Google InceptionNet-V3網路結構圖：

Inception V3網路結構圖：

Inception V3中設計CNN的思想和Trick：

（1）Factorization into small convolutions很有效，可以降低引數量，減輕
過擬合，增加網路非線性的表達能力。

（2）卷積網路從輸入到輸出，應該讓圖片尺寸逐漸減小，輸出通道數逐漸增加，
即讓空間結構化，將空間資訊轉化為高階抽象的特徵資訊。

（3）Inception Module用多個分支提取不同抽象程度的高階特徵的思路很有效，
可以豐富網路的表達能力。

# coding:UTF-8
import tensorflow as tf
from datetime import datetime
import math
import time

slim = tf.contrib.slim
trunc_normal = lambda stddev: tf.truncated_normal_initializer(0.0
 
, stddev) #產生截斷的正態分佈


########定義函式生成網路中經常用到的函式的預設引數########
# 預設引數：卷積的啟用函式、權重初始化方式、標準化器等
def inception_v3_arg_scope(weight_decay=0.00004,  # 設定L2正則的weight_decay
                           stddev=0.1, # 標準差預設值0.1
                           batch_norm_var_collection='moving_vars'):

  batch_norm_params = {  # 定義batch normalization（標準化）的引數字典
      'decay': 0.9997,  # 定義引數衰減係數
      'epsilon': 0.001,  
      'updates_collections': tf.GraphKeys.UPDATE_OPS,
      'variables_collections': {
          'beta': None,
          'gamma': None,
          'moving_mean': [batch_norm_var_collection],
          'moving_variance': [batch_norm_var_collection],
      }
  }

  with slim.arg_scope([slim.conv2d, slim.fully_connected], # 給函式的引數自動賦予某些預設值
                      weights_regularizer=slim.l2_regularizer(weight_decay)): # 對[slim.conv2d, slim.fully_connected]自動賦值
  # 使用slim.arg_scope後就不需要每次都重複設定引數了，只需要在有修改時設定
    with slim.arg_scope( # 巢狀一個slim.arg_scope對卷積層生成函式slim.conv2d的幾個引數賦予預設值
        [slim.conv2d],
        weights_initializer=trunc_normal(stddev), # 權重初始化器
        activation_fn=tf.nn.relu, # 啟用函式
        normalizer_fn=slim.batch_norm, # 標準化器
        normalizer_params=batch_norm_params) as sc: # 標準化器的引數設定為前面定義的batch_norm_params
      return sc # 最後返回定義好的scope


########定義函式可以生成Inception V3網路的卷積部分########
def inception_v3_base(inputs, scope=None):
  '''
  Args:
  inputs：輸入的tensor
  scope：包含了函式預設引數的環境
  '''
  end_points = {} # 定義一個字典表儲存某些關鍵節點供之後使用

  with tf.variable_scope(scope, 'InceptionV3', [inputs]):
    with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d], # 對三個引數設定預設值
                        stride=1, padding='VALID'):
      # 正式定義Inception V3的網路結構。首先是前面的非Inception Module的卷積層
      # 299 x 299 x 3
      # 第一個引數為輸入的tensor，第二個是輸出的通道數，卷積核尺寸，步長stride，padding模式
      net = slim.conv2d(inputs, 32, [3, 3], stride=2, scope='Conv2d_1a_3x3') # 直接使用slim.conv2d建立卷積層
      # 149 x 149 x 32
      '''
      因為使用了slim以及slim.arg_scope，我們一行程式碼就可以定義好一個卷積層
      相比AlexNet使用好幾行程式碼定義一個卷積層，或是VGGNet中專門寫一個函式定義卷積層，都更加方便
      '''
      net = slim.conv2d(net, 32, [3, 3], scope='Conv2d_2a_3x3')
      # 147 x 147 x 32
      net = slim.conv2d(net, 64, [3, 3], padding='SAME', scope='Conv2d_2b_3x3')
      # 147 x 147 x 64
      net = slim.max_pool2d(net, [3, 3], stride=2, scope='MaxPool_3a_3x3')
      # 73 x 73 x 64
      net = slim.conv2d(net, 80, [1, 1], scope='Conv2d_3b_1x1')
      # 73 x 73 x 80.
      net = slim.conv2d(net, 192, [3, 3], scope='Conv2d_4a_3x3')
      # 71 x 71 x 192.
      net = slim.max_pool2d(net, [3, 3], stride=2, scope='MaxPool_5a_3x3')
      # 35 x 35 x 192.

