) ) U^_c_tUuUu) ) ) %( ( ( ( "3t'<#=#=>>( ( ( $ !%Xd.?%@%@ A A#2# F&  t04 4 4[`d`p[[DHDUVXDY[[ $7 )B&*D'$8!%:"$8!#6 !2,!%!1A!5'>$,H))B&+F(.L+ 0,'>$1R.#6 $,8,DLL;XaJb&;"t$$$!2""6"""""r?)NNNr r r r r r r r rFrFrrrr rrrNr rr)__name__ __module__ __qualname____doc__ model_typerrNintstrfloatbooldictrU __classcell__)rWs@r=rrsTTl"J15,0,0#))**+$%%&$%#$#&$'3-2+.-0./ ! $#'*'+'(37#'7W#W#"49-W#tCy)W#tCy) W#  W# ! W#$'W#%(W#"W# #W#"W#!W#!W#W#"%W# '+!W#"$)#W#$&+%W#&),'W#()W#*+W#,-W#. %/W#0tn1W#2"%3W#4,15W#6!7W#W#W#W#W#W#W#W#W#W#r?rN)typingrconfiguration_utilsrmodeling_rope_utilsrr__all__r9r?r=rgs333333999999p#p#p#p#p#+p#p#p#f " "r?