测试准确率高于训练准确率

Question

为什么测试准确率高于我的训练准确率？这不是验证准确性的情况。是不是因为我拆分数据集的方式？

修改网络不起作用，所以我猜我在数据集准备部分做错了什么。

数据集由恶意软件和正常活动的数据包捕获组成。dataset.txt文件总共包含777行和28列。

#converting dataset and labels to numpy arrays
x = np.genfromtxt("dataset.txt", delimiter=",")
y = np.genfromtxt("label.txt", delimiter=",")

#handling missing values
x[np.isnan(x)] = 0

#shuffling the data
indices = np.arange(x.shape[0])
np.random.shuffle(indices)
x = x[indices]
y = y[indices]

#dividing the dataset into train and test 
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=0)

#building the model
def build_model():
        model = models.Sequential()
        model.add(layers.Dense(32, activation='relu', input_shape=(28,)))
        model.add(layers.Dense(32, activation='relu'))
        model.add(layers.Dense(32, activation='relu'))
        model.add(Dropout(0.2))
        model.add(layers.Dense(1, activation='sigmoid'))
        model.compile(optimizer='rmsprop',  loss='binary_crossentropy', 
                      metrics=['accuracy'])
        return model

'''cross validation 
k = 5
num_val_samples = len(x_train) // k
all_scores = []

for i in range(k):
   print('fold #', i)
   x_val = x_train[i * num_val_samples: (i + 1) * num_val_samples]
   y_val = y_train[i * num_val_samples: (i + 1) * num_val_samples]
   partial_x_train = np.concatenate([x_train[:i * num_val_samples], 
                     x_train[(i + 1) * num_val_samples:]], axis=0)
   partial_y_train = np.concatenate([y_train[:i * num_val_samples], 
                     y_train[(i + 1) * num_val_samples:]], axis=0)
   model = build_model()
   model.fit(partial_x_train, partial_y_train,epochs=20, batch_size=16, 
             verbose=0)
   val_loss, val_acc = model.evaluate(x_val, y_val, verbose=0)
   all_scores.append(val_acc)

print(all_scores)
val_acc = np.mean(all_scores)
print(val_loss , val_acc) 
'''

#training the model with the entire training dataset
model = build_model()
model.fit(x_train, y_train, epochs=20, batch_size=16)

#confusion matrix
y_pred = model.predict(x_test)
y_pred = (y_pred > 0.5)
result = confusion_matrix(y_test, y_pred)
print ('Confusion Matrix:')
print(result)

#calculating the test accuracy
model_acc = accuracy_score(y_test, y_pred)
print('Test Accuracy:')
print(model_acc)

Answer 1

这是因为keras报告了每个时期的平均准确率。对于少量的时期，这意味着在一个时期结束时，你的模型比这个时期的平均水平更好。

这也可能是因为测试集中随机地有“更容易”的样本，但如果你在代码的相同部分随机拆分它，这种情况就不会在每次运行时发生。