      # 上面部分程式碼一共有5個卷積層，2個池化層，實現了對圖片資料的尺寸壓縮，並對圖片特徵進行了抽象

    '''
    三個連續的Inception模組組，三個Inception模組組中各自分別有多個Inception Module，這部分是Inception Module V3
    的精華所在。每個Inception模組組內部的幾個Inception Mdoule結構非常相似，但是存在一些細節的不同
    '''
    # Inception blocks
    with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d], # 設定所有模組組的預設引數
                        stride=1, padding='SAME'): # 將所有卷積層、最大池化、平均池化層步長都設定為1
      # mixed: 35 x 35 x 256.
      # 第一個模組組包含了三個結構類似的Inception Module
      with tf.variable_scope('Mixed_5b'): # 第一個Inception Module名稱。Inception Module有四個分支
        with tf.variable_scope('Branch_0'): # 第一個分支64通道的1*1卷積
          branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'): # 第二個分支48通道1*1卷積，連結一個64通道的5*5卷積
          branch_1 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 64, [5, 5], scope='Conv2d_0b_5x5')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
          branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
        with tf.variable_scope('Branch_3'): # 第四個分支為3*3的平均池化，連線32通道的1*1卷積
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(branch_3, 32, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3) # 將四個分支的輸出合併在一起（第三個維度合併，即輸出通道上合併）

      '''
      因為這裡所有層步長均為1，並且padding模式為SAME，所以圖片尺寸不會縮小，但是通道數增加了。四個分支通道數之和
      64+64+96+32=256，最終輸出的tensor的圖片尺寸為35*35*256。
      第一個模組組所有Inception Module輸出圖片尺寸都是35*35，但是後兩個輸出通道數會發生變化。
      '''

      # mixed_1: 35 x 35 x 288.
      with tf.variable_scope('Mixed_5c'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0b_1x1')
          branch_1 = slim.conv2d(branch_1, 64, [5, 5], scope='Conv_1_0c_5x5')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
          branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)

      # mixed_2: 35 x 35 x 288.
      with tf.variable_scope('Mixed_5d'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 64, [5, 5], scope='Conv2d_0b_5x5')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
          branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)

      # 第二個Inception模組組。第二個到第五個Inception Module結構相似。
      # mixed_3: 17 x 17 x 768.
      with tf.variable_scope('Mixed_6a'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 384, [3, 3], stride=2,
                                 padding='VALID', scope='Conv2d_1a_1x1') # 圖片會被壓縮
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 96, [3, 3], scope='Conv2d_0b_3x3')
          branch_1 = slim.conv2d(branch_1, 96, [3, 3], stride=2,
                                 padding='VALID', scope='Conv2d_1a_1x1') # 圖片被壓縮
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID',
                                     scope='MaxPool_1a_3x3')
        net = tf.concat([branch_0, branch_1, branch_2], 3) # 輸出尺寸定格在17 x 17 x 768

      # mixed4: 17 x 17 x 768.
      with tf.variable_scope('Mixed_6b'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 128, [1, 7], scope='Conv2d_0b_1x7') # 串聯1*7卷積和7*1卷積合成7*7卷積，減少了引數，減輕了過擬合
          branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
        with tf.variable_scope('Branch_2'): 
          branch_2 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1') # 反覆將7*7卷積拆分
          branch_2 = slim.conv2d(branch_2, 128, [7, 1], scope='Conv2d_0b_7x1') 
          branch_2 = slim.conv2d(branch_2, 128, [1, 7], scope='Conv2d_0c_1x7')
          branch_2 = slim.conv2d(branch_2, 128, [7, 1], scope='Conv2d_0d_7x1')
          branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0e_1x7')
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)

