本文直接從Inception v3的程式碼實現入手，分析其中值得借鑑的思想

首先要知道一個slim的元件，可以給引數自動賦值，可以省去很多操作

def inception_arg_scope(weight_decay=0.00004,
                        use_batch_norm=True,
                        batch_norm_decay=0.9997,
                        batch_norm_epsilon=0.001):
  """Defines the default arg scope for inception models.
  Args:
    weight_decay: 設定L2正則
    use_batch_norm: 設定是否使用batch normalization
    batch_norm_decay: BN的衰減係數
    batch_norm_epsilon: 為了避免除數為0加的一個小型浮點數

  Returns:
    An `arg_scope` to use for the inception models.
  """
  batch_norm_params = {
      'decay': batch_norm_decay,
      'epsilon': batch_norm_epsilon,
      'updates_collections': tf.GraphKeys.UPDATE_OPS,
  }
 

  if use_batch_norm:
    normalizer_fn = slim.batch_norm
    normalizer_params = batch_norm_params
  else:
    normalizer_fn = None
    normalizer_params = {}
  # 下面這句會對conv2d和全連線層這兩個函式的weights_regularizer引數自動賦值為
  with slim.arg_scope([slim.conv2d, slim.fully_connected],
                      weights_regularizer=slim.l2_regularizer(weight_decay)):
 

    #接下來再巢狀一個slim.arg_scope,對conv2d的權重、啟用函式、正則化函式及其引數自動賦值後將其返回 
    with slim.arg_scope(
        [slim.conv2d],
        weights_initializer=slim.variance_scaling_initializer(),
        activation_fn=tf.nn.relu,
        normalizer_fn=normalizer_fn,
        normalizer_params=normalizer_params) as sc:
      return sc
 

trunc_normal = lambda stddev: tf.truncated_normal_initializer(0.0, stddev)

接下來定義inception v3 base,它可以生成inception v3的卷積部分

def inception_v3_base(inputs,
                      final_endpoint='Mixed_7c',
                      min_depth=16,
                      depth_multiplier=1.0,
                      scope=None):
  """Inception model from http://arxiv.org/abs/1512.00567.

  總體名稱對應結構如下
  Old name          | New name
  =======================================
  conv0             | Conv2d_1a_3x3
  conv1             | Conv2d_2a_3x3
  conv2             | Conv2d_2b_3x3
  pool1             | MaxPool_3a_3x3
  conv3             | Conv2d_3b_1x1
  conv4             | Conv2d_4a_3x3
  pool2             | MaxPool_5a_3x3
  mixed_35x35x256a  | Mixed_5b
  mixed_35x35x288a  | Mixed_5c
  mixed_35x35x288b  | Mixed_5d
  mixed_17x17x768a  | Mixed_6a
  mixed_17x17x768b  | Mixed_6b
  mixed_17x17x768c  | Mixed_6c
  mixed_17x17x768d  | Mixed_6d
  mixed_17x17x768e  | Mixed_6e
  mixed_8x8x1280a   | Mixed_7a
  mixed_8x8x2048a   | Mixed_7b
  mixed_8x8x2048b   | Mixed_7c

  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    final_endpoint: specifies the endpoint to construct the network up to. It
      can be one of ['Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3',
      'MaxPool_3a_3x3', 'Conv2d_3b_1x1', 'Conv2d_4a_3x3', 'MaxPool_5a_3x3',
      'Mixed_5b', 'Mixed_5c', 'Mixed_5d', 'Mixed_6a', 'Mixed_6b', 'Mixed_6c',
      'Mixed_6d', 'Mixed_6e', 'Mixed_7a', 'Mixed_7b', 'Mixed_7c'].
    min_depth: Minimum depth value (number of channels) for all convolution ops.
      Enforced when depth_multiplier < 1, and not an active constraint when
      depth_multiplier >= 1.
    depth_multiplier: Float multiplier for the depth (number of channels)
      for all convolution ops. The value must be greater than zero. Typical
      usage will be to set this value in (0, 1) to reduce the number of
      parameters or computation cost of the model.
    scope: Optional variable_scope.

