手写数字识别完整代码带注释
时间: 2023-09-14 19:06:25 浏览: 50
好的,以下是手写数字识别的完整代码带注释,使用的是Python和Keras框架:
```python
# 导入所需的库和模块
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import RMSprop
# 加载MNIST数据集并将其分为训练集和测试集
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# 将训练集和测试集的像素值从0到255的范围缩放到0到1的范围内
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
# 将标签转换为独热编码形式
y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)
# 创建模型,包含两个隐藏层和一个输出层
model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784,)))
model.add(Dropout(0.2))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
# 输出模型的结构信息
model.summary()
# 编译模型,使用交叉熵损失函数和RMSprop优化器
model.compile(loss='categorical_crossentropy',
optimizer=RMSprop(),
metrics=['accuracy'])
# 训练模型并在测试集上进行评估
history = model.fit(x_train, y_train,
batch_size=128,
epochs=20,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
```
注释中已经解释了每个步骤的作用,这个代码可以训练一个具有两个隐藏层和一个输出层的神经网络模型,用于识别手写数字。