#!/usr/bin/env python3 
# -*- coding: utf-8 -*- 
""" 
Created on Thu May 25 08:56:30 2017 
 
@author: marsjhao 
""" 
 
import tensorflow as tf 
from tensorflow.examples.tutorials.mnist import input_data 
 
INPUT_NODE = 784 # 輸入節(jié)點數(shù) 
OUTPUT_NODE = 10 # 輸出節(jié)點數(shù) 
LAYER1_NODE = 500 # 隱含層節(jié)點數(shù) 
BATCH_SIZE = 100 
LEARNING_RETE_BASE = 0.8 # 基學(xué)習(xí)率 
LEARNING_RETE_DECAY = 0.99 # 學(xué)習(xí)率的衰減率 
REGULARIZATION_RATE = 0.0001 # 正則化項的權(quán)重系數(shù) 
TRAINING_STEPS = 10000 # 迭代訓(xùn)練次數(shù) 
MOVING_AVERAGE_DECAY = 0.99 # 滑動平均的衰減系數(shù) 
 
# 傳入神經(jīng)網(wǎng)絡(luò)的權(quán)重和偏置，計算神經(jīng)網(wǎng)絡(luò)前向傳播的結(jié)果 
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2): 
  # 判斷是否傳入ExponentialMovingAverage類對象 
  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) 
 
# 神經(jīng)網(wǎng)絡(luò)模型的訓(xùn)練過程 
def train(mnist): 
  x = tf.placeholder(tf.float32, [None,INPUT_NODE], name='x-input') 
  y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input') 
 
  # 定義神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)的參數(shù) 
  weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], 
                        stddev=0.1)) 
  biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE])) 
  weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], 
                        stddev=0.1)) 
  biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE])) 
 
  # 計算非滑動平均模型下的參數(shù)的前向傳播的結(jié)果 
  y = inference(x, None, weights1, biases1, weights2, biases2) 
   
  global_step = tf.Variable(0, trainable=False) # 定義存儲當(dāng)前迭代訓(xùn)練輪數(shù)的變量 
 
  # 定義ExponentialMovingAverage類對象 
  variable_averages = tf.train.ExponentialMovingAverage( 
            MOVING_AVERAGE_DECAY, global_step) # 傳入當(dāng)前迭代輪數(shù)參數(shù) 
  # 定義對所有可訓(xùn)練變量trainable_variables進行更新滑動平均值的操作op 
  variables_averages_op = variable_averages.apply(tf.trainable_variables()) 
 
  # 計算滑動模型下的參數(shù)的前向傳播的結(jié)果 
  average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2) 
 
  # 定義交叉熵?fù)p失值 
  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) 
  # 定義L2正則化器并對weights1和weights2正則化 
  regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE) 
  regularization = regularizer(weights1) + regularizer(weights2) 
  loss = cross_entropy_mean + regularization # 總損失值 
 
  # 定義指數(shù)衰減學(xué)習(xí)率 
  learning_rate = tf.train.exponential_decay(LEARNING_RETE_BASE, global_step, 
          mnist.train.num_examples / BATCH_SIZE, LEARNING_RETE_DECAY) 
  # 定義梯度下降操作op，global_step參數(shù)可實現(xiàn)自加1運算 
  train_step = tf.train.GradientDescentOptimizer(learning_rate)\ 
             .minimize(loss, global_step=global_step) 
  # 組合兩個操作op 
  train_op = tf.group(train_step, variables_averages_op) 
  ''''' 
  # 與tf.group()等價的語句 
  with tf.control_dependencies([train_step, variables_averages_op]): 
    train_op = tf.no_op(name='train') 
  ''' 
  # 定義準(zhǔn)確率 
  # 在最終預(yù)測的時候，神經(jīng)網(wǎng)絡(luò)的輸出采用的是經(jīng)過滑動平均的前向傳播計算結(jié)果 
  correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1)) 
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 
 
  # 初始化回話sess并開始迭代訓(xùn)練 
  with tf.Session() as sess: 
    sess.run(tf.global_variables_initializer()) 
    # 驗證集待喂入數(shù)據(jù) 
    validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels} 
    # 測試集待喂入數(shù)據(jù) 
    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 steps, validation accuracy' 
           ' using average model is %f' % (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 steps, test accuracy' 
       ' using average model is %f' % (TRAINING_STEPS, test_acc)) 
 