  Returns:
    tensor_out: output tensor corresponding to the final_endpoint.
    end_points: a set of activations for external use, for example summaries or
                losses.

  Raises:
    ValueError: if final_endpoint is not set to one of the predefined values,
                or depth_multiplier <= 0
  """
  # end_points will collect relevant activations for external use, for example
  # summaries or losses.
  end_points = {}

  if depth_multiplier <= 0:
    raise ValueError('depth_multiplier is not greater than zero.')

  #用來計算深度的函式，與乘子結合
  depth = lambda d: max(int(d * depth_multiplier), min_depth)
  
  with tf.variable_scope(scope, 'InceptionV3', [inputs]):
    with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
                        stride=1, padding='VALID'):
      # 299 x 299 x 3
      end_point = 'Conv2d_1a_3x3'
      net = slim.conv2d(inputs, depth(32), [3, 3], stride=2, scope=end_point)
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 149 x 149 x 32
      end_point = 'Conv2d_2a_3x3'
      net = slim.conv2d(net, depth(32), [3, 3], scope=end_point)
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 147 x 147 x 32
      end_point = 'Conv2d_2b_3x3'
      net = slim.conv2d(net, depth(64), [3, 3], padding='SAME', scope=end_point)
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 147 x 147 x 64
      end_point = 'MaxPool_3a_3x3'
      net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point)
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 73 x 73 x 64
      end_point = 'Conv2d_3b_1x1'
      net = slim.conv2d(net, depth(80), [1, 1], scope=end_point)
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 73 x 73 x 80.
      end_point = 'Conv2d_4a_3x3'
      net = slim.conv2d(net, depth(192), [3, 3], scope=end_point)
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 71 x 71 x 192.
      end_point = 'MaxPool_5a_3x3'
      net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point)
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 35 x 35 x 192.
    # 接下來將是三個連續的Inception模組組，模組組中各自分別有多個incpetion模組,
    # 這部分結構是Inception v3的精華 
    # Inception blocks 第一個模組組的名稱為Mixed_5b
    # 先用slim設定所有inception Module的預設引數，所有卷積、最大池化、平均池化層的步長為1，padding為'SAME' 

    with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
                        stride=1, padding='SAME'):
      # mixed: 35 x 35 x 256.
      end_point = 'Mixed_5b'
      with tf.variable_scope(end_point):

        #第一組模組有4個分支
         #第一個分支為64通道的1x1卷積
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
         #第二個分支為48通道的1x1卷積接一個64通道的5x5卷積
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, depth(48), [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, depth(64), [5, 5],
                                 scope='Conv2d_0b_5x5')
         #第三個分支為64通道的1x1卷積接一個96通道的3x3的卷積
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, depth(96), [3, 3],
                                 scope='Conv2d_0b_3x3')
          branch_2 = slim.conv2d(branch_2, depth(96), [3, 3],
                                 scope='Conv2d_0c_3x3')
        #第四個分支為3x3平均池化接一個32通道的1x1卷積
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(branch_3, depth(32), [1, 1],
                                 scope='Conv2d_0b_1x1')
        #將4個分支的輸出合併在一起，在輸出通道維度上進行合併 
        net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      #由於設定了步長為1，padding為'same',所以尺寸不會減少，只是通道數量增加了
      # 按照相同的方法設定第二個Inception Module，輸出通道數為288
      # mixed_1: 35 x 35 x 288.
      end_point = 'Mixed_5c'
      with tf.variable_scope(end_point):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, depth(48), [1, 1], scope='Conv2d_0b_1x1')
          branch_1 = slim.conv2d(branch_1, depth(64), [5, 5],
                                 scope='Conv_1_0c_5x5')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, depth(64), [1, 1],
                                 scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, depth(96), [3, 3],
                                 scope='Conv2d_0b_3x3')
          branch_2 = slim.conv2d(branch_2, depth(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, depth(64), [1, 1],
                                 scope='Conv2d_0b_1x1')
        net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points

