keras中是否有基于精度或召回率而不是损失的优化程序? [英] Is there an optimizer in keras based on precision or recall instead of loss?

问题描述

我正在开发一个只有两个类别的分段神经网络，即0和1(0是背景，而1是我想在图像上找到的对象).在每个图像上，大约1的80％和0的20％.如您所见，数据集是不平衡的，并且会导致结果错误.我的准确度是85％，损失也很低，但这仅仅是因为我的模型擅长寻找背景！

I am developping a segmentation neural network with only two classes, 0 and 1 (0 is the background and 1 the object that I want to find on the image). On each image, there are about 80% of 1 and 20% of 0. As you can see, the dataset is unbalanced and it makes the results wrong. My accuracy is 85% and my loss is low, but that is only because my model is good at finding the background !

我希望优化器基于另一个指标，例如精度或召回率，在这种情况下更有用.

I would like to base the optimizer on another metric, like precision or recall which is more usefull in this case.

有人知道如何实现吗?

推荐答案

由于我们的注释不够清楚，让我为您提供跟踪所需内容的代码.您不会使用精度或召回率来进行优化.您只需将它们作为有效分数进行跟踪即可获得最佳权重.请勿混合使用损失，优化程序，指标和其他内容.它们不是为了同一件事.

as our comment were not clear enough, let me give you the code to track what you need. You don't use precision or recall to be optimize. You just track them as valid scores to get the best weights. Do not mix loss, optimizer, metrics and other. They are not meant for the same thing.

THRESHOLD = 0.5
def precision(y_true, y_pred, threshold_shift=0.5-THRESHOLD):

    # just in case 
    y_pred = K.clip(y_pred, 0, 1)

    # shifting the prediction threshold from .5 if needed
    y_pred_bin = K.round(y_pred + threshold_shift)

    tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
    fp = K.sum(K.round(K.clip(y_pred_bin - y_true, 0, 1)))

    precision = tp / (tp + fp)
    return precision


def recall(y_true, y_pred, threshold_shift=0.5-THRESHOLD):

    # just in case 
    y_pred = K.clip(y_pred, 0, 1)

    # shifting the prediction threshold from .5 if needed
    y_pred_bin = K.round(y_pred + threshold_shift)

    tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
    fn = K.sum(K.round(K.clip(y_true - y_pred_bin, 0, 1)))

    recall = tp / (tp + fn)
    return recall


def fbeta(y_true, y_pred, threshold_shift=0.5-THRESHOLD):
    beta = 2

    # just in case 
    y_pred = K.clip(y_pred, 0, 1)

    # shifting the prediction threshold from .5 if needed
    y_pred_bin = K.round(y_pred + threshold_shift)

    tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
    fp = K.sum(K.round(K.clip(y_pred_bin - y_true, 0, 1)))
    fn = K.sum(K.round(K.clip(y_true - y_pred, 0, 1)))

    precision = tp / (tp + fp)
    recall = tp / (tp + fn)

    beta_squared = beta ** 2
    return (beta_squared + 1) * (precision * recall) / (beta_squared * precision + recall) 


def model_fit(X,y,X_test,y_test):
    class_weight={
    1: 1/(np.sum(y) / len(y)),
    0:1}
    np.random.seed(47)
    model = Sequential()
    model.add(Dense(1000, input_shape=(X.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dropout(0.35))
    model.add(Dense(500))
    model.add(Activation('relu'))
    model.add(Dropout(0.35))
    model.add(Dense(250))
    model.add(Activation('relu'))
    model.add(Dropout(0.35))
    model.add(Dense(1))
    model.add(Activation('sigmoid'))

    model.compile(loss='binary_crossentropy', optimizer='adamax',metrics=[fbeta,precision,recall])
    model.fit(X, y,validation_data=(X_test,y_test), epochs=200, batch_size=50, verbose=2,class_weight = class_weight)
    return model

这篇关于keras中是否有基于精度或召回率而不是损失的优化程序?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！