facenet专题3：train_sotfmax.py源代码解析--网络结构

接上文，下面我们来介绍具体的网络结构图，起始代码如下：

prelogits, _ = network.inference(image_batch, args.keep_probability,
                                         phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size,
                                         weight_decay=args.weight_decay)

根据上一章介绍，实际执行的是 network = importlib.import_module(models.inception_resnet_v1)，即导入models/文件夹下的inception_resnet_v1.py并命名为network，因此我们查看inception_resnet_v1.py下对应的inference函数：

def inference(images, keep_probability, phase_train=True, 
              bottleneck_layer_size=128, weight_decay=0.0, reuse=None):
    batch_norm_params = {
        # Decay for the moving averages.
        'decay': 0.995,
        # epsilon to prevent 0s in variance.
        'epsilon': 0.001,
        # force in-place updates of mean and variance estimates
        'updates_collections': None,
        # Moving averages ends up in the trainable variables collection
        'variables_collections': [ tf.GraphKeys.TRAINABLE_VARIABLES ],
    }
    
    with slim.arg_scope([slim.conv2d, slim.fully_connected],
                        weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
                        weights_regularizer=slim.l2_regularizer(weight_decay),
                        normalizer_fn=slim.batch_norm,
                        normalizer_params=batch_norm_params):
        return inception_resnet_v1(images, is_training=phase_train,
              dropout_keep_prob=keep_probability, bottleneck_layer_size=bottleneck_layer_size, reuse=reuse)

使用with slim.arg_scope对常用函数进行了定义，真正的网络结构为函数inception_resnet_v1：

def inception_resnet_v1(inputs, is_training=True,
                        dropout_keep_prob=0.8,
                        bottleneck_layer_size=128,
                        reuse=None, 
                        scope='InceptionResnetV1'):
    """Creates the Inception Resnet V1 model.
    Args:
      inputs: a 4-D tensor of size [batch_size, height, width, 3].
      num_classes: number of predicted classes.
      is_training: whether is training or not.
      dropout_keep_prob: float, the fraction to keep before final layer.
      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 logits outputs of the model.
      end_points: the set of end_points from the inception model.
    """
    end_points = {}
  
    with tf.variable_scope(scope, 'InceptionResnetV1', [inputs], reuse=reuse):
        with slim.arg_scope([slim.batch_norm, slim.dropout],
                            is_training=is_training):
            with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
                                stride=1, padding='SAME'):
      
                # 149 x 149 x 32
                net = slim.conv2d(inputs, 32, 3, stride=2, padding='VALID',
                                  scope='Conv2d_1a_3x3')
                end_points['Conv2d_1a_3x3'] = net
                # 147 x 147 x 32
                net = slim.conv2d(net, 32, 3, padding='VALID',
                                  scope='Conv2d_2a_3x3')
                end_points['Conv2d_2a_3x3'] = net
                # 147 x 147 x 64
                net = slim.conv2d(net, 64, 3, scope='Conv2d_2b_3x3')
                end_points['Conv2d_2b_3x3'] = net
                # 73 x 73 x 64
                net = slim.max_pool2d(net, 3, stride=2, padding='VALID',
                                      scope='MaxPool_3a_3x3')
                end_points['MaxPool_3a_3x3'] = net
                # 73 x 73 x 80
                net = slim.conv2d(net, 80, 1, padding='VALID',
                                  scope='Conv2d_3b_1x1')
                end_points['Conv2d_3b_1x1'] = net
                # 71 x 71 x 192
                net = slim.conv2d(net, 192, 3, padding='VALID',
                                  scope='Conv2d_4a_3x3')
                end_points['Conv2d_4a_3x3'] = net
                # 35 x 35 x 256
                net = slim.conv2d(net, 256, 3, stride=2, padding='VALID',
                                  scope='Conv2d_4b_3x3')
                end_points['Conv2d_4b_3x3'] = net
                
                # 5 x Inception-resnet-A
                net = slim.repeat(net, 5, block35, scale=0.17)
        
                # Reduction-A
                with tf.variable_scope('Mixed_6a'):
                    net = reduction_a(net, 192, 192, 256, 384)
                end_points['Mixed_6a'] = net
                
                # 10 x Inception-Resnet-B
                net = slim.repeat(net, 10, block17, scale=0.10)
                
                # Reduction-B
                with tf.variable_scope('Mixed_7a'):
                    net = reduction_b(net)
                end_points['Mixed_7a'] = net
                
                # 5 x Inception-Resnet-C
                net = slim.repeat(net, 5, block8, scale=0.20)
                net = block8(net, activation_fn=None)
                
                with tf.variable_scope('Logits'):
                    end_points['PrePool'] = net
                    #pylint: disable=no-member
                    net = slim.avg_pool2d(net, net.get_shape()[1:3], padding='VALID',
                                          scope='AvgPool_1a_8x8')
                    net = slim.flatten(net)
          
                    net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
                                       scope='Dropout')
          
                    end_points['PreLogitsFlatten'] = net
                
                net = slim.fully_connected(net, bottleneck_layer_size, activation_fn=None, 
                        scope='Bottleneck', reuse=False)
  
    return net, end_points

inception_resnet_v1的网络结构如下图：

注意几点，代码通过net = slim.repeat(net, 5, block35, scale=0.17)来完成resnet网络的插入，通过reduction_a和reduction_b来实现reduction模块，这里不再详述，最后返回提取的特征net以及字典end_points，end_points记录了各个中间层的结果。

接下来调用slim的全连接层slim.fully_connected生成全连接层：

        logits = slim.fully_connected(prelogits, len(train_set), activation_fn=None,
                                      weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
                                      weights_regularizer=slim.l2_regularizer(args.weight_decay),
                                      scope='Logits', reuse=False)

slim.fully_connected的第二个参数是输出的单元数len(train_set)，由上文数据加载部分的介绍可以知道len(train_set)为所有人的个数，接下来同样对prologits处理，对其进行单位化处理：

embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')

对输出进行单位化处理。