Python 3.x 如何使用keras测试深度学习模型？

我正在尝试使用keras在深度学习模型中测试我的拆分 这是我的密码

 from keras.models import Sequential
from keras.layers import Dense, Dropout
import numpy as np
from scipy import signal
import matplotlib.pyplot as plt
import pandas as pd
import itertools
np.random.seed(7)

train = np.loadtxt("TrainDatasetFinal.txt", delimiter=",")
test = np.loadtxt("testDatasetFinal.txt", delimiter=",")

y_train = train[:,7]
y_test = test[:,7]

magnitude_training = train[:,5]
norm_train = (magnitude_training - np.mean(magnitude_training))/np.std(magnitude_training)
magnitude_testing = test[:,5]
norm_test = (magnitude_testing - np.mean(magnitude_testing))/np.std(magnitude_testing)

model = Sequential()
model.add(Dense(12, input_dim=1, activation='relu'))
model.add(Dense(8,  activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy' , optimizer='adam', metrics=['accuracy'])

model.fit(norm_train, y_train, epochs=2, batch_size=64, verbose=2)

score=model.evaluate(norm_test, y_test, verbose=2)
print(score)

对于培训，它给了我以下输出

Epoch 1/2
 - 34s - loss: 0.2077 - acc: 0.9430
Epoch 2/2
 - 35s - loss: 0.2027 - acc: 0.9430

但是测试输出我无法理解

[0.22448099704202343, 0.939972481247623]

---

这两个数字是什么？

0.2244809970402343：测试损耗

---

0.939972481247623：测试准确度

如果您打印

模型。度量名称

您将获得输出

['loss'，'acc']

“测试准确度”是测试准确度的平均值？？是的，它是平均值。