      # mixed_2: 35 x 35 x 288.
      end_point = 'Mixed_5d'
      with tf.variable_scope(end_point):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, depth(48), [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, depth(64), [5, 5],
                                 scope='Conv2d_0b_5x5')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, depth(96), [3, 3],
                                 scope='Conv2d_0b_3x3')
          branch_2 = slim.conv2d(branch_2, depth(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, depth(64), [1, 1],
                                 scope='Conv2d_0b_1x1')
        net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 第一個模組組的3個Module到這裡結束

      # 第二個模組組包含了5個Module,第2-5個結構相似
     # mixed_3: 17 x 17 x 768.
      end_point = 'Mixed_6a'
      with tf.variable_scope(end_point):
     # 包含3分支 
     # 第一分支stride=2,尺寸壓縮到17x17
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(384), [3, 3], stride=2,
                                 padding='VALID', scope='Conv2d_1a_1x1')
     #第二分支有三層，第一層是一個64通道的1x1卷積，第二層是96通道的3x3卷積，第三層是96通道3x3卷積，尺寸壓縮 
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, depth(96), [3, 3],
                                 scope='Conv2d_0b_3x3')
          branch_1 = slim.conv2d(branch_1, depth(96), [3, 3], stride=2,
                                 padding='VALID', scope='Conv2d_1a_1x1')
     #第三個分支3x3最大池化層，尺寸同樣壓縮 
        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(axis=3, values=[branch_0, branch_1, branch_2])
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
       # 所以最後的尺寸是17x17x(384+96+256)=17x17x768
       # 隨後的Module尺寸全部固定到17x17x768      
       # mixed4: 17 x 17 x 768.      
       # 第二個模組組的第二個Module有4個分支      
      end_point = 'Mixed_6b'      
      with tf.variable_scope(end_point):        
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
       # 第二個分支有3層卷積
       # 第二層是一個128通道的1x7卷積，第三層是一個192通道的7x1卷積
       # 這裡用到了Factorization into small convolutions的思想，串聯一個1x7和7x1的卷積相當於7x卷積
       # 但是引數量大大減少了 ，只有2/7,同時多了一個啟用函式增強了非線性特徵變換，減輕了過擬合
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, depth(128), [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, depth(128), [1, 7], 
                                scope='Conv2d_0b_1x7')
          branch_1 = slim.conv2d(branch_1, depth(192), [7, 1],
                                 scope='Conv2d_0c_7x1')
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, depth(128), [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(branch_2, depth(128), [7, 1],
                                 scope='Conv2d_0b_7x1')
          branch_2 = slim.conv2d(branch_2, depth(128), [1, 7],
                                 scope='Conv2d_0c_1x7')
          branch_2 = slim.conv2d(branch_2, depth(128), [7, 1], 
                                scope='Conv2d_0d_7x1')
          branch_2 = slim.conv2d(branch_2, depth(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, depth(192), [1, 1],
                                 scope='Conv2d_0b_1x1')
        net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
      # 最後該module的尺寸是17x17x(192+192+192+192)=17x17x768
      # mixed_5: 17 x 17 x 768.
      end_point = 'Mixed_6c'
      with tf.variable_scope(end_point):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
 #第二個模組組的第三個Module與第二個Module的不同就是第二個分支和第三個分支的前幾個卷積層
 # 的輸出通道數不同，從128變成了160，最終通道數不變
 # 這樣做特徵相當於被重新計算了一遍，對網路的豐富性提升很大

      # 第一個Module包含3個分支 
      with tf.variable_scope(end_point):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
          branch_0 = slim.conv2d(branch_0, depth(320), [3, 3], stride=2,
                                 padding='VALID', scope='Conv2d_1a_3x3')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, depth(192), [1, 7],
                                 scope='Conv2d_0b_1x7')
          branch_1 = slim.conv2d(branch_1, depth(192), [7, 1],
                                 scope='Conv2d_0c_7x1')
          branch_1 = slim.conv2d(branch_1, depth(192), [3, 3], stride=2,
                                 padding='VALID', scope='Conv2d_1a_3x3')

        #這裡的輸出是8x8x768 
        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(axis=3, values=[branch_0, branch_1, branch_2])
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points

