o Zhn5@sdZddlmZddlmZddlmZddlmZddl m Z ddl m Z dd l mZd d lmZe eZGd d d eZGddde Zd dgZdS)zDETR model configuration OrderedDict)Mapping)version)PretrainedConfig) OnnxConfig)logging) verify_backbone_config_arguments)CONFIG_MAPPINGcseZdZdZdZdgZdddZ                          d$fdd Zede fddZ ede fdd Z e d!e fd"d#ZZS)% 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: use_timm_backbone (`bool`, *optional*, defaults to `True`): Whether or not to use the `timm` library for the backbone. If set to `False`, will use the [`AutoBackbone`] API. backbone_config (`PretrainedConfig` or `dict`, *optional*): 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://arxiv.org/abs/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://arxiv.org/abs/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"`. backbone (`str`, *optional*, defaults to `"resnet50"`): 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*, `True`): Whether to use pretrained weights for the backbone. 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. 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 ```ZdetrZpast_key_valuesd_modelencoder_attention_heads) hidden_sizenum_attention_headsTNrdrelu皙?{Gz??Fsineresnet50r c#& s|r|duri}|rd|d<gd|d<||d<n/|sH|dvrH|dur1tdtdd gd }nt|trD|d }$t|$}%|%|}d}d}t|||||d ||_||_ ||_ ||_ ||_ ||_ ||_||_| |_||_| |_||_||_||_||_||_||_| |_| |_||_||_||_||_||_||_ ||_!||_"||_#||_$||_%||_&| |_'|!|_(|"|_)t*j+dd | i|#dS)NZ output_stride)rr rZ out_indicesZin_chans)NrzX`backbone_config` is `None`. Initializing the config with the default `ResNet` backbone.ZresnetZstage4)Z out_features model_type)use_timm_backboneuse_pretrained_backbonebackbonebackbone_configbackbone_kwargsis_encoder_decoder),loggerinfor isinstancedictget from_dictr r#r& num_channels num_queriesrencoder_ffn_dimencoder_layersrdecoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdinit_xavier_stdencoder_layerdropdecoder_layerdropZnum_hidden_layersauxiliary_lossposition_embedding_typer%r$r'dilation class_cost bbox_cost giou_costmask_loss_coefficientdice_loss_coefficientbbox_loss_coefficientgiou_loss_coefficienteos_coefficientsuper__init__)&selfr#r&r0r1r3r2rr5r4r6r=r>r(r:rr7r8r9r;r<r?r@r%r$r'rArBrCrDrErFrGrHrIkwargsZbackbone_model_typeZ config_class __class__r)Z/var/www/auris/lib/python3.10/site-packages/transformers/models/detr/configuration_detr.pyrKst (       zDetrConfig.__init__returncC|jSN)rrLr)r)rPrzDetrConfig.num_attention_headscCrRrS)rrTr)r)rPrrUzDetrConfig.hidden_sizer&cKs|dd|i|S)a-Instantiate a [`DetrConfig`] (or a derived class) from a pre-trained backbone model configuration. Args: backbone_config ([`PretrainedConfig`]): The backbone configuration. Returns: [`DetrConfig`]: An instance of a configuration object r&Nr)r))clsr&rMr)r)rPfrom_backbone_configs zDetrConfig.from_backbone_config)"TNrrrrrrrrrrTrrrrrrrFrrTNFrrr rrrr r)__name__ __module__ __qualname____doc__r"Zkeys_to_ignore_at_inferenceZ attribute_maprKpropertyintrr classmethodrrW __classcell__r)r)rNrPr s`fir c@s\eZdZedZedeeee efffddZ ede fddZ ede fddZ d S) DetrOnnxConfigz1.11rQcCs"tddddddfdddifgS) NZ pixel_valuesbatchr0heightwidth)rrr rZ pixel_maskrrrTr)r)rPinputss  zDetrOnnxConfig.inputscCdS)Ngh㈵>r)rTr)r)rPatol_for_validationz"DetrOnnxConfig.atol_for_validationcCre)N r)rTr)r)rPdefault_onnx_opsetrgz!DetrOnnxConfig.default_onnx_opsetN)rXrYrZrparseZtorch_onnx_minimum_versionr\rstrr]rdfloatrfrir)r)r)rPr` s  r`N)r[ collectionsrtypingr packagingrZconfiguration_utilsrZonnxrutilsr Zutils.backbone_utilsr autor Z get_loggerrXr*r r`__all__r)r)r)rPs         m