o oi" @s4ddlZ d dejdejdededejf dd ZdS) NFpredtarget num_classes normalizedreturncCsTt|s|jtjurtdt|t|s(|jtjur(tdt||j|jks:td|jd|j|j|jksLtd|jd|jt |t rU|dkr\td||jd }|||}| |d }g}t |D]}||} tj | |dd } || qst|} | |||tj} |rtj| d d d} | | d} | S)a Compute confusion matrix to evaluate the accuracy of a classification. Args: pred: 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. normalized: whether to return the confusion matrix normalized. Returns: a tensor containing the confusion matrix with shape :math:`(B, K, K)` where K is the number of classes. Example: >>> logits = torch.tensor([[0, 1, 0]]) >>> target = torch.tensor([[0, 1, 0]]) >>> confusion_matrix(logits, target, num_classes=3) tensor([[[2., 0., 0.], [0., 1., 0.], [0., 0., 0.]]]) zBInput pred type is not a torch.Tensor with torch.int64 dtype. Got zDInput target type is not a torch.Tensor with torch.int64 dtype. Got z6Inputs pred and target must have the same shape. Got: z and z(Inputs must be in the same device. Got: z - z?The number of classes must be an integer bigger than two. Got: r) minlengthT)dimkeepdimgư>)torch is_tensordtypeint64 TypeErrortypeshape ValueErrordevice isinstanceintviewrangebincountappendstacktofloat32sum)rrrr batch_size pre_bincountpre_bincount_vecconfusion_listiter_idpb bin_count confusion_vec confusion_matnorm_valr*S/home/ubuntu/.local/lib/python3.10/site-packages/kornia/metrics/confusion_matrix.pyconfusion_matrixs0         r,)F)r Tensorrboolr,r*r*r*r+s