问题描述
我尝试参加我的第一场Kaggle比赛，其中给出 RMSLE 作为必需的损失函数。因为我对如何实现此损失函数一无所知，所以我尝试满足 RMSE 的要求。我知道这过去是 Keras 的一部分，有没有办法在最新版本中使用它，也许可以通过 backend ？
I try to participate in my first Kaggle competition where RMSLE is given as the required loss function. For I have found nothing how to implement this loss function I tried to settle for RMSE. I know this was part of Keras in the past, is there any way to use it in the latest version, maybe with a customized function via backend?
这是我设计的NN：
from keras.models import Sequential
from keras.layers.core import Dense , Dropout
from keras import regularizers
model = Sequential()
model.add(Dense(units = 128, kernel_initializer = "uniform", activation = "relu", input_dim = 28,activity_regularizer = regularizers.l2(0.01)))
model.add(Dropout(rate = 0.2))
model.add(Dense(units = 128, kernel_initializer = "uniform", activation = "relu"))
model.add(Dropout(rate = 0.2))
model.add(Dense(units = 1, kernel_initializer = "uniform", activation = "relu"))
model.compile(optimizer = "rmsprop", loss = "root_mean_squared_error")#, metrics =["accuracy"])
model.fit(train_set, label_log, batch_size = 32, epochs = 50, validation_split = 0.15)
我尝试了在GitHub上找到的自定义 root_mean_squared_error 函数，但就我所知，语法不是什么需要。我认为 y_true 和 y_pred 必须在传递给返回值之前进行定义，但我不知道该如何精确，我刚开始使用python编程，而我的数学确实不是那么好...
I tried a customized root_mean_squared_error function I found on GitHub but for all I know the syntax is not what is required. I think the y_true and the y_pred would have to be defined before passed to the return but I have no idea how exactly, I just started with programming in python and I am really not that good in math...
from keras import backend as K
def root_mean_squared_error(y_true, y_pred):
return K.sqrt(K.mean(K.square(y_pred - y_true), axis=-1))
此功能收到以下错误：
ValueError: ('Unknown loss function', ':root_mean_squared_error')
谢谢对于您的想法，我非常感谢您的帮助！
Thanks for your ideas, I appreciate every help!
推荐答案
使用自定义损失时，需要将其不带引号，例如您传递函数对象，而不是字符串：
When you use a custom loss, you need to put it without quotes, as you pass the function object, not a string:
def root_mean_squared_error(y_true, y_pred):
return K.sqrt(K.mean(K.square(y_pred - y_true)))
model.compile(optimizer = "rmsprop", loss = root_mean_squared_error,
metrics =["accuracy"])
这篇关于Keras中的RMSE / RMSLE损失函数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！