^j7~ddlmZddlmZddlmZddlmZddlm Z ed eGd d eZ d gZ y ) )strict)%consolidate_backbone_kwargs_to_config)PreTrainedConfig)auto_docstring) AutoConfigz"Intellindust/DEIMv2_HGNetv2_N_COCO) checkpointceZdZUdZdZdeiZddgZdddZd Z e e d <d Z e d ze d <d Z e e d<d Ze e d<d Zeezd ze d<dZee d<dZee d<dZeeeedfze d<dZeeeedfze d<dZee d<dZee d<dZee d<dZe eze d<dZe eze d <d!Zeeeedfze d"<d#Z ee d$<d%Z!e"e d&<d'Z#e"e d(<d Z$eeeeefzd ze d)<d*Z%ee d+<d,Z&e e d-<dZ'ee d<d.Z(ee d/<d0Z)eeeedfze d1<dZ*ee d2<d3Z+ee d4<d5Z,eeeze d6<d7Z-ee d8<dZ.ee d9<d:Z/e"e d;<dZ0e eze d<<d=Z1ee d><d?Z2e e d@<d,Z3e e dA<d*Z4ee dB<d Z5eeezd ze dC<dZ6ee dD<dEZ7e e dF<dGZ8e e dH<dGZ9e e dI<dJZ:e e dK<dGZ;e e dL<dZe e dP<dGZ?e e dQ<d,Z@e e dR<dJZAe e dS<dGZBe e dT<dUZCe e dV<dWZDe e dX<dYZEe e dZ<d[ZFee d\<d,ZGee ze d]<d^ZHee d_<d`ZIe e da<d,ZJe e db<d5ZKee dc<ddZLee de<dfZMee dg<d?ZNe e dh<diZOe"e dj<d?ZPe e dk<dZQee dl<dZRee dm<d,ZSe e dn<dZTee do<d ZUe d ze dp<dqZVe"e dr<dsZWee dt<duZXe"e dv<dZYee dw<d*ZZee dx<dZ[ee dy<fdzZ\d{Z]xZ^S)| Deimv2Configa# initializer_bias_prior_prob (`float`, *optional*): The prior probability used by the bias initializer to initialize biases for `enc_score_head` and `class_embed`. If `None`, `prior_prob` computed as `prior_prob = 1 / (num_labels + 1)` while initializing model weights. freeze_backbone_batch_norms (`bool`, *optional*, defaults to `True`): Whether to freeze the batch normalization layers in the backbone. encoder_in_channels (`list`, *optional*, defaults to `[512, 1024, 2048]`): Multi level features input for encoder. feat_strides (`list[int]`, *optional*, defaults to `[8, 16, 32]`): Strides used in each feature map. encode_proj_layers (`list[int]`, *optional*, defaults to `[2]`): Indexes of the projected layers to be used in the encoder. positional_encoding_temperature (`int`, *optional*, defaults to 10000): The temperature parameter used to create the positional encodings. encoder_activation_function (`str`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. eval_size (`list[int]` or `tuple[int, int]`, *optional*): Height and width used to computes the effective height and width of the position embeddings after taking into account the stride. normalize_before (`bool`, *optional*, defaults to `False`): Determine whether to apply layer normalization in the transformer encoder layer before self-attention and feed-forward modules. hidden_expansion (`float`, *optional*, defaults to 1.0): Expansion ratio to enlarge the dimension size of RepVGGBlock and CSPRepLayer. num_queries (`int`, *optional*, defaults to 300): Number of object queries. decoder_in_channels (`list`, *optional*, defaults to `[256, 256, 256]`): Multi level features dimension for decoder. num_feature_levels (`int`, *optional*, defaults to 3): The number of input feature levels. decoder_n_points (`int`, *optional*, defaults to 4): The number of sampled keys in each feature level for each attention head in the decoder. decoder_activation_function (`str`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the decoder. num_denoising (`int`, *optional*, defaults to 100): The total number of denoising tasks or queries to be used for contrastive denoising. label_noise_ratio (`float`, *optional*, defaults to 0.5): The fraction of denoising labels to which random noise should be added. box_noise_scale (`float`, *optional*, defaults to 1.0): Scale or magnitude of noise to be added to the bounding boxes. learn_initial_query (`bool`, *optional*, defaults to `False`): Indicates whether the initial query embeddings for the decoder should be learned during training. anchor_image_size (`tuple[int, int]`, *optional*): Height and width of the input image used during evaluation to generate the bounding box anchors. with_box_refine (`bool`, *optional*, defaults to `True`): Whether to apply iterative bounding box refinement. matcher_alpha (`float`, *optional*, defaults to 0.25): Parameter alpha used by the Hungarian Matcher. matcher_gamma (`float`, *optional*, defaults to 2.0): Parameter gamma used by the Hungarian Matcher. matcher_class_cost (`float`, *optional*, defaults to 2.0): The relative weight of the class loss used by the Hungarian Matcher. matcher_bbox_cost (`float`, *optional*, defaults to 5.0): The relative weight of the bounding box loss used by the Hungarian Matcher. matcher_giou_cost (`float`, *optional*, defaults to 2.0): The relative weight of the giou loss of used by the Hungarian Matcher. use_focal_loss (`bool`, *optional*, defaults to `True`): Parameter informing if focal loss should be used. focal_loss_alpha (`float`, *optional*, defaults to 0.75): Parameter alpha used to compute the focal loss. focal_loss_gamma (`float`, *optional*, defaults to 2.0): Parameter gamma used to compute the focal loss. weight_loss_vfl (`float`, *optional*, defaults to 1.0): Relative weight of the varifocal loss in the object detection loss. weight_loss_bbox (`float`, *optional*, defaults to 5.0): Relative weight of the L1 bounding box loss in the object detection loss. weight_loss_giou (`float`, *optional*, defaults to 2.0): Relative weight of the generalized IoU loss in the object detection loss. weight_loss_fgl (`float`, *optional*, defaults to 0.15): Relative weight of the fine-grained localization loss in the object detection loss. weight_loss_ddf (`float`, *optional*, defaults to 1.5): Relative weight of the decoupled distillation focal loss in the object detection loss. eval_idx (`int`, *optional*, defaults to -1): Index of the decoder layer to use for evaluation. layer_scale (`float`, *optional*, defaults to `1.0`): Scaling factor for the hidden dimension in later decoder layers. max_num_bins (`int`, *optional*, defaults to 32): Maximum number of bins for the distribution-guided bounding box refinement. reg_scale (`float`, *optional*, defaults to 4.0): Scale factor for the regression distribution. depth_mult (`float`, *optional*, defaults to 1.0): Multiplier for the number of blocks in RepNCSPELAN5 layers. top_prob_values (`int`, *optional*, defaults to 4): Number of top probability values to consider from each corner's distribution. lqe_hidden_dim (`int`, *optional*, defaults to 64): Hidden dimension size for the Location Quality Estimator (LQE) network. lqe_layers (`int`, *optional*, defaults to 2): Number of layers in the Location Quality Estimator MLP. decoder_offset_scale (`float`, *optional*, defaults to 0.5): Offset scale used in deformable attention. decoder_method (`str`, *optional*, defaults to `"default"`): The method to use for the decoder: `"default"` or `"discrete"`. up (`float`, *optional*, defaults to 0.5): Controls the upper bounds of the Weighting Function. weight_loss_mal (`float`, *optional*, defaults to 1.0): Relative weight of the matching auxiliary loss in the object detection loss. use_dense_one_to_one (`bool`, *optional*, defaults to `True`): Whether to use dense one-to-one matching across decoder layers. mal_alpha (`float`, *optional*): Alpha parameter for the Matching Auxiliary Loss (MAL). If `None`, uses `focal_loss_alpha`. encoder_fuse_op (`str`, *optional*, defaults to `"sum"`): Fusion operation used in the encoder FPN. DEIMv2 uses `"sum"` instead of D-FINE's `"cat"`. spatial_tuning_adapter_inplanes (`int`, *optional*, defaults to 16): Number of input planes for the STA convolutional stem. encoder_type (`str`, *optional*, defaults to `"hybrid"`): Type of encoder to use. `"hybrid"` uses the full HybridEncoder with AIFI, FPN, and PAN. `"lite"` uses the lightweight LiteEncoder with GAP fusion for smaller variants (Atto, Femto, Pico). use_gateway (`bool`, *optional*, defaults to `True`): Whether to use the gateway mechanism (cross-attention gating) in decoder layers. When `False`, uses RMSNorm on the encoder attention output instead. share_bbox_head (`bool`, *optional*, defaults to `False`): Whether to share the bounding box prediction head across all decoder layers. encoder_has_trailing_conv (`bool`, *optional*, defaults to `True`): Whether the encoder's CSP blocks include a trailing 3x3 convolution after the bottleneck path. `True` for RepNCSPELAN4 (used by HGNetV2 N and LiteEncoder variants). `False` for RepNCSPELAN5 (used by DINOv3 variants). deimv2backbone_configbasic bottleneckd_modelencoder_attention_heads) hidden_sizenum_attention_headsg{Gz?initializer_rangeNinitializer_bias_prior_probgh㈵>layer_norm_epsbatch_norm_epsTfreeze_backbone_batch_normsencoder_hidden_dim)ii.encoder_in_channels) feat_stridesencoder_layersrencoder_ffn_dimrgdropoutactivation_dropout)rencode_proj_layersi'positional_encoding_temperaturegeluencoder_activation_functionsiluactivation_function eval_sizeFnormalize_beforeg?hidden_expansioni, num_queries)rrrdecoder_in_channelsdecoder_ffn_dimrnum_feature_levelsdecoder_n_pointsdecoder_layersdecoder_attention_headsreludecoder_activation_functionattention_dropoutd num_denoisingg?label_noise_ratiobox_noise_scalelearn_initial_queryanchor_image_sizewith_box_refineg? matcher_alphag@ matcher_gammamatcher_class_costg@matcher_bbox_costmatcher_giou_costuse_focal_lossauxiliary_lossg?focal_loss_alphafocal_loss_gammaweight_loss_vflweight_loss_bboxweight_loss_gioug333333?weight_loss_fglg?weight_loss_ddfg-C6?eos_coefficienteval_idx layer_scaler max_num_binsg@ reg_scale depth_multtop_prob_values@lqe_hidden_dimr lqe_layersdecoder_offset_scaledefaultdecoder_methoduptie_word_embeddingsis_encoder_decoderweight_loss_maluse_dense_one_to_one mal_alphasumencoder_fuse_oprspatial_tuning_adapter_inplaneshybrid encoder_type use_gatewayshare_bbox_headencoder_has_trailing_convc td|jddgdid|\|_}|j|jz|_t |di|y)Nhgnet_v2 out_indices)rrr4)rdefault_config_typedefault_config_kwargs)rrrr8head_dimsuper __post_init__)selfkwargs __class__s z/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/deimv2/configuration_deimv2.pyruzDeimv2Config.__post_init__s`'L(  00 *#0)"<(  ( $f  (D(DD  ''cpt|jtrQt|j|jk7r/t dt|jd|jd|j |jz|jk7r%t d|jd|jy)zOPart of `@strict`-powered validation. Validates the architecture of the config.z!Length of decoder_n_points list (z!) must match num_feature_levels (z).zEmbedded dimension z. must be divisible by decoder_attention_heads N) isinstancer5listlenr3 ValueErrorrsr8r)rvs ryvalidate_architecturez"Deimv2Config.validate_architectures d++T 24(()T-D-DD 7Dr?r@rArBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQrSrTrUrVrWrXrZr[r\r^r_r`rarbrcrdrfrgrirjrkrlrur __classcell__)rxs@ryr r stlJ$j1KL)K 8M $u#044 NE  NE 6:OT,,t3:(,,"!7HcU38_4H0;L$s)eCHo-;NCOS#$S$GUS[&) )6:S E#s(O3:+0#S0'--%%48ItCy5c?*T18"d"!e!GSK7FcU38_4FOS()cDIo)NC#$S$'--%(us{(M3"u" OU %%04sT#Y-4 OT  M5M5 ##"u""u"NDND"e"!e! OU !e!!e!!OU! OU !OU!Hc"Ku"L#IuJOSNCJ"%%%#NC#BO $$## OU !%$%"Iut|" OS +-#S- L# K!OT!&*t*( rzr N) huggingface_hub.dataclassesrbackbone_utilsrconfiguration_utilsrutilsrautor r __all__rrrzryrsO*/C3# ?@f#fAfR  rz