13、计算机视觉深度学习：卷积神经网络与小数据集训练

计算机视觉深度学习：卷积神经网络与小数据集训练

1. 卷积神经网络基础

1.1 数据预处理与模型训练

在计算机视觉领域，卷积神经网络（Convolutional Neural Networks, CNN）表现出色。以MNIST数据集为例，以下是数据预处理和模型训练的代码：

train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32') / 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=5, batch_size=64)

对模型在测试数据上进行评估：

test_loss, test_acc = model.