      # mixed_5: 17 x 17 x 768.
      with tf.variable_scope('Mixed_6c'):
        with tf.variable_scope('Branch_0'):
          '''
          我們的網路每經過一個inception module，即使輸出尺寸不變，但是特徵都相當於被重新精煉了一遍，
          其中豐富的卷積和非線性化對提升網路效能幫助很大。
          '''
          branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 160, [1, 7], scope='Conv2d_0b_1x7')
          branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, 160, [7, 1], scope='Conv2d_0b_7x1')
          branch_2 = slim.conv2d(branch_2, 160, [1, 7], scope='Conv2d_0c_1x7')
          branch_2 = slim.conv2d(branch_2, 160, [7, 1], scope='Conv2d_0d_7x1')
          branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0e_1x7')
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
      # mixed_6: 17 x 17 x 768.
      with tf.variable_scope('Mixed_6d'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 160, [1, 7], scope='Conv2d_0b_1x7')
          branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, 160, [7, 1], scope='Conv2d_0b_7x1')
          branch_2 = slim.conv2d(branch_2, 160, [1, 7], scope='Conv2d_0c_1x7')
          branch_2 = slim.conv2d(branch_2, 160, [7, 1], scope='Conv2d_0d_7x1')
          branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0e_1x7')
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)

      # mixed_7: 17 x 17 x 768.
      with tf.variable_scope('Mixed_6e'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 192, [1, 7], scope='Conv2d_0b_1x7')
          branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, 192, [7, 1], scope='Conv2d_0b_7x1')
          branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0c_1x7')
          branch_2 = slim.conv2d(branch_2, 192, [7, 1], scope='Conv2d_0d_7x1')
          branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0e_1x7')
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
      end_points['Mixed_6e'] = net # 將Mixed_6e儲存於end_points中，作為Auxiliary Classifier輔助模型的分類

      # 第三個inception模組組包含了三個inception module
      # mixed_8: 8 x 8 x 1280.
      with tf.variable_scope('Mixed_7a'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
          branch_0 = slim.conv2d(branch_0, 320, [3, 3], stride=2,
                                 padding='VALID', scope='Conv2d_1a_3x3') # 壓縮圖片
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 192, [1, 7], scope='Conv2d_0b_1x7')
          branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
          branch_1 = slim.conv2d(branch_1, 192, [3, 3], stride=2,
                                 padding='VALID', scope='Conv2d_1a_3x3')
        with tf.variable_scope('Branch_2'): # 池化層不會對輸出通道數產生改變
          branch_2 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID',
                                     scope='MaxPool_1a_3x3')
        net = tf.concat([branch_0, branch_1, branch_2], 3) # 輸出圖片尺寸被縮小，通道數增加，tensor的總size在持續下降中
      # mixed_9: 8 x 8 x 2048.
      with tf.variable_scope('Mixed_7b'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 320, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = tf.concat([
              slim.conv2d(branch_1, 384, [1, 3], scope='Conv2d_0b_1x3'),
              slim.conv2d(branch_1, 384, [3, 1], scope='Conv2d_0b_3x1')], 3)
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, 448, [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(
              branch_2, 384, [3, 3], scope='Conv2d_0b_3x3')
          branch_2 = tf.concat([
              slim.conv2d(branch_2, 384, [1, 3], scope='Conv2d_0c_1x3'),
              slim.conv2d(branch_2, 384, [3, 1], scope='Conv2d_0d_3x1')], 3)
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(
              branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3) # 輸出通道數增加到2048