      # 輸出尺寸 8x8x(320+192+768)=8x8x1280

  
      # mixed_9: 8 x 8 x 2048.
      end_point = 'Mixed_7b'
      with tf.variable_scope(end_point):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(320), [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, depth(384), [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = tf.concat(axis=3, values=[
              slim.conv2d(branch_1, depth(384), [1, 3], scope='Conv2d_0b_1x3'),
              slim.conv2d(branch_1, depth(384), [3, 1], scope='Conv2d_0b_3x1')])

        # 第三個分支比較複雜

        # 顯示448通道的1x1卷積接一個384通道的3x3卷積，然後在分支內拆成兩個分支，384通道1x3和3x1

        # 最後合併的到8x8x768  
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, depth(448), [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(
              branch_2, depth(384), [3, 3], scope='Conv2d_0b_3x3')
          branch_2 = tf.concat(axis=3, values=[
              slim.conv2d(branch_2, depth(384), [1, 3], scope='Conv2d_0c_1x3'),
              slim.conv2d(branch_2, depth(384), [3, 1], scope='Conv2d_0d_3x1')])
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(
              branch_3, depth(192), [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points

      # mixed_10: 8 x 8 x 2048.
      end_point = 'Mixed_7c'
      with tf.variable_scope(end_point):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, depth(320), [1, 1], scope='Conv2d_0a_1x1')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, depth(384), [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = tf.concat(axis=3, values=[
              slim.conv2d(branch_1, depth(384), [1, 3], scope='Conv2d_0b_1x3'),
              slim.conv2d(branch_1, depth(384), [3, 1], scope='Conv2d_0c_3x1')])
        with tf.variable_scope('Branch_2'):
          branch_2 = slim.conv2d(net, depth(448), [1, 1], scope='Conv2d_0a_1x1')
          branch_2 = slim.conv2d(
              branch_2, depth(384), [3, 3], scope='Conv2d_0b_3x3')
          branch_2 = tf.concat(axis=3, values=[
              slim.conv2d(branch_2, depth(384), [1, 3], scope='Conv2d_0c_1x3'),
              slim.conv2d(branch_2, depth(384), [3, 1], scope='Conv2d_0d_3x1')])
        with tf.variable_scope('Branch_3'):
          branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
          branch_3 = slim.conv2d(
              branch_3, depth(192), [1, 1], scope='Conv2d_0b_1x1')
        net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
      end_points[end_point] = net
      if end_point == final_endpoint: return net, end_points
    raise ValueError('Unknown final endpoint %s' % final_endpoint)


	到這裡Inception的核心部分完成，包含了3個inception模組組，每個模組組內包含了多個結構類似的Inceptionmodule。

	圖片的尺寸從299x299經過5個步長為2的卷結或池化後縮減到8x8,通道數從3一直到2048。

	每個Inception模組組的目的都是獎空間結構簡化，同時把空間資訊轉化為高階抽象的特徵資訊。

	這一過程使得每層輸出tensor的size持續下降，降低了計算量。

	可以發現InceptionModule的規律，一般情況下有4個分支，第1個分支一般是1x1卷積，第2個分支一般是1x1卷積後再接分解的1xn和nx1卷積

	第3個分支和第2個分支類似,但是一般更深一些,第4個分支一般具有最大池化或者平均池化

	因此，Inception Module是通過組合比較簡單的特徵抽象(分支1)，比較複雜的特徵抽象(2,3),和一個簡化的池化層(分支4)，一共4種不同程度的

	特徵抽象和變化來有選擇的保留不同層次的高階特徵，最大程度豐富網路的表達能力

def inception_v3(inputs,
                 num_classes=1000,
                 is_training=True,
                 dropout_keep_prob=0.8,
                 min_depth=16,
                 depth_multiplier=1.0,
                 prediction_fn=slim.softmax,
                 spatial_squeeze=True,
                 reuse=None,
                 scope='InceptionV3'):
  """Inception model from http://arxiv.org/abs/1512.00567.

  "Rethinking the Inception Architecture for Computer Vision"

  Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
  Zbigniew Wojna.

