卷积神经网络python实例

以下是一个使用Python和Keras库实现卷积神经网络的例子：

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras.datasets import mnist

# 加载MNIST数据集
(X_train, y_train), (X_test, y_test) = mnist.load_data()

# 将数据集转换为4D张量
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1)
X_test = X_test.reshape(X_test.shape[0], 28, 28,1)

# 将数据类型转换为float32
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')

# 将像素值标准化到0到1之间
X_train /= 255
X_test /= 255

# 将类向量转换为二进制类矩阵
Y_train = np_utils.to_categorical(y_train, 10)
Y_test = np_utils.to_categorical(y_test,10)

# 创建模型
model = Sequential()

# 添加卷积层和池化层
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

# 添加全连接层
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))

# 编译模型
model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

# 训练模型
model.fit(X_train, Y_train,
          batch_size=32, epochs=10, verbose=1)

# 评估模型
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

该模型使用了两个卷积层和一个池化层，然后是两个全连接层。它被训练用于MNIST手写数字识别数据集，并在测试集上获得了约99％的准确率。