在keras的不同培训课程中不同的验证精度[副本]

我在Mnist上训练了keras模型,使训练和模型超参数保持一致。培训和验证数据完全相同。在不同的训练中,我得到了五种不同的准确度-0.71,0.62,0.59,0.52,0.46。模型每次从零开始训练8个时期

代码如下:

def train():
    model = Sequential()
    model.add(Dense(32, input_dim=784))
    model.add(Dense(10, activation="softmax"))
    model.compile(loss='categorical_crossentropy',
                  optimizer='adam',
                  metrics=['accuracy'])

    model.fit(x_train, y_train, batch_size=32, epochs=8, verbose=0)
    results = model.evaluate(x_test, y_test, verbose=0)
    print(results[1])


for i in range(5):
    print(i)
    train()

结果:

0
2019-01-23 13:26:54.475110: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
0.7192
1
0.6223
2
0.5976
3
0.5223
4
0.4624