kears 4_mnist数据集分类_交叉熵_dropou

from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import SGD
from keras.regularizers import l2

# 载入数据
(x_train, y_train), (x_test, y_test) = mnist.load_data()
print("x_train:", x_train.shape, "y_train:", y_train.shape)

# 将数据由（60000,28,28）转换为（60000,784），并进行归一化
x_train = x_train.reshape(x_train.shape[0], -1) / 255.0
x_test = x_test.reshape(x_test.shape[0], -1) / 255.0

# 将数据标签转换为one-hot编码的格式
y_train = np_utils.to_categorical(y_train, num_classes=10)
y_test = np_utils.to_categorical(y_test, num_classes=10)

# 创建网络模型，输入是784个神经元，输出为10类
model = Sequential(
    [Dense(units=200,input_dim=784,bias_initializer="one",activation="relu"),
     Dropout(0.5),
     Dense(units=300,bias_initializer="one",activation="relu"),
     Dropout(0.5),
     Dense(units=10,bias_initializer="one",activation="softmax")
     ]
)

# 自定义优化器
sgd = SGD(lr=0.1)

# 编译模型，定义优化器，loss_funcion,训练过程计算准确率
model.compile(optimizer=sgd,loss="categorical_crossentropy",metrics=["accuracy"],)

# 喂入数据集，
model.fit(x_train,y_train,batch_size=32,epochs=20)

# 评估模型
loss,accuracy = model.evaluate(x_test, y_test)
print("test losee:",loss,"accuracy:",accuracy)