      # mixed_10: 8 x 8 x 2048.
      with tf.variable_scope('Mixed_7c'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 320, [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = tf.concat([
              slim.conv2d(branch_1, 384, [1, 3], scope='Conv2d_0b_1x3'),
              slim.conv2d(branch_1, 384, [3, 1], scope='Conv2d_0c_3x1')], 3)
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, 448, [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(
              branch_2, 384, [3, 3], scope='Conv2d_0b_3x3')
          branch_2 = tf.concat([
              slim.conv2d(branch_2, 384, [1, 3], scope='Conv2d_0c_1x3'),
              slim.conv2d(branch_2, 384, [3, 1], scope='Conv2d_0d_3x1')], 3)
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(
              branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
      return net, end_points
      #Inception V3網路的核心部分，即卷積層部分就完成了
      '''
      設計inception net的重要原則是圖片尺寸不斷縮小，inception模組組的目的都是將空間結構簡化，同時將空間資訊轉化為
      高階抽象的特徵資訊，即將空間維度轉為通道的維度。降低了計算量。Inception Module是通過組合比較簡單的特徵
      抽象（分支1）、比較比較複雜的特徵抽象（分支2和分支3）和一個簡化結構的池化層（分支4），一共四種不同程度的
      特徵抽象和變換來有選擇地保留不同層次的高階特徵，這樣最大程度地豐富網路的表達能力。
      '''


########全域性平均池化、Softmax和Auxiliary Logits########
def inception_v3(inputs,
                 num_classes=1000, # 最後需要分類的數量（比賽資料集的種類數）
                 is_training=True, # 標誌是否為訓練過程，只有在訓練時Batch normalization和Dropout才會啟用
                 dropout_keep_prob=0.8, # 節點保留比率
                 prediction_fn=slim.softmax, # 最後用來分類的函式
                 spatial_squeeze=True, # 引數標誌是否對輸出進行squeeze操作（去除維度數為1的維度，比如5*3*1轉為5*3）
                 reuse=None, # 是否對網路和Variable進行重複使用
                 scope='InceptionV3'): # 包含函式預設引數的環境

  with tf.variable_scope(scope, 'InceptionV3', [inputs, num_classes], # 定義引數預設值
                         reuse=reuse) as scope:
    with slim.arg_scope([slim.batch_norm, slim.dropout], # 定義標誌預設值
                        is_training=is_training):
      # 拿到最後一層的輸出net和重要節點的字典表end_points
      net, end_points = inception_v3_base(inputs, scope=scope) # 用定義好的函式構築整個網路的卷積部分

      # Auxiliary Head logits作為輔助分類的節點，對分類結果預測有很大幫助
      with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
                          stride=1, padding='SAME'): # 將卷積、最大池化、平均池化步長設定為1
        aux_logits = end_points['Mixed_6e'] # 通過end_points取到Mixed_6e
        with tf.variable_scope('AuxLogits'):
          aux_logits = slim.avg_pool2d(
              aux_logits, [5, 5], stride=3, padding='VALID', # 在Mixed_6e之後接平均池化。壓縮影象尺寸
              scope='AvgPool_1a_5x5')
          aux_logits = slim.conv2d(aux_logits, 128, [1, 1], # 卷積。壓縮影象尺寸。
                                   scope='Conv2d_1b_1x1')

          # Shape of feature map before the final layer.
          aux_logits = slim.conv2d(
              aux_logits, 768, [5,5],
              weights_initializer=trunc_normal(0.01), # 權重初始化方式重設為標準差為0.01的正態分佈
              padding='VALID', scope='Conv2d_2a_5x5')
          aux_logits = slim.conv2d(
              aux_logits, num_classes, [1, 1], activation_fn=None,
              normalizer_fn=None, weights_initializer=trunc_normal(0.001), # 輸出變為1*1*1000
              scope='Conv2d_2b_1x1')
          if spatial_squeeze: # tf.squeeze消除tensor中前兩個為1的維度。
            aux_logits = tf.squeeze(aux_logits, [1, 2], name='SpatialSqueeze')
          end_points['AuxLogits'] = aux_logits # 最後將輔助分類節點的輸出aux_logits儲存到字典表end_points中

