qi(xdZddlmZddlmZddlmZddlmZeje Z GddeZ dgZ y ) zDETR model configuration)%consolidate_backbone_kwargs_to_config)PreTrainedConfig)logging) AutoConfigc|eZdZdZdZdeiZdgZdddZ d fd Z xZ S) DetrConfiga_ This is the configuration class to store the configuration of a [`DetrModel`]. It is used to instantiate a DETR 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 DETR [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) 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 (`Union[dict, "PreTrainedConfig"]`, *optional*, defaults to `ResNetConfig()`): The configuration of the backbone model. Only used in case `use_timm_backbone` is set to `False` in which case it will default to `ResNetConfig()`. num_channels (`int`, *optional*, defaults to 3): The number of input channels. num_queries (`int`, *optional*, defaults to 100): Number of object queries, i.e. detection slots. This is the maximal number of objects [`DetrModel`] can detect in a single image. For COCO, we recommend 100 queries. d_model (`int`, *optional*, defaults to 256): This parameter is a general dimension parameter, defining dimensions for components such as the encoder layer and projection parameters in the decoder layer, among others. 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. decoder_layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the decoder. 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"`. dilation (`bool`, *optional*, defaults to `False`): Whether to replace stride with dilation in the last convolutional block (DC5). Only supported when `use_timm_backbone` = `True`. 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. Examples: ```python >>> from transformers import DetrConfig, DetrModel >>> # Initializing a DETR facebook/detr-resnet-50 style configuration >>> configuration = DetrConfig() >>> # Initializing a model (with random weights) from the facebook/detr-resnet-50 style configuration >>> model = DetrModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```detrbackbone_configpast_key_valuesd_modelencoder_attention_heads) hidden_sizenum_attention_headsc |jdi} | jd|dd| jdgdd}!|r| jdd |!d<td|d d d d gi|!d|\}}||_||_||_||_||_||_||_||_ ||_ | |_ ||_ ||_ ||_| |_||_||_| |_| |_||_||_||_||_||_||_||_||_||_||_||_t?"|dd| i|y)Nbackbone_kwargs num_channelsTF out_indices)rr)r features_onlyuse_pretrained_backboner output_strideresnet50resnet out_featuresstage4)r default_backbonedefault_config_typedefault_config_kwargstimm_default_kwargsis_encoder_decoder)!getrr r num_queriesr encoder_ffn_dimencoder_layersrdecoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdinit_xavier_stdencoder_layerdropdecoder_layerdropnum_hidden_layersauxiliary_lossposition_embedding_type class_cost bbox_cost giou_costmask_loss_coefficientdice_loss_coefficientbbox_loss_coefficientgiou_loss_coefficienteos_coefficientsuper__init__)#selfr rr&r(r'rr*r)r+r2r3r#r/r r,r-r.r0r1r5r6dilationr7r8r9r:r;r<r=r>kwargsrr" __class__s# ]/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/detr/configuration_detr.pyr@zDetrConfig.__init__|sD!**%6;+// M!',*..}lK   3B3F3FXZ3[  0"G# +' (#1H:"> 3 #  #  /(& .,'>$.,'>$ !2"4#6   .!2!2!/,'>$$""%:"%:"%:"%:". I,>I&I)NrdrHrIrJrKTrelu皙?rKrKg{Gz?g?FsineFrrrrrPrrN) __name__ __module__ __qualname____doc__ model_typer sub_configskeys_to_ignore_at_inference attribute_mapr@ __classcell__)rDs@rEr r sX tJ$j1K#4"5 8M ! !" &?TJTJrFr N)rTbackbone_utilsrconfiguration_utilsrutilsrautor get_loggerrQloggerr __all__r$rFrErasEC3   H %wJ!wJt .rF