Question

我的困惑矩阵工作正常，只是在生成分数时遇到了一些麻烦。一点帮助将大有帮助。我目前收到错误消息。 “张量对象不可调用”。

def get_confused(model_ft):
    nb_classes = 120
    from sklearn.metrics import precision_recall_fscore_support as score
    confusion_matrix = torch.zeros(nb_classes, nb_classes)
    with torch.no_grad():
        for i, (inputs, classes) in enumerate(dataloaders['val']):
            inputs = inputs.to(device)
            classes = classes.to(device)
            outputs = model_ft(inputs)
            _, preds = torch.max(outputs, 1)
            for t, p in zip(classes.view(-1), preds.view(-1)):
                    confusion_matrix[t.long(), p.long()] += 1

            cm = confusion_matrix(classes, preds)
            recall = np.diag(cm) / np.sum(cm, axis = 1)
            precision = np.diag(cm) / np.sum(cm, axis = 0)
    print(confusion_matrix)
    print(confusion_matrix.diag()/confusion_matrix.sum(1))

Answer 1

问题在于此行。

cm = confusion_matrix(classes, preds)

confusion_matrix是一个张量，您不能像函数一样调用它。因此Tensor is not callable。我也不确定您为什么需要此行。相反，我认为您可能想编写cm= confusion_matrix.cpu().data.numpy()使其成为我认为的numpy数组。从您的代码看来，cm是np.array。

Answer 2

您可以尝试以下代码

def F_score(logit, label, threshold=0.5, beta=2):
    prob = torch.sigmoid(logit)
    prob = prob > threshold
    label = label > threshold
    TP = (prob & label).sum().float()
    TN = ((~prob) & (~label)).sum().float()
    FP = (prob & (~label)).sum().float()
    FN = ((~prob) & label).sum().float()
    accuracy = (TP+TN)/(TP+TN+FP+FN)
    precision = torch.mean(TP / (TP + FP + 1e-12))
    recall = torch.mean(TP / (TP + FN + 1e-12))
    F2 = (1 + beta**2) * precision * recall / (beta**2 * precision + recall + 1e-12)
    return accuracy, precision, recall, F2.mean(0)

将函数称为

accuracy, precision, recall, F1_score = F_score(output.squeeze(), labels.float())

参考：- https://www.kaggle.com/c/human-protein-atlas-image-classification/discussion/73246

我无法为模型计算准确性，召回率，准确性和f1分数

2 个答案: