`iv7pdZddlmZddlmZddlmZejeZ GddeZ dgZ dS) zDETA model configuration)PretrainedConfig)logging)CONFIG_MAPPINGceZdZdZdZdddZ d fd ZedefdZ edefdZ edZ xZ S)! DetaConfiga This is the configuration class to store the configuration of a [`DetaModel`]. It is used to instantiate a DETA 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 DETA [SenseTime/deformable-detr](https://huggingface.co/SenseTime/deformable-detr) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: backbone_config (`PretrainedConfig` or `dict`, *optional*, defaults to `ResNetConfig()`): The configuration of the backbone model. backbone (`str`, *optional*): Name of backbone to use when `backbone_config` is `None`. If `use_pretrained_backbone` is `True`, this will load the corresponding pretrained weights from the timm or transformers library. If `use_pretrained_backbone` is `False`, this loads the backbone's config and uses that to initialize the backbone with random weights. use_pretrained_backbone (`bool`, *optional*, `False`): Whether to use pretrained weights for the backbone. use_timm_backbone (`bool`, *optional*, `False`): Whether to load `backbone` from the timm library. If `False`, the backbone is loaded from the transformers library. backbone_kwargs (`dict`, *optional*): Keyword arguments to be passed to AutoBackbone when loading from a checkpoint e.g. `{'out_indices': (0, 1, 2, 3)}`. Cannot be specified if `backbone_config` is set. num_queries (`int`, *optional*, defaults to 900): Number of object queries, i.e. detection slots. This is the maximal number of objects [`DetaModel`] can detect in a single image. In case `two_stage` is set to `True`, we use `two_stage_num_proposals` instead. d_model (`int`, *optional*, defaults to 256): Dimension of the layers. encoder_layers (`int`, *optional*, defaults to 6): Number of encoder layers. decoder_layers (`int`, *optional*, defaults to 6): Number of decoder layers. encoder_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. decoder_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer decoder. decoder_ffn_dim (`int`, *optional*, defaults to 2048): Dimension of the "intermediate" (often named feed-forward) layer in decoder. encoder_ffn_dim (`int`, *optional*, defaults to 2048): Dimension of the "intermediate" (often named feed-forward) layer in decoder. activation_function (`str` or `function`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. init_std (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. init_xavier_std (`float`, *optional*, defaults to 1): The scaling factor used for the Xavier initialization gain in the HM Attention map module. encoder_layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. auxiliary_loss (`bool`, *optional*, defaults to `False`): Whether auxiliary decoding losses (loss at each decoder layer) are to be used. position_embedding_type (`str`, *optional*, defaults to `"sine"`): Type of position embeddings to be used on top of the image features. One of `"sine"` or `"learned"`. class_cost (`float`, *optional*, defaults to 1): Relative weight of the classification error in the Hungarian matching cost. bbox_cost (`float`, *optional*, defaults to 5): Relative weight of the L1 error of the bounding box coordinates in the Hungarian matching cost. giou_cost (`float`, *optional*, defaults to 2): Relative weight of the generalized IoU loss of the bounding box in the Hungarian matching cost. mask_loss_coefficient (`float`, *optional*, defaults to 1): Relative weight of the Focal loss in the panoptic segmentation loss. dice_loss_coefficient (`float`, *optional*, defaults to 1): Relative weight of the DICE/F-1 loss in the panoptic segmentation loss. bbox_loss_coefficient (`float`, *optional*, defaults to 5): Relative weight of the L1 bounding box loss in the object detection loss. giou_loss_coefficient (`float`, *optional*, defaults to 2): Relative weight of the generalized IoU loss in the object detection loss. eos_coefficient (`float`, *optional*, defaults to 0.1): Relative classification weight of the 'no-object' class in the object detection loss. num_feature_levels (`int`, *optional*, defaults to 5): The number of input feature levels. encoder_n_points (`int`, *optional*, defaults to 4): The