o h,@sNdZddlmZddlmZddlmZeeZ ddiZ Gdd d eZ d S) z DETA model configuration)PretrainedConfig)logging)CONFIG_MAPPINGzut/detaz7https://huggingface.co/ut/deta/resolve/main/config.jsoncseZdZdZdZdddZ                        d"fdd ZedefddZ edefd d!Z Z S)# DetaConfiga4 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. 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://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"`. 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. 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_headsNTrelu皙?{Gz??Fsine,r?c&) sP|durtdtdgdd}nt|tr&|d}'t|'}(|(|}||_||_||_ | |_ ||_ ||_ ||_ ||_||_| |_||_||_||_| |_||_||_| |_||_||_||_||_||_||_||_||_||_ |dur|durt!d||_"||_#||_$| |_%|!|_&|"|_'|#|_(|$|_)|%|_*t+j,d d | i|&dS) NzX`backbone_config` is `None`. Initializing the config with the default `ResNet` backbone.resnet)stage2stage3stage4) out_features model_typeTFz3If two_stage is True, with_box_refine must be True.is_encoder_decoder)-loggerinfor isinstancedictpop from_dictbackbone_config num_queriesmax_position_embeddingsrencoder_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_stage ValueError class_cost bbox_cost giou_costmask_loss_coefficientdice_loss_coefficientbbox_loss_coefficientgiou_loss_coefficienteos_coefficient focal_alphasuper__init__))selfr+r,r-r/r.r r1r0r2r9r#r6rr3r4r5r7r8return_intermediater:r;r<r=r>r?r@rArBrDrErFrGrHrIrJrKrLkwargsbackbone_model_type config_class __class__r$a/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/deta/configuration_deta.pyrNsZ)    zDetaConfig.__init__returncC|jSN)r rOr$r$rVr zDetaConfig.num_attention_headscCrXrY)rrZr$r$rVr r[zDetaConfig.hidden_size)%Nr r rr rrrrrTrrrrrrrTFrrrrTrTTrrrrrrrrr) __name__ __module__ __qualname____doc__r" attribute_maprNpropertyintr r __classcell__r$r$rTrVrs`a\rN) r_configuration_utilsrutilsrautor get_loggerr\r%"DETA_PRETRAINED_CONFIG_ARCHIVE_MAPrr$r$r$rVs