+ j7^RIHt^RIHt^RIHt^RIHt^RIH t ]!RR7]!RR ]444t R .t R #) )strict)%consolidate_backbone_kwargs_to_config)PreTrainedConfig)auto_docstring) AutoConfigz"Intellindust/DEIMv2_HGNetv2_N_COCO) checkpointcaa]tRt^toRtRtR]/tRR.tRRRR /t R t R t R t R t R tR tRtR(tR)t^tRt^tRtRtR*tRtRtRtR tRtRtRtRt R+t!Rt"^t#^t$^t%^t&Rt'Rt(^dt)Rt*Rt+Rt,R t-R t.Rt/Rt0Rt1Rt2Rt3R t4R t5Rt6Rt7Rt8Rt9Rt:Rt;RtRt?^ t@R tARtB^tC^@tD^tERtFR!tGRtHR tIR tJRtKR tLR tMR"tN^tOR#tPR tQRtRR tSV3R$ltTR%tUV3R&ltVR'tWVtXV;tY#)- Deimv2ConfigaP 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 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 bottleneck hidden_sized_modelnum_attention_headsencoder_attention_headsg{Gz?Ngh㈵>Tgi'gelusiluFg?i,relug?g?g@g@g?g333333?g?g-C6?g@defaultsumhybridc <\RRVPRRRR.RO//VBwVnpVPVP,Vn\ SV`!R/VBR#)r default_config_typehgnet_v2default_config_kwargs out_indicesN))rr rdecoder_attention_headshead_dimsuper __post_init__)selfkwargs __class__s&,p/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/deimv2/configuration_deimv2.pyr'Deimv2Config.__post_init__sl'L(  00( *( $1)"<(  ( $f  (D(DD  ''c \VP\4'dT\VP4VP8wd0\ R\VP4 RVP R24hVP VP,VP8wd&\ RVP RVP 24hR#)zOPart of `@strict`-powered validation. Validates the architecture of the config.z!Length of decoder_n_points list (z!) must match num_feature_levels (z).zEmbedded dimension z. must be divisible by decoder_attention_heads N) isinstancedecoder_n_pointslistlennum_feature_levels ValueErrorr%r$r)r(s&r+validate_architecture"Deimv2Config.validate_architectures d++T 2 24(()T-D-DD 7D&S[;R?&S[;R@&S[;RA&S[;RB&S[;RC&S[;RD&S[;RE&S[R,;RF&S[;RG&S[;RH&S[;RI&S[;RJ&S[;RK&S[;RL&#)Mr!initializer_rangeNinitializer_bias_prior_problayer_norm_epsbatch_norm_epsr freeze_backbone_batch_normsencoder_hidden_dim.encoder_in_channels feat_stridesencoder_layersencoder_ffn_dimrdropoutactivation_dropoutencode_proj_layerspositional_encoding_temperatureencoder_activation_functionactivation_function eval_sizenormalize_beforehidden_expansionr num_queriesdecoder_in_channelsdecoder_ffn_dimr3r0decoder_layersr$decoder_activation_functionattention_dropout num_denoisinglabel_noise_ratiobox_noise_scalelearn_initial_queryanchor_image_sizewith_box_refine matcher_alpha matcher_gammamatcher_class_costmatcher_bbox_costmatcher_giou_costuse_focal_lossauxiliary_lossfocal_loss_alphafocal_loss_gammaweight_loss_vflweight_loss_bboxweight_loss_giouweight_loss_fglweight_loss_ddfeos_coefficienteval_idx layer_scale max_num_bins reg_scale depth_multtop_prob_valueslqe_hidden_dim lqe_layersdecoder_offset_scaledecoder_methoduptie_word_embeddingsis_encoder_decoderweight_loss_maluse_dense_one_to_one mal_alphaencoder_fuse_opspatial_tuning_adapter_inplanes encoder_type use_gatewayshare_bbox_headencoder_has_trailing_conv)floatdictrboolintr1tuplestr)format __classdict__s"r+ __annotate__Deimv2Config.__annotate__sB#CD"'4EF GH IJ,,t3:KL"&,MR!STcU38_4HUVs)eCHo-;WXYZ[\!$]^S[_` )abS E#s(O3:cd&)0ef"%-gh%ilCy5c?*T18mn"op!qvwxyzcU38_4F{|}~@DIo)ABCD!$EF"%-GHs{(IJKL"MN OP%QRT#Y-4ST UZ[\]^#_`"ab"cdefgh"ij!kl mn!op!qr!st uv!wxyzu"{|}~@ABCDEFGH %IJ#KL OMN$OP#QR ST%UVt|"WX YZ&)-[\ ]^_`!ab $*cr-)r r%)iri) )r!)rrr)Z__name__ __module__ __qualname____firstlineno____doc__ model_typer sub_configs layer_types attribute_mapr8r9r:r;r r<r=r>r?r@rArrBrCrDrErFrGrHrIrJrrKrLrMr3r0rNr$rOrPrQrRrSrTrUrVrWrXrYrZr[r\r]r^r_r`rarbrcrdrerfrgrhrirjrkrlrmrnrorprqrrrsrtrurvrwrxryrzr{r'r5__annotate_func____static_attributes____classdictcell__ __classcell__)r*rs@@r+r r stlJ$j1KL)Ky8M $04 N N6:O(,"7H0;LNO#$G&)6:+0#'-%48I"!GK7FO()N#$'-%(M" O %04 O MM #""NN"! O!!!O O!OH"KLIJONJ"%#NB $# O!%"I O+-# LK!O&*( {r-r N) huggingface_hub.dataclassesrbackbone_utilsrconfiguration_utilsrutilsrautorr __all__r r-r+rsO*/C3# ?@f#fAfR  r-