# 主函數(shù) 
def main(argv=None): 
  mnist = input_data.read_data_sets("MNIST_data", one_hot=True) 
  train(mnist) 
 
# 當(dāng)前的python文件是shell文件執(zhí)行的入口文件，而非當(dāng)做import的python module。 
if __name__ == '__main__': # 在模塊內(nèi)部執(zhí)行 
  tf.app.run() # 調(diào)用main函數(shù)并傳入所需的參數(shù)list 

import tensorflow as tf 
 
INPUT_NODE = 784 
OUTPUT_NODE = 10 
LAYER1_NODE = 500 
 
def get_weight_variable(shape, regularizer): 
  weights = tf.get_variable("weights", shape, 
         initializer=tf.truncated_normal_initializer(stddev=0.1)) 
  if regularizer != None: 
    # 將權(quán)重參數(shù)的正則化項加入至損失集合 
    tf.add_to_collection('losses', regularizer(weights)) 
  return weights 
 
def inference(input_tensor, regularizer): 
  with tf.variable_scope('layer1'): 
    weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer) 
    biases = tf.get_variable("biases", [LAYER1_NODE], 
                 initializer=tf.constant_initializer(0.0)) 
    layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases) 
 
  with tf.variable_scope('layer2'): 
    weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer) 
    biases = tf.get_variable("biases", [OUTPUT_NODE], 
                 initializer=tf.constant_initializer(0.0)) 
    layer2 = tf.matmul(layer1, weights) + biases 
 
  return layer2 

import os 
import tensorflow as tf 
from tensorflow.examples.tutorials.mnist import input_data 
import mnist_inference 
 
BATCH_SIZE = 100 
LEARNING_RATE_BASE = 0.8 
LEARNING_RATE_DECAY = 0.99 
REGULARIZATION_RATE = 0.0001 
TRAINING_STEPS = 10000 
MOVING_AVERAGE_DECAY = 0.99 
 
MODEL_SAVE_PATH = "Model_Folder/" 
MODEL_NAME = "model.ckpt" 
 
def train(mnist): 
  # 定義輸入placeholder 
  x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], 
            name='x-input') 
  y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], 
            name='y-input') 
  # 定義正則化器及計算前向過程輸出 
  regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE) 
  y = mnist_inference.inference(x, regularizer) 
  # 定義當(dāng)前訓(xùn)練輪數(shù)及滑動平均模型 
  global_step = tf.Variable(0, trainable=False) 
  variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, 
                             global_step) 
  variables_averages_op = variable_averages.apply(tf.trainable_variables()) 
  # 定義損失函數(shù) 
  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) 
  loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses')) 
  # 定義指數(shù)衰減學(xué)習(xí)率 
  learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, 
          mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY) 
  # 定義訓(xùn)練操作，包括模型訓(xùn)練及滑動模型操作 
  train_step = tf.train.GradientDescentOptimizer(learning_rate)\ 
          .minimize(loss, global_step=global_step) 
  train_op = tf.group(train_step, variables_averages_op) 
  # 定義Saver類對象，保存模型，TensorFlow持久化類 
  saver = tf.train.Saver() 
 
  # 定義會話，啟動訓(xùn)練過程 
  with tf.Session() as sess: 
    tf.global_variables_initializer().run() 
 
    for i in range(TRAINING_STEPS): 
      xs, ys = mnist.train.next_batch(BATCH_SIZE) 
      _, loss_value, step = sess.run([train_op, loss, global_step], 
                      feed_dict={x: xs, y_: ys}) 
      if i % 1000 == 0: 
        print("After %d training step(s), loss on training batch is %g."\ 
            % (step, loss_value)) 
        # save方法的global_step參數(shù)可以讓每個被保存的模型的文件名末尾加上當(dāng)前訓(xùn)練輪數(shù) 
        saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), 
              global_step=global_step) 
 
def main(argv=None): 
  mnist = input_data.read_data_sets("MNIST_data", one_hot=True) 
  train(mnist) 
 
if __name__ == '__main__': 
  tf.app.run() 

import time 
import tensorflow as tf 
from tensorflow.examples.tutorials.mnist import input_data 
import mnist_inference 
import mnist_train 
 
EVAL_INTERVAL_SECS = 10 
 
def evaluate(mnist): 
  with tf.Graph().as_default() as g: 
    # 定義輸入placeholder 
    x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], 
              name='x-input') 
    y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], 
              name='y-input') 
    # 定義feed字典 
    validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels} 
    # 測試時不加參數(shù)正則化損失 
    y = mnist_inference.inference(x, None) 
    # 計算正確率 
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1)) 
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 
    # 加載滑動平均模型下的參數(shù)值 
    variable_averages = tf.train.ExponentialMovingAverage( 
                   mnist_train.MOVING_AVERAGE_DECAY) 
    saver = tf.train.Saver(variable_averages.variables_to_restore()) 
 
    # 每隔EVAL_INTERVAL_SECS秒啟動一次會話 
    while True: 
      with tf.Session() as sess: 
        ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH) 
        if ckpt and ckpt.model_checkpoint_path: 
          saver.restore(sess, ckpt.model_checkpoint_path) 
          # 取checkpoint文件中的當(dāng)前迭代輪數(shù)global_step 
          global_step = ckpt.model_checkpoint_path\ 
                   .split('/')[-1].split('-')[-1] 
          accuracy_score = sess.run(accuracy, feed_dict=validate_feed) 
          print("After %s training step(s), validation accuracy = %g"\ 
             % (global_step, accuracy_score)) 
 
        else: 
          print('No checkpoint file found') 
          return 
      time.sleep(EVAL_INTERVAL_SECS) 
 
def main(argv=None): 
  mnist = input_data.read_data_sets("MNIST_data", one_hot=True) 
  evaluate(mnist) 
 
if __name__ == '__main__': 
  tf.app.run()