FPh3ddlZddlmZddlmcmZddlmZddlm Z ddl m Z m Z GddejZ ddZy) N)linear_sum_assignment)bbox_iou) xywh2xyxy xyxy2xywhc,eZdZdZdfd ZddZxZS)HungarianMatchera A module implementing the HungarianMatcher, which is a differentiable module to solve the assignment problem in an end-to-end fashion. HungarianMatcher performs optimal assignment over the predicted and ground truth bounding boxes using a cost function that considers classification scores, bounding box coordinates, and optionally, mask predictions. Attributes: cost_gain (dict): Dictionary of cost coefficients: 'class', 'bbox', 'giou', 'mask', and 'dice'. use_fl (bool): Indicates whether to use Focal Loss for the classification cost calculation. with_mask (bool): Indicates whether the model makes mask predictions. num_sample_points (int): The number of sample points used in mask cost calculation. alpha (float): The alpha factor in Focal Loss calculation. gamma (float): The gamma factor in Focal Loss calculation. Methods: forward(pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=None, gt_mask=None): Computes the assignment between predictions and ground truths for a batch. _cost_mask(bs, num_gts, masks=None, gt_mask=None): Computes the mask cost and dice cost if masks are predicted. ct||dddddd}||_||_||_||_||_||_y)zInitializes HungarianMatcher with cost coefficients, Focal Loss, mask prediction, sample points, and alpha gamma factors. N)classbboxgioumaskdice)super__init__ cost_gainuse_fl with_masknum_sample_pointsalphagamma)selfrrrrrr __class__s gC:\Users\daisl\Desktop\realtime-object-detection\venv\Lib\site-packages\ultralytics/models/utils/ops.pyrzHungarianMatcher.__init__"sQ   "#Q1aPI" "!2  c  |j\}} } t|dk(rat|D cgc]L} tjgtj tjgtj fNc} S|j jd| }|jrtj|ntj|d}|j jdd}|dd|f}|jrqd|jz ||jzzd|z dzj z} |jd|z |jzz|dzj z} | | z }n| }|jd|jdz j!jd}d t#|jd|jdd d j%dz }|j&d |z|j&d |zz|j&d|zz}|j(r||j+||||z }d||j-|j/z<|j|| dj1}t3|j5|dDcgc]\}}t7||}}}tj8dg|ddj;d}t3|Dcgc]X\}\}}tj|tj tj|tj ||zfZc}}}Scc} wcc}}wcc}}}w)a= Forward pass for HungarianMatcher. This function computes costs based on prediction and ground truth (classification cost, L1 cost between boxes and GIoU cost between boxes) and finds the optimal matching between predictions and ground truth based on these costs. Args: pred_bboxes (Tensor): Predicted bounding boxes with shape [batch_size, num_queries, 4]. pred_scores (Tensor): Predicted scores with shape [batch_size, num_queries, num_classes]. gt_cls (torch.Tensor): Ground truth classes with shape [num_gts, ]. gt_bboxes (torch.Tensor): Ground truth bounding boxes with shape [num_gts, 4]. gt_groups (List[int]): List of length equal to batch size, containing the number of ground truths for each image. masks (Tensor, optional): Predicted masks with shape [batch_size, num_queries, height, width]. Defaults to None. gt_mask (List[Tensor], optional): List of ground truth masks, each with shape [num_masks, Height, Width]. Defaults to None. Returns: (List[Tuple[Tensor, Tensor]]): A list of size batch_size, each element is a tuple (index_i, index_j), where: - index_i is the tensor of indices of the selected predictions (in order) - index_j is the tensor of indices of the corresponding selected ground truth targets (in order) For each batch element, it holds: len(index_i) = len(index_j) = min(num_queries, num_target_boxes) rdtypedimNr g:0yE>?T)xywhGIoUr rr)shapesumrangetorchtensorlongdetachviewrFsigmoidsoftmaxrrlog unsqueezeabsrsqueezerr _cost_maskisnanisinfcpu enumeratesplitr as_tensorcumsum_)r pred_bboxes pred_scores gt_bboxesgt_cls gt_groupsmasksgt_maskbsnqnc_neg_cost_classpos_cost_class cost_class cost_bbox cost_giouCicindiceskjs rforwardzHungarianMatcher.forward0s.4!