      # 處理正常的分類預測邏輯
      # Final pooling and prediction
      with tf.variable_scope('Logits'):
        net = slim.avg_pool2d(net, [8, 8], padding='VALID',
                              scope='AvgPool_1a_8x8')
        # 1 x 1 x 2048
        net = slim.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
        end_points['PreLogits'] = net
        # 2048
        logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, # 輸出通道數1000
                             normalizer_fn=None, scope='Conv2d_1c_1x1') # 啟用函式和規範化函式設為空
        if spatial_squeeze: # tf.squeeze去除輸出tensor中維度為1的節點
          logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
        # 1000
      end_points['Logits'] = logits
      end_points['Predictions'] = prediction_fn(logits, scope='Predictions') # Softmax對結果進行分類預測
  return logits, end_points # 最後返回logits和包含輔助節點的end_points



########評估AlexNet每輪計算時間########
def time_tensorflow_run(session, target, info_string):

  # Args:
  # session:the TensorFlow session to run the computation under.
  # target:需要評測的運算運算元。
  # info_string:測試名稱。

  num_steps_burn_in = 10 # 先定義預熱輪數（頭幾輪跌代有視訊記憶體載入、cache命中等問題因此可以跳過，只考量10輪迭代之後的計算時間）
  total_duration = 0.0 # 記錄總時間
  total_duration_squared = 0.0 # 總時間平方和  -----用來後面計算方差
  for i in xrange(FLAGS.num_batches + num_steps_burn_in): # 迭代輪數
    start_time = time.time() # 記錄時間
    _ = session.run(target) # 每次迭代通過session.run(target)
    duration = time.time() - start_time # 
    if i >= num_steps_burn_in: 
      if not i % 10:
        print ('%s: step %d, duration = %.3f' %
               (datetime.now(), i - num_steps_burn_in, duration))
      total_duration += duration  # 累加便於後面計算每輪耗時的均值和標準差
      total_duration_squared += duration * duration
  mn = total_duration / FLAGS.num_batches # 每輪迭代的平均耗時
  vr = total_duration_squared / FLAGS.num_batches - mn * mn 
  sd = math.sqrt(vr) # 標準差
  print ('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %
         (datetime.now(), info_string, FLAGS.num_batches, mn, sd))

batch_size = 32 # 因為網路結構較大依然設定為32，以免GPU視訊記憶體不夠
height, width = 299, 299 # 圖片尺寸
inputs = tf.random_uniform((batch_size, height, width, 3)) # 隨機生成圖片資料作為input
with slim.arg_scope(inception_v3_arg_scope()): # scope中包含了batch normalization預設引數，啟用函式和引數初始化方式的預設值
  logits, end_points = inception_v3(inputs, is_training=False) # inception_v3中傳入inputs獲取裡logits和end_points

init = tf.global_variables_initializer() # 初始化全部模型引數
sess = tf.Session() # 建立session
sess.run(init)  
num_batches=100 # 測試的batch數量
time_tensorflow_run(sess, logits, "Forward")
'''
雖然輸入圖片比VGGNet的224*224大了78%，但是forward速度卻比VGGNet更快。
這主要歸功於其較小的引數量，inception V3引數量比inception V1的700萬
多了很多，不過仍然不到AlexNet的6000萬引數量的一半。相比VGGNet的1.4
億引數量就更少了。整個網路的浮點計算量為50億次，比inception V1的15億
次大了不少，但是相比VGGNet來說不算大。因此較少的計算量讓inception V3
網路變得非常實用，可以輕鬆地移植到普通伺服器上提供快速響應服務，甚至
移植到手機上進行實時的影象識別。
'''