計算指標 Keras model 深度學習

Question

希望你一切順利; 我有一個 model 可以預測人體姿勢（彎曲、躺、坐、站）然后我有一個多標簽分類問題，我會計算我的 model 的指標（准確度、fmeasure、召回率、精度），問題，這個以下代碼在多標簽分類中計算這些指標是否正確？

def check_units(y_true, y_pred):
    if y_pred.shape[1] != 1:
        y_pred = y_pred[:,1:2]
        y_true = y_true[:,1:2]

return y_true, y_pred

def precision(y_true, y_pred):
    y_true, y_pred = check_units(y_true, y_pred)
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = true_positives / (predicted_positives + K.epsilon())

return precision

def recall(y_true, y_pred):
    y_true, y_pred = check_units(y_true, y_pred)
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
    recall = true_positives / (possible_positives + K.epsilon())

return recall

def fmeasure(y_true, y_pred):
    def recall(y_true, y_pred):
        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
        possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
        recall = true_positives / (possible_positives + K.epsilon())

    return recall

def precision(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = true_positives / (predicted_positives + K.epsilon())

    return precision

    y_true, y_pred = check_units(y_true, y_pred)
    precision = precision(y_true, y_pred)
    recall = recall(y_true, y_pred)

return 2*((precision*recall)/(precision+recall+K.epsilon()))

Answer 1

您可以在sklearn中使用內置函數，如下所示：

from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score

true_labels=[0,0,1,0,2,1,1,2,2,0,0,1]  # three classes 0,1,2
predicted_labels=[0,1,1,0,2,0,1,2,1,1,0,1] # predicted labels

print("Accuracy=",accuracy_score(true_labels,predicted_labels))
print("F1 Score=",f1_score(true_labels,predicted_labels, average="macro"))
print("Precision=",precision_score(true_labels,predicted_labels, average="macro"))
print("Recall=",recall_score(true_labels,predicted_labels, average="macro"))

您可以將函數的結果與這些內置函數進行比較以測試它們。 希望這可以幫助。