方式1 只含参数y_true和y_pred
特点:适合只利用y_true和y_pred设计简单的loss,比如MSE、MAE、交叉熵loss等等
import keras.backend as K
"""
这里定义model
"""
# 只含参数 y_true, y_pred
# MSE loss
def mean_squared_error(y_true, y_pred):
# 这里自己写,或者直接return
return K.mean(K.square(y_pred - y_true), axis=-1)
model.compile(optimizer='rmsprop',
loss=mean_squared_error, # 这里对应上面loss函数名称即可
metrics=['accuracy', mean_pred])
"""
下面为其他loss函数,可替换上面的MSE loss
"""
def mean_absolute_error(y_true, y_pred):
return K.mean(K.abs(y_pred - y_true), axis=-1)
def mean_absolute_percentage_error(y_true, y_pred):
diff = K.abs((y_true - y_pred) / K.clip(K.abs(y_true), K.epsilon(), np.inf))
return 100. * K.mean(diff, axis=-1)
def mean_squared_logarithmic_error(y_true, y_pred):
first_log = K.log(K.clip(y_pred, K.epsilon(), np.inf) + 1.)
second_log = K.log(K.clip(y_true, K.epsilon(), np.inf) + 1.)
return K.mean(K.square(first_log - second_log), axis=-1)
def squared_hinge(y_true, y_pred):
return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)), axis=-1)
def hinge(y_true, y_pred):
return K.mean(K.maximum(1. - y_true * y_pred, 0.), axis=-1)
def categorical_crossentropy(y_true, y_pred):
'''Expects a binary class matrix instead of a vector of scalar classes.
'''
return K.categorical_crossentropy(y_pred, y_true)
def sparse_categorical_crossentropy(y_true, y_pred):
'''expects an array of integer classes.
Note: labels shape must have the same number of dimensions as output shape.
If you get a shape error, add a length-1 dimension to labels.
'''
return K.sparse_categorical_crossentropy(y_pred, y_true)
def binary_crossentropy(y_true, y_pred):
return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
def kullback_leibler_divergence(y_true, y_pred):
y_true = K.clip(y_true, K.epsilon(), 1)
y_pred = K.clip(y_pred, K.epsilon(), 1)
return K.sum(y_true * K.log(y_true / y_pred), axis=-1)
def poisson(y_true, y_pred):
return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)
def cosine_proximity(y_true, y_pred):
y_true = K.l2_normalize(y_true, axis=-1)
y_pred = K.l2_normalize(y_pred, axis=-1)
return -K.mean(y_true * y_pred, axis=-1)
方式2 将自定义loss写为层 (可实现多输入)
特点:适合利用多输入设计复杂loss,比如计算网络中任意两个特征之间的距离等等
参考:
Keras中自定义复杂的loss函数 - 科学空间|Scientific Spaces (kexue.fm)
keras 自定义 loss损失函数, sample在loss上的加权 和 metric_keras add_loss-CSDN博客
Keras中无损实现复杂(多入参)的损失函数 - 知乎 (zhihu.com)
Faster R-CNN系列(三):用keras构建多输入-多输出-多自定义loss的模型_keras 多输出自定义损失层-CSDN博客
方式3 重点:如何只利用参数y_true和y_pred实现自定义loss?
特点:方式2的便捷版,但适用情况有限
思路:根据自己的网络模型,将要添加的loss,比如网络中两个分支的特征feature1和feature2做L2范数loss,这时候可以在网络中提前算好特征feature1和feature2的L2 loss,然后将输出结果和y_pred做级联,再在方式1的写法中,拆开即可
注意:本方式仅适合临时凑活用(懒得调了)
import keras.backend as K
"""
这里定义model
"""
def model():
input =
feature1 = Conv2D(...)(input)
feature2 = Conv2D(...)(...)
output= Conv2D(...)(...)
# 这里先计算feature1和feature2 之间的距离
loss_dis_feature = ...
output = Lambda(tf.concat)([output, loss_dis_feature])
return model(input, output)
def custom_loss(y_true, y_pred):
# 将y_pred中拆分出loss_dis_feature
loss1 = loss_dis_feature
# 这里时原始的的loss,由y_true, y_pred计算得到
loss2 = K.mean(K.square(y_pred - y_true), axis=-1)
return loss1 + loss2
model.compile(optimizer='rmsprop',
loss=custom_loss, # 这里返回函数名称
metrics=['accuracy', mean_pred])