Python學習之路：MINST實戰第一版

1、項目介紹：

搭建淺層神經網絡完成MNIST數字圖像的識別。

2、詳細步驟：

（1）將二維圖像轉成一維，MNIST圖像大小為28*28，轉成一維就是784。

（2）定義好神經網絡的相關參數：

# MNIST數據集相關的常數
INPUT_NODE = 784;
OUTPUT_NODE = 10;

LAYER1_NODE = 500;
BATCH_SIZE = 100;

LEARNING_RATE_BASE = 0.8;
LEARNING_RATE_DECAY = 0.99;
REGULARIZATION_RATE = 0.0001;
TRAINING_STEPS = 5000;
MOVING_ACERTAGE_DECAY = 0.99;

（3）定義一個接口來算神網輸出結果，之所以設置這個接口是因為為了適應滑動平均的方法：

def interface(input_tensor,avg_class,weights1,biases1,weights2,biases2):
    if avg_class == None:
        layer1 = tf.nn.relu(tf.matmul(input_tensor,weights1)+biases1);
        return tf.matmul(layer1,weights2)+biases2;
    else:
        layer1 = tf.nn.relu(tf.matmul(input_tensor,avg_class.average(weights1))+avg_class.\
                            average(biases1));
        return tf.matmul(layer1,avg_class.average(weights2))+avg_class.average(biases2);

（4）定義訓練主函數：

訓練主函數按照：輸入輸出placeholder，各層網絡節點權值與偏移量定義，設置滑動平滑，輸出兩種結果y和acroos_y，定義y的交叉熵和正則化，定義指數衰減學習，訓練。

def train(mnist):
    x = tf.placeholder(dtype=tf.float32,shape=[None,INPUT_NODE],name="x_input");
    y_ = tf.placeholder(dtype=tf.float32,shape=[None,OUTPUT_NODE],name="y_output");
    
    weights1 = tf.Variable(tf.truncated_normal(shape=[INPUT_NODE,LAYER1_NODE],stddev=0.1));
    biases1 = tf.Variable(tf.constant(0.1,dtype=tf.float32,shape=[LAYER1_NODE]));
    
    weights2 = tf.Variable(tf.truncated_normal(shape=[LAYER1_NODE,OUTPUT_NODE],stddev=0.1));
    biases2 = tf.Variable(tf.constant(0.1,dtype=tf.float32,shape=[OUTPUT_NODE]));
    
    y = interface(x,None,weights1,biases1,weights2,biases2);
    
    global_step = tf.Variable(0,trainable=False);
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_ACERTAGE_DECAY,global_step);
    variable_averages_op = variable_averages.apply(tf.trainable_variables());
    average_y = interface(x,variable_averages,weights1,biases1,weights2,biases2);
    
    # why????????????????????
    # 這里的交叉熵是以 y 為標准的
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.argmax(y_,1));
    cross_entropy_mean = tf.reduce_mean(cross_entropy);
    
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE);
    regularization = regularizer(weights1) + regularizer(weights2);
    
    loss = cross_entropy_mean + regularization;
    
    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,
                                               global_step,
                                               mnist.train.num_examples / BATCH_SIZE,
                                              LEARNING_RATE_DECAY);
    
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step = global_step);
    
    
    with tf.control_dependencies([train_step,variable_averages_op]):
        train_op = tf.no_op(name="train");
    
    correct_prediction = tf.equal(tf.argmax(average_y,1),tf.argmax(y_,1));
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32));
    
    with tf.Session() as sess:
        tf.global_variables_initializer().run();
        
        validate_feed = {x:mnist.validation.images, y_:mnist.validation.labels};
        test_feed = {x:mnist.test.images, y_:mnist.test.labels};
        
        for i in range(TRAINING_STEPS):
            if i % 1000 == 0:
                validate_acc = sess.run(accuracy,feed_dict = validate_feed);
                print("After %d training step(s), validation accuracy using average model is %g " \
                      % (i, validate_acc));
            xs,ys = mnist.train.next_batch(BATCH_SIZE)
            sess.run(train_op,feed_dict={x:xs,y_:ys});                
        
        test_acc = sess.run(accuracy,feed_dict = test_feed);
        print(("After %d training step(s), test accuracy using average model is %g" 
               %(TRAINING_STEPS, test_acc)));

（5）主函數代碼：

def main(argv = None):
    mnist = input_data.read_data_sets("C://Users/hasee/TensorFlow/實戰TensorFlow代碼/datasets/MNIST_data/",
                                  one_hot=True);
    train(mnist);

（6）運行程序：

if __name__ == "__main__":
    main();