计算F1-Score'加权'在Keras

时间:2018-05-02 16:11:45

标签: python neural-network keras classification

我想计算一个F1分数加权,以便惩罚我罕见标签上的错误。 不幸的是,我甚至无法获得正常的F1比分。 这些是我的指标

def sensitivity(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)))
    return true_positives / (possible_positives + K.epsilon())

def specificity(y_true, y_pred):
    true_negatives = K.sum(K.round(K.clip((1-y_true) * (1-y_pred), 0, 1)))
    possible_negatives = K.sum(K.round(K.clip(1-y_true, 0, 1)))
    return true_negatives / (possible_negatives + K.epsilon())

def f1(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
    precision = precision(y_true, y_pred)
    recall = recall(y_true, y_pred)
    return 2*((precision*recall)/(precision+recall)) 

model.compile(loss='binary_crossentropy',
              optimizer=RMSprop(0.001),
              metrics=[sensitivity, specificity, 'accuracy', f1])

在这里我训练模型并评估:

model.fit(x_train, y_train, epochs=12, batch_size=32, verbose=1, class_weight=class_weights_dict, validation_split=0.3)
classes = model.predict(x_test)
loss_and_metrics = model.evaluate(x_test, y_test, batch_size=128, verbose=1)

我总是得到nan作为f1得分,代码有问题吗?因为数据与我使用的sklearn与SVM分类器相同。 我还没有解决加权计算问题。 结果如下:

Epoch 1/12
5133/5133 [==============================] - 5s 976us/step - loss: 0.6955 - sensitivity: 0.0561 - specificity: 0.9377 - acc: 0.8712 - f1: nan - val_loss: 0.6884 - val_sensitivity: 0.8836 - val_specificity: 0.0000e+00 - val_acc: 0.0723 - val_f1: nan
Epoch 2/12
5133/5133 [==============================] - 5s 894us/step - loss: 0.6954 - sensitivity: 0.3865 - specificity: 0.5548 - acc: 0.5398 - f1: nan - val_loss: 0.6884 - val_sensitivity: 0.0000e+00 - val_specificity: 1.0000 - val_acc: 0.9277 - val_f1: nan
Epoch 3/12
5133/5133 [==============================] - 5s 925us/step - loss: 0.6953 - sensitivity: 0.3928 - specificity: 0.5823 - acc: 0.5696 - f1: nan - val_loss: 0.6884 - val_sensitivity: 0.0000e+00 - val_specificity: 1.0000 - val_acc: 0.9277 - val_f1: nan
Epoch 4/12
5133/5133 [==============================] - 5s 935us/step - loss: 0.6954 - sensitivity: 0.1309 - specificity: 0.8504 - acc: 0.7976 - f1: nan - val_loss: 0.6884 - val_sensitivity: 0.0000e+00 - val_specificity: 1.0000 - val_acc: 0.9277 - val_f1: nan
etc.

决赛:     [0.6859536773606656,0.0,1.0,0.9321705426356589,nan]

提前感谢您的建议

1 个答案:

答案 0 :(得分:0)

关于f1指标中的nan:

如果查看日志,验证灵敏度为0.这意味着您的精确度和召回率也都为零。因此,在f1计算中,您将除以零并得到一个纳米。

添加K.epsilon(),就像在其他函数中一样。

在旁注中,从您的损失来判断,这对火车组的改善可以忽略不计,您的网络什么都没学到。我建议你首先增加时代数量,使网络更深入,不要将任何内容传递给class_weight参数(你提到的还没有使用加权计算,但你的代码确实设置了一些类权重)。