keras 中是否有基于精度或召回率而不是损失的优化器? [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的分割神经网络，0 和 1(0 是背景，1 是我想在图像上找到的对象).在每张图像上，大约有 80% 的 1 和 20% 的 0.如您所见，数据集不平衡，导致结果错误.我的准确率是 85%，我的损失很低，但这只是因为我的模型很擅长寻找背景！

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，例如在这种情况下更有用的精度或召回率.

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

您不使用精度或召回来进行优化.您只需将它们作为有效分数进行跟踪即可获得最佳权重.不要混合损失、优化器、指标和其他.它们的用途不同.

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器?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！