  With the default arguments this method constructs the exact model defined in
  the paper. However, one can experiment with variations of the inception_v3
  network by changing arguments dropout_keep_prob, min_depth and
  depth_multiplier.

  The default image size used to train this network is 299x299.

  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    num_classes: number of predicted classes.
    is_training: whether is training or not.
    dropout_keep_prob: the percentage of activation values that are retained.
    min_depth: Minimum depth value (number of channels) for all convolution ops.
      Enforced when depth_multiplier < 1, and not an active constraint when
      depth_multiplier >= 1.
    depth_multiplier: Float multiplier for the depth (number of channels)
      for all convolution ops. The value must be greater than zero. Typical
      usage will be to set this value in (0, 1) to reduce the number of
      parameters or computation cost of the model.
    prediction_fn: a function to get predictions out of logits.
    spatial_squeeze: if True, logits is of shape [B, C], if false logits is
        of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
    reuse: whether or not the network and its variables should be reused. To be
      able to reuse 'scope' must be given.
    scope: Optional variable_scope.

  Returns:
    logits: the pre-softmax activations, a tensor of size
      [batch_size, num_classes]
    end_points: a dictionary from components of the network to the corresponding
      activation.

  Raises:
    ValueError: if 'depth_multiplier' is less than or equal to zero.
  """
  if depth_multiplier <= 0:
    raise ValueError('depth_multiplier is not greater than zero.')
  depth = lambda d: max(int(d * depth_multiplier), min_depth)
  with tf.variable_scope(scope, 'InceptionV3', [inputs, num_classes],
                         reuse=reuse) as scope:
    with slim.arg_scope([slim.batch_norm, slim.dropout],
                        is_training=is_training):
      net, end_points = inception_v3_base(
          inputs, scope=scope, min_depth=min_depth,
          depth_multiplier=depth_multiplier)

      # Auxiliary Head logits
      # 先把卷積、最大池化、平均池化的預設步長設為1
      with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
                          stride=1, padding='SAME'):
        aux_logits = end_points['Mixed_6e']
      # 在6e之後接一個5x5的平均池化，步長為3，padding位VALID,這樣尺寸從17x17x768變成5x5x768 
        with tf.variable_scope('AuxLogits'):
          aux_logits = slim.avg_pool2d(
              aux_logits, [5, 5], stride=3, padding='VALID',
              scope='AvgPool_1a_5x5')
         #接著連一個128通道的1x1卷積和一個768通道的的5x5卷積
          aux_logits = slim.conv2d(aux_logits, depth(128), [1, 1],
                                   scope='Conv2d_1b_1x1')

          # Shape of feature map before the final layer.
          kernel_size = _reduced_kernel_size_for_small_input(
              aux_logits, [5, 5])
          aux_logits = slim.conv2d(
              aux_logits, depth(768), kernel_size,
              weights_initializer=trunc_normal(0.01),
              padding='VALID', scope='Conv2d_2a_{}x{}'.format(*kernel_size))
          # 最後接一個輸出通道為num_classes的1x1卷積，不設定啟用函式和規範化函式
          # 輸出變成了1x1x1000 
          aux_logits = slim.conv2d(
              aux_logits, num_classes, [1, 1], activation_fn=None,
              normalizer_fn=None, weights_initializer=trunc_normal(0.001),
              scope='Conv2d_2b_1x1')
         # 消除tensor中前兩個為1的維度
          if spatial_squeeze: 
            aux_logits = tf.squeeze(aux_logits, [1, 2], name='SpatialSqueeze')
          end_points['AuxLogits'] = aux_logits


      # 之後就是正常的分類預測
      # Final pooling and prediction
      with tf.variable_scope('Logits'):
        kernel_size = _reduced_kernel_size_for_small_input(net, [8, 8])
        net = slim.avg_pool2d(net, kernel_size, padding='VALID',
                              scope='AvgPool_1a_{}x{}'.format(*kernel_size))
        # 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,
                             normalizer_fn=None, scope='Conv2d_1c_1x1')
        if spatial_squeeze:
          logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
        # 1000
      end_points['Logits'] = logits
      end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
  return logits, end_points