我在计算模型的准确性、召回率、精确度和 f1 分数时遇到问题

Question

我的混淆矩阵工作正常，只是在生成分数时遇到了一些问题。一点帮助将大有帮助。我目前收到错误。 "Tensor object is not callable"。

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

这一行有问题。

cm = confusion_matrix(classes, preds)

confusion_matrix 是张量，不能像函数一样调用它。因此 Tensor is not callable。我也是，不确定你为什么需要这条线。相反，我想你会想写 cm= confusion_matrix.cpu().data.numpy() 使它成为我认为的 numpy 数组。从你的代码来看，cm 似乎是 np.array.

Answer 2

你可以试试下面的代码，

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)

调用函数为，

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

我在计算模型的准确性、召回率、精确度和 f1 分数时遇到问题

I am having trouble calculating the accuracy, recall, precision and f1-score for my model

confusion-matrix

deep-learning

pytorch