number of sampled keys in each feature level for each attention head in the encoder. decoder_n_points (`int`, *optional*, defaults to 4): The number of sampled keys in each feature level for each attention head in the decoder. two_stage (`bool`, *optional*, defaults to `True`): Whether to apply a two-stage deformable DETR, where the region proposals are also generated by a variant of DETA, which are further fed into the decoder for iterative bounding box refinement. two_stage_num_proposals (`int`, *optional*, defaults to 300): The number of region proposals to be generated, in case `two_stage` is set to `True`. with_box_refine (`bool`, *optional*, defaults to `True`): Whether to apply iterative bounding box refinement, where each decoder layer refines the bounding boxes based on the predictions from the previous layer. focal_alpha (`float`, *optional*, defaults to 0.25): Alpha parameter in the focal loss. assign_first_stage (`bool`, *optional*, defaults to `True`): Whether to assign each prediction i to the highest overlapping ground truth object if the overlap is larger than a threshold 0.7. assign_second_stage (`bool`, *optional*, defaults to `True`): Whether to assign second assignment procedure in the second stage closely follows the first stage assignment procedure. disable_custom_kernels (`bool`, *optional*, defaults to `True`): Disable the use of custom CUDA and CPU kernels. This option is necessary for the ONNX export, as custom kernels are not supported by PyTorch ONNX export. Examples: ```python >>> from transformers import DetaConfig, DetaModel >>> # Initializing a DETA SenseTime/deformable-detr style configuration >>> configuration = DetaConfig() >>> # Initializing a model (with random weights) from the SenseTime/deformable-detr style configuration >>> model = DetaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```detad_modelencoder_attention_heads) hidden_sizenum_attention_headsNFTrelu皙?{Gz??siner,?c, "|rtd||td|5|3tdtdgd}nLt |t r7|d}-t|-}.|.|}||r|td||_||_ ||_ ||_ ||_ ||_ ||_||_| |_||_| |_| |_| |_| |_||_||_||_||_||_||_||_||_||_||_||_ ||_!||_"||_#||_$| |_%|!|_&|d ur|d urtd |"|_'|#|_(|$|_)|%|_*|&|_+|'|_,|(|_-|)|_.|*|_/|+|_0tcj2d d |i|,dS)Nz+Pretrained backbones are not supported yet.z8You can't specify both `backbone` and `backbone_config`.zX`backbone_config` is `None`. Initializing the config with the default `ResNet` backbone.resnet)stage2stage3stage4) out_features model_typez?You can't specify both `backbone_kwargs` and `backbone_config`.TFz3If two_stage is True, with_box_refine must be True.is_encoder_decoder)3 ValueErrorloggerinfor isinstancedictpop from_dictbackbone_configbackboneuse_pretrained_backboneuse_timm_backbonebackbone_kwargs num_queriesmax_position_embeddingsr encoder_ffn_dimencoder_layersr decoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdinit_xavier_stdencoder_layerdropauxiliary_lossposition_embedding_typenum_feature_levelsencoder_n_pointsdecoder_n_points two_stagetwo_stage_num_proposalswith_box_refineassign_first_stageassign_second_stage class_cost bbox_cost giou_costmask_loss_coefficientdice_loss_coefficientbbox_loss_coefficientgiou_loss_coefficienteos_coefficient focal_alphadisable_custom_kernelssuper__init__)0selfr/r0r1r2r3r4r5r7r6r r9r8r:rAr&r>r r;r<r=r?r@return_intermediaterBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQrRrSrTrUkwargsbackbone_model_type config_class __class__s0 /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/deprecated/deta/configuration_deta.pyrWzDetaConfig.__init__se^ # LJKK K  &8+?WXX X  "x'7 KKr s s s,X6DbDbDbcccOO/400 J&5&9&9,&G&G#-.AB "."8"8"I"I  &? &?Z^__ _.  '>$!2.&'>$ .,'>$.,'>$ !2"4#6   .!2,'>$"4 0 0"'>$."4#6   E!9!9RSS S$""%:"%:"%:"%:".&&<#II,>I&IIIIIreturnc|jSN)r rXs r^r zDetaConfig.num_attention_headss ++r_c|jSrb)r rcs r^r zDetaConfig.hidden_size s |r_cTt|dddt|jiniS)Nr/)getattrtyper/rcs r^ sub_configszDetaConfig.sub_configs s7t.55AT%9 : : ; ; r_)+NNFFNrrrrrrrrrTrrrrrrrTFrrrrTrTTTrrrrrrrrrT) __name__ __module__ __qualname____doc__r% attribute_maprWpropertyintr r rh __classcell__)r]s@r^rrs]r r hJ 8M % $ ! !"  & # #YoJoJoJoJoJoJb,S,,,X,SX  X     r_rN) rlconfiguration_utilsrutilsrautor get_loggerrir)r__all__r'r_r^rvs444444""""""  H % %z z z z z !z z z z .r_