在 Keras 的 MNIST 数字识别中获得不同的测试数据精度
Posted
技术标签:
【中文标题】在 Keras 的 MNIST 数字识别中获得不同的测试数据精度【英文标题】:Getting different accuracy on test data in MNIST digit recognition in Keras 【发布时间】:2019-04-11 23:51:42 【问题描述】:我正在使用 Keras 进行 手写数字识别,我有两个文件:predict.py 和 train.py。
train.py 训练模型(如果尚未训练)并将其保存到一个目录中,否则它只会从保存到的目录中加载经过训练的模型并打印 @ 987654321@和Test Accuracy
。
def getData():
(X_train, y_train), (X_test, y_test) = mnist.load_data()
y_train = to_categorical(y_train, num_classes=10)
y_test = to_categorical(y_test, num_classes=10)
X_train = X_train.reshape(X_train.shape[0], 784)
X_test = X_test.reshape(X_test.shape[0], 784)
# normalizing the data to help with the training
X_train /= 255
X_test /= 255
return X_train, y_train, X_test, y_test
def trainModel(X_train, y_train, X_test, y_test):
# training parameters
batch_size = 1
epochs = 10
# create model and add layers
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(784,)))
model.add(Dense(10, activation = 'softmax'))
# compiling the sequential model
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
# training the model and saving metrics in history
history = model.fit(X_train, y_train,
batch_size=batch_size, epochs=epochs,
verbose=2,
validation_data=(X_test, y_test))
loss_and_metrics = model.evaluate(X_test, y_test, verbose=2)
print("Test Loss", loss_and_metrics[0])
print("Test Accuracy", loss_and_metrics[1])
# Save model structure and weights
model_json = model.to_json()
with open('model.json', 'w') as json_file:
json_file.write(model_json)
model.save_weights('mnist_model.h5')
return model
def loadModel():
json_file = open('model.json', 'r')
model_json = json_file.read()
json_file.close()
model = model_from_json(model_json)
model.load_weights("mnist_model.h5")
return model
X_train, y_train, X_test, y_test = getData()
if(not os.path.exists('mnist_model.h5')):
model = trainModel(X_train, y_train, X_test, y_test)
print('trained model')
print(model.summary())
else:
model = loadModel()
print('loaded model')
print(model.summary())
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
loss_and_metrics = model.evaluate(X_test, y_test, verbose=2)
print("Test Loss", loss_and_metrics[0])
print("Test Accuracy", loss_and_metrics[1])
这是输出(假设模型之前训练过,这次模型将被加载):
('测试损失', 1.741784990310669)
('测试精度', 0.414)
predict.py,另一方面,预测一个手写数字:
def loadModel():
json_file = open('model.json', 'r')
model_json = json_file.read()
json_file.close()
model = model_from_json(model_json)
model.load_weights("mnist_model.h5")
return model
model = loadModel()
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
(X_train, y_train), (X_test, y_test) = mnist.load_data()
y_test = to_categorical(y_test, num_classes=10)
X_test = X_test.reshape(X_test.shape[0], 28*28)
loss_and_metrics = model.evaluate(X_test, y_test, verbose=2)
print("Test Loss", loss_and_metrics[0])
print("Test Accuracy", loss_and_metrics[1])
在这种情况下,令我惊讶的是,得到以下结果:
('测试损失', 1.8380377866744995)
('测试精度', 0.8856)
在第二个文件中,我得到的 Test Accuracy
为 0.88(是我之前得到的两倍多)。
另外,model.summery()
在两个文件中是相同的:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 64) 50240
_________________________________________________________________
dense_2 (Dense) (None, 10) 650
=================================================================
Total params: 50,890
Trainable params: 50,890
Non-trainable params: 0
_________________________________________________________________
我无法弄清楚这种行为背后的原因。正常吗?还是我错过了什么?
【问题讨论】:
在训练模型之前没有进行任何预处理吗? 我做到了。编辑了我的问题(我现在已经包含了完整的文件) 我猜你使用的是 Python 2.x? 是的,Python 2.7.15rc1
【参考方案1】:
这种差异是由于一次您使用标准化数据(即除以 255)调用evaluate()
方法而另一次(即在“predict.py”文件中)您使用非标准化数据调用它数据。在推理时间(即测试时间),您应该始终使用与训练数据相同的预处理步骤。
此外,首先将数据转换为浮点数,然后将其除以 255(否则,使用/
,在 Python 2.x 中会进行真正的除法,而在 Python 3.x 中运行@987654323 时会出错@和X_test /= 255
):
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255.
X_test /= 255.
【讨论】:
以上是关于在 Keras 的 MNIST 数字识别中获得不同的测试数据精度的主要内容,如果未能解决你的问题,请参考以下文章
keras库的安装及使用,以全连接层和手写数字识别MNIST为例