&& B y>Q fklnfopfoabU\\"EJJ7bPUPZPZ9[\fop p"((*//B7 04 aii ,;\^A_ !((*//A6 "!V), ;;$**n 1JKQRU`Q`cgQgPlPlPnOnoN!ZZA O +JKQ\_cQcPhPhPjOjkN'.8J%J!**1- 0C0CA0FFKKMQQRTU (;#8#8#;Y=P=PQR=SZ^eijrrsuvv  NN7 #j 0 NN6 "Y . / NN6 "Y . / >> Yw? ?A$'!'')aggi  FF2r2  " " $;DQWWYXZE[;\];\41a(1.;\]OOQ$83B$89AA!D "+7!35!3IAv1auzz2ELL%**4UXabcXd4de!35 5OqH^5sAM4>M9AM?)NTFi1g?@)NN)__name__ __module__ __qualname____doc__rrV __classcell__)rs@rrr s* E5rrc  |r|dkry|d}t|} t|} | dk(ry|| z} | dk(rdn| } t|} |d} |d}|d}| jd| z}|jd| zd}|jd| zj d }t j | | zt j|j | | zz}|dkDr|t j|j|d zk}t j|jd }t j|d||j|j }|||<|dkDrt|}|d dd fd zjdd|z}t j|dddzdz }t j |}||xxdz cc<||z}|||zz }|j#ddt%|}t j&|d}t)| dz| z}||}t j*| ||jd | j}t j*| |d|j}t j,|Dcgc]0}t j.t1|t j2c}}t j2t1| D cgc] } || | zz c} d}!t j,t1d| zD cgc] } || | zz c} }||||f<||||f<||z}"t j*|"|"gt j4}#d|#|d d |f<t1| D]} | dk(r#d|#| dz| z| dz| dzz| dz| dzz|f<| | dz k(r!d|#| dz| z| dz| dzzd | | zdzf<Td|#| dz| z| dz| dzz| dz| dzz|f<d|#| dz| z| dz| dzzd | dz| zf<|!j7j9t;|dD$cgc]}$|$j=d c}$| ||gd}%|j?|j|j?|j|#j?|j|%fScc}wcc} wcc} wcc}$w)a Get contrastive denoising training group. This function creates a contrastive denoising training group with positive and negative samples from the ground truths (gt). It applies noise to the class labels and bounding box coordinates, and returns the modified labels, bounding boxes, attention mask and meta information. Args: batch (dict): A dict that includes 'gt_cls' (torch.Tensor with shape [num_gts, ]), 'gt_bboxes' (torch.Tensor with shape [num_gts, 4]), 'gt_groups' (List(int)) which is a list of batch size length indicating the number of gts of each image. num_classes (int): Number of classes. num_queries (int): Number of queries. class_embed (torch.Tensor): Embedding weights to map class labels to embedding space. num_dn (int, optional): Number of denoising. Defaults to 100. cls_noise_ratio (float, optional): Noise ratio for class labels. Defaults to 0.5. box_noise_scale (float, optional): Noise scale for bounding box coordinates. Defaults to 1.0. training (bool, optional): If it's in training mode. Defaults to False. Returns: (Tuple[Optional[Tensor], Optional[Tensor], Optional[Tensor], Optional[Dict]]): The modified class embeddings, bounding boxes, attention mask and meta information for denoising. If not in training mode or 'num_dn' is less than or equal to 0, the function returns None for all elements in the tuple. r)NNNNrDr clsbboxes batch_idxr r!)r device?.NrWr%r()minmaxgư>)eps)rar$rr"T) dn_pos_idx dn_num_group dn_num_split) r*rdlenrepeatr0r,aranger.rarandr)nonzeror7 randint_liker r rand_likeclip_rlogitintzeroscatr-r+stackboolr;r=listreshapeto)&batch num_classes num_queries class_embednum_dncls_noise_ratiobox_noise_scaletrainingrD total_nummax_nums num_grouprGrCgt_bboxb_idxdn_clsdn_bboxdn_b_idxneg_idxridx new_label known_bboxdiff rand_sign rand_part dn_cls_embed padding_cls padding_bboxnum map_indicesrQpos_idxtgt_size attn_maskpdn_metas& r get_cdn_grouprs> 1%k"III9~H1}%("I!^I YB 5\FHoG + E]]1y= )FnnQ]A.G||A M*//3Hll9y0 7>>Z]fir]rrGzz&,,'?S+@AmmD!))"-&&sA{&,,W]WdWde s w' QR 3&..q!4F&&w15;cA OOG, 'c!Y i$&& Sc*J'++g40 A ) *Fv&L++b&,*<*>+,, -|{?Q?Q/RT]T`T`U$ %%3^PV$[s5R0R5R:>R?)drbr%F)r,torch.nnnntorch.nn.functional functionalr1scipy.optimizerultralytics.utils.metricsrultralytics.utils.opsrrModulerrrrrsC 0.6i5ryyi5\"%"% n%r