a dY@sNddlZddlmZd ejejeeejdddZejejejdd d ZdS) N)confusion_matrixư>)inputtarget num_classesepsreturnc Cst|s(|jtjur(tdt|t|sP|jtjurPtdt||j|jksptd|j|j|j |j kstd|j |j t |t r|dkrtd|t |||}tj |dd}tj |dd}tj|d d d }|||}||||} | S) aCalculate mean Intersection-Over-Union (mIOU). The function internally computes the confusion matrix. Args: input : tensor with estimated targets returned by a classifier. The shape can be :math:`(B, *)` and must contain integer values between 0 and K-1. target: tensor with ground truth (correct) target values. The shape can be :math:`(B, *)` and must contain integer values between 0 and K-1, where targets are assumed to be provided as one-hot vectors. num_classes: total possible number of classes in target. Returns: a tensor representing the mean intersection-over union with shape :math:`(B, K)` where K is the number of classes. Example: >>> logits = torch.tensor([[0, 1, 0]]) >>> target = torch.tensor([[0, 1, 0]]) >>> mean_iou(logits, target, num_classes=3) tensor([[1., 1., 1.]]) zEInput input type is not a torch.Tensor with torch.int64 dtype. Got {}zFInput target type is not a torch.Tensor with torch.int64 dtype. Got {}z@Inputs input and target must have the same shape. Got: {} and {}z/Inputs must be in the same device. Got: {} - {}zAThe number of classes must be an integer bigger than two. Got: {}r)Zdim)Zdim1Zdim2)torchZ is_tensorZdtypeint64 TypeErrorformattypeshape ValueErrorZdevice isinstanceintrsumZdiagonal) rrrrZconf_matZ sum_over_rowZ sum_over_colZ conf_mat_diag denominatorZiousr`/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/kornia/metrics/mean_iou.pymean_ious*     r)boxes_1boxes_2r c Cs|dddf|dddfdksX|dddf|dddfdksXtd|dddf|dddfdks|dddf|dddfdkstdt|ddddfd|ddddfd}t|ddddfd|ddddfd}tj||dd}|dddddf|dddddf}|dddf|dddf|dddf|dddf}|dddf|dddf|dddf|dddf}|d|d|}||S) aCompute the IoU of the cartesian product of two sets of boxes. Each box in each set shall be (x1, y1, x2, y2). Args: boxes_1: a tensor of bounding boxes in :math:`(B1, 4)`. boxes_2: a tensor of bounding boxes in :math:`(B2, 4)`. Returns: a tensor in dimensions :math:`(B1, B2)`, representing the intersection of each of the boxes in set 1 with respect to each of the boxes in set 2. Example: >>> boxes_1 = torch.tensor([[40, 40, 60, 60], [30, 40, 50, 60]]) >>> boxes_2 = torch.tensor([[40, 50, 60, 70], [30, 40, 40, 50]]) >>> mean_iou_bbox(boxes_1, boxes_2) tensor([[0.3333, 0.0000], [0.1429, 0.2500]]) Nr rrz0Boxes_1 does not follow (x1, y1, x2, y2) format.z0Boxes_2 does not follow (x1, y1, x2, y2) format.)min)allAssertionErrorr maxZ unsqueezerclamp) rrZ lower_boundsZ upper_boundsZintersection_dims intersectionZ areas_set_1Z areas_set_2unionrrr mean_iou_bbox?sPP88,@@r%)r)r rZTensorrfloatrr%rrrrs 9