在 Keras 中规范化神经网络的验证集

Question

所以，我知道规范化对于训练神经网络很重要。

我也明白我必须使用训练集中的参数规范化验证和测试集(例如，请参阅此讨论：https://stats.stackexchange.com/questions/77350/perform-feature-normalization-before-or-within-model-validation(

我的问题是：如何在 Keras 中执行此操作？

我目前正在做的是：

import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.callbacks import EarlyStopping
def Normalize(data):
mean_data = np.mean(data)
std_data = np.std(data)
norm_data = (data-mean_data)/std_data
return norm_data
input_data, targets = np.loadtxt(fname='data', delimiter=';')
norm_input = Normalize(input_data)
model = Sequential()
model.add(Dense(25, input_dim=20, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
early_stopping = EarlyStopping(monitor='val_acc', patience=50) 
model.fit(norm_input, targets, validation_split=0.2, batch_size=15, callbacks=[early_stopping], verbose=1)

但是在这里，我首先对整个数据集的数据进行规范化，然后拆分验证集，根据上述讨论，这是错误的。

从训练集(training_mean 和 training_std 中保存平均值和标准差没什么大不了的，但是我如何分别在验证集上应用training_mean和training_std的归一化？

Answer 1

以下代码正是您想要的：

import numpy as np
def normalize(x_train, x_test):
mu = np.mean(x_train, axis=0)
std = np.std(x_train, axis=0)
x_train_normalized = (x_train - mu) / std
x_test_normalized = (x_test - mu) / std
return x_train_normalized, x_test_normalized

然后你可以像这样将它与 keras 一起使用：

from keras.datasets import boston_housing
(x_train, y_train), (x_test, y_test) = boston_housing.load_data()
x_train, x_test = normalize(x_train, x_test)

丰益国际的回答是不正确的。

Answer 2

在使用sklearn.model_selection.train_test_split拟合模型之前，可以手动将数据拆分为训练数据集和测试数据集。然后，根据训练数据的平均值和标准差规范化训练和测试数据。最后，使用validation_data参数调用model.fit。

代码示例

import numpy as np
from sklearn.model_selection import train_test_split
data = np.random.randint(0,100,200).reshape(20,10)
target = np.random.randint(0,1,20)
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2)
def Normalize(data, mean_data =None, std_data =None):
if not mean_data:
mean_data = np.mean(data)
if not std_data:
std_data = np.std(data)
norm_data = (data-mean_data)/std_data
return norm_data, mean_data, std_data
X_train, mean_data, std_data = Normalize(X_train)
X_test, _, _ = Normalize(X_test, mean_data, std_data)
model.fit(X_train, y_train, validation_data=(X_test,y_test), batch_size=15, callbacks=[early_stopping], verbose=1)