Shallow Net in Keras

简单神经网络实现mnist数据集分类（Keras）

# 导入模块
import numpy as np
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import BatchNormalization
from keras.optimizers import SGD

np.random.seed(42)  # 设置随机数种子
n_classes = 10  # 分类的类别数

#加载数据
(X_train, y_train), (X_test, y_test) = mnist.load_data()
'''观察数据结构
print(X_train.shape)
print(y_train.shape)
print(X_test.shape)
print(y_test.shape)
'''

# 改变数据形状，将其转化成向量表示
X_train = X_train.reshape(60000, 784).astype('float32')
X_test = X_test.reshape(10000, 784).astype('float32')

# 归一化，将范围缩小到0~1
X_train /= 255
X_test /= 255

# 将类别标签转化成one-hot形式
y_train = keras.utils.to_categorical(y_train, n_classes)
y_test = keras.utils.to_categorical(y_test, n_classes)

#构建模型
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(784,)))
model.add(BatchNormalization())
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))

# 编译创建好的模型
model.compile(optimizer=SGD(lr=0.01), loss='mean_squared_error', metrics=['accuracy'])

# 拟合模型
model.fit(X_train, y_train, batch_size=128, epochs=20, verbose=1, validation_data=(X_test, y_test))