CNN：人工智能之神经网络算法进阶优化，六种不同优化算法实现手写数字识别逐步提高，应用案例自动驾驶之捕捉并识别周围车牌号—Jason niu

import mnist_loader
from network3 import Network                                         
from network3 import ConvPoolLayer, FullyConnectedLayer, SoftmaxLayer  

training_data, validation_data, test_data = mnist_loader.load_data_wrapper()   
mini_batch_size = 10  

#NN算法：sigmoid函数；准确率97%
net = Network([        
        FullyConnectedLayer(n_in=784, n_out=100),          
        SoftmaxLayer(n_in=100, n_out=10)], mini_batch_size) 
net.SGD(training_data, 60, mini_batch_size, 0.1, validation_data, test_data) 

#CNN算法：1层Convolution+sigmoid函数；准确率98.78%
net = Network([        
        ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28), 
                      filter_shape=(20, 1, 5, 5),           
                      poolsize=(2, 2)),                     
        FullyConnectedLayer(n_in=20*12*12, n_out=100),      
        SoftmaxLayer(n_in=100, n_out=10)], mini_batch_size) 

#CNN算法：2层Convolution+sigmoid函数；准确率99.06%。层数过多并不会使准确率大幅度提高，有可能overfit，合适的层数需要通过实验验证出来，并不是越多越好
net = Network([
        ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28), 
                      filter_shape=(20, 1, 5, 5), 
                      poolsize=(2, 2)),
        ConvPoolLayer(image_shape=(mini_batch_size, 20, 12, 12), 
                      filter_shape=(40, 20, 5, 5), 
                      poolsize=(2, 2)),
        FullyConnectedLayer(n_in=40*4*4, n_out=100),
        SoftmaxLayer(n_in=100, n_out=10)], mini_batch_size)

#CNN算法：用Rectified Linear Units即f(z) = max(0, z)，代替sigmoid函数；准确率99.23%
net = Network([
        ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28), 
                      filter_shape=(20, 1, 5, 5), 
                      poolsize=(2, 2), 
                      activation_fn=ReLU),   #激活函数采用ReLU函数
        ConvPoolLayer(image_shape=(mini_batch_size, 20, 12, 12), 
                      filter_shape=(40, 20, 5, 5), 
                      poolsize=(2, 2), 
                      activation_fn=ReLU),
        FullyConnectedLayer(n_in=40*4*4, n_out=100, activation_fn=ReLU),
        SoftmaxLayer(n_in=100, n_out=10)], mini_batch_size)

#CNN算法：用ReLU函数+增大训练集25万(原先50000*5，只需将每个像素向上下左右移动一个像素)；准确率99.37%
$ python expand_mnist.py   #将图片像素向上下左右移动
expanded_training_data, _, _ = network3.load_data_shared("../data/mnist_expanded.pkl.gz")  
net = Network([
        ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28), 
                      filter_shape=(20, 1, 5, 5), 
                      poolsize=(2, 2), 
                      activation_fn=ReLU),
        ConvPoolLayer(image_shape=(mini_batch_size, 20, 12, 12), 
                      filter_shape=(40, 20, 5, 5), 
                      poolsize=(2, 2), 
                      activation_fn=ReLU),
        FullyConnectedLayer(n_in=40*4*4, n_out=100, activation_fn=ReLU),
        SoftmaxLayer(n_in=100, n_out=10)], mini_batch_size)
net.SGD(expanded_training_data, 60, mini_batch_size, 0.03,validation_data, test_data, lmbda=0.1)


#CNN算法：用ReLU函数+增大训练集25万+dropout(随机选取一半神经元)用在最后的FullyConnected层；准确率99.60%
expanded_training_data, _, _ = network3.load_data_shared("../data/mnist_expanded.pkl.gz")
net = Network([
        ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28), 
                      filter_shape=(20, 1, 5, 5), 
                      poolsize=(2, 2), 
                      activation_fn=ReLU),
        ConvPoolLayer(image_shape=(mini_batch_size, 20, 12, 12), 
                      filter_shape=(40, 20, 5, 5), 
                      poolsize=(2, 2), 
                      activation_fn=ReLU),
        FullyConnectedLayer(
            n_in=40*4*4, n_out=1000, activation_fn=ReLU, p_dropout=0.5),
        FullyConnectedLayer(
            n_in=1000, n_out=1000, activation_fn=ReLU, p_dropout=0.5),
        SoftmaxLayer(n_in=1000, n_out=10, p_dropout=0.5)], 
        mini_batch_size)
net.SGD(expanded_training_data, 40, mini_batch_size, 0.03,